Search

Total Result(s) Found: 151

Deep-sea sediments off the Al Wajh Carbonate Platform, Red Sea - Sample preparation and analysis

Energy Resources and Petroleum Engineering

Professor Volker Vahrenkamp’s research team is currently recruiting for an up to 6-month internship joining the Carbonate Reservoirs Studies Group (CaResS Geology) at King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia. Project description: The Red Sea records climatic and associated sea-level and hydrological changes throughout the Quaternary. Extreme fluxes of windblown dust reflect high winds and extreme aridity in the region associated with glacial phases, meanwhile, geochemical data demonstrate enhanced humidity associated with interglacial phases and sea-level highstands. In the northern Red Sea, these environmental changes have influenced the development of steep-sloped shallow-water carbonate platforms and fringing reefs. Al Wajh is a land-attached carbonate platform in the northern Red Sea; it is almost completely rimmed by a reef shoal belt and characterised by a large and deep lagoon. Along the Red Sea basin, the deep-sea sediments are mainly controlled by the pelagic sedimentation and a background aeolian and sporadic fluvial input. While the deep-sea sediments from the southern and central regions near the axial trough and the African margin have been the most studied, the climate-driven deep-sea sedimentation basin off the Al Wajh carbonate in the northern region remains unclear.

BAS/1/1399-01-01

juliana.guzmangonzalez@kaust.edu.sa

Marine Sedimentology, Micro-palaeontology, Carbonate Geology

The internship will focus on Pleistocene–Holocene marine microfossil analysis for further geochemical measurements and palaeoenvironmental applications. The project includes preparing sediment samples for the recovery of calcareous microfossils and isolation of the terrigenous sediment fraction, the collection and identification of foraminifera and planktic gastropods (pteropods) as well as characterizing samples geochemically. Also included are researching the taxonomy of Red Sea foraminifera and pteropods to identify the species that are targets for geochemical analyses. Fields of study: sedimentology, micropalaeontology, geosciences.

Energy Resources and Petroleum Engineering

Physical Sciences and Engineering

Ali I. Al-Naimi Petroleum Engineering Research Center

Screening semiconductors for photoelectrochemical transistors

Program:

BioEngineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Sahika Inal

Sustainable membrane materials and separation processes for pharmaceuticals and the environment

Program:

Chemical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Gyorgy Szekely

Separation processes play a remarkable role in the chemical and pharmaceutical industries, where they account for 50 to 70% of both capital and operational costs. Organic synthesis in the chemical and pharmaceutical industry are frequently performed in organic solvents and consist of products with high added value that should be removed from the organic solvents. Our natural waterways and industrial wastewater are contaminated with pesticides, dyes, oil and nanoplastics, which also need to be separated out.Nanofiltration is an emerging technology which allows the isolation and separation of solutes in water and organic solvents. The development of nanofiltration membranes stable in outdoors or harsh environments (e.g. polar aprotic solvents, extreme temperature, pressure and pH) is of utmost importance. Robust nanofiltration membranes will be fabricated exhibiting superior chemical stability and selectivity compared to commercial polymer membranes. Depending on the interests and background of the visiting student, the focus of the project will be fine-tuned towards polymer synthesis, pharmaceutical synthesis, membrane separations, materials fabrication or sustainability assessment.

BAS/1/1401-01-01

gyorgy.szekely@kaust.edu.sa

Organic solvent nanofiltration, membrane fabrication, membrane separations, hybrid processes

Engineering in Pharmaceutical Industry

The student will acquire soft skills such as team working, project and time management, giving oral presentations. By the end of the traineeship the student will have a deep understanding of membrane separations, particularly in nanofiltration. Practical and theoretical aspects of process design, surface modification techniques and polymer chemistry techniques will be acquired. Depending on the background and interest of the student, sustainable product design and assessment skills will also be acquired.

Chemical Engineering

Physical Sciences and Engineering

Graduate or Undergraduate

Non-terrestrial Communication System for Aerial-based Object Recognition and Positioning

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Basem Shihada

Modern aerial-based technology offers a promising way to ensure sustainability and increase productivity in the outdoor economy, such as agriculture, environment monitoring, and infrastructure inspection. UAVs play a crucial role in modern intelligent systems. Equipped with cameras and sensors, UAVs fly over large areas and capture high-resolution aerial imagery to provide real-time object information. Moreover, the wireless transceivers equipped on UAVs facilitate data collection and forwarding services. However, in remote desert areas, traditional terrestrial networks and electricity infrastructure are often unavailable. Satellite connections are not suitable due to high latency and expensive service charges. Using UAVs to set up a non-terrestrial wireless communication system is a more practical and cost-effective solution. The aim of this project is to utilize civilian single-lens drones to develop a cost-effective system for detecting and tracking objects from high-altitude perspectives and establish an energy-efficient non-terrestrial communication system. The student will focus on creating a robust model tailored for high-altitude object recognition, developing a positioning system that can handle the unique challenges of desert environments, and conducting thorough evaluations to ensure the wireless communication system is energy-efficient and sustainable.

BAS/1/1601-01-01

lau.pong@kaust.edu.sa

Computer Vision, Drones, Object recognition, Localization, Data training

Computer Engineering and Computer vision

1. Training a new deep learning model for object recognition from the UAV perspective. 2. Developing an object positioning and tracking system for desert environments from the UAV perspective. 3. Evaluating the energy consumption of building a non-terrestrial communication system by UAVs for object recognition and positioning.

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Leveraging Non-Terrestrial Platforms

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Basem Shihada

Solar cells with Unconventional Shapes

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Nazek Elatab

Conservative Linear Multistep Methods For Time-dependent PDEs

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

David Ketcheson

Statistical Inference for High Dimensional Models with Applications to Imaging Genetics

Program:

Statistics

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Conceptual design of membrane processes

Program:

Chemistry

Division:

Physical Sciences and Engineering

Faculty Name:

Zhiping Lai

Investigating the Design and Engineering of Nanobodies for Advanced Biomedical Applications

Program:

BioEngineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Magnus Rueping

Cell-free Protein Synthesis of Next-Generation Therapeutics

Program:

BioEngineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Magnus Rueping

Nanobiomarine: Integrating Nanowire-Enhanced Beneficial Microorganisms for Advanced Coral Restoration

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Alexandre Rosado

Large-Scale Volumetric Mesh Visualization and Analysis

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Markus Hadwiger

Membrane development for sustainable separations

Program:

Chemical Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Suzana Nunes

Uncovering and Addressing Bias in LLM Interactions

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Roberto Di Pietro

Accelerated simulation of reactive flows using deep neural networks

Program:

Mechanical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Hong Im

Unlocking the Secrets of the Extreme Microbiome: Biotechnological Frontiers on Earth and Beyond

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Alexandre Rosado

Extremophiles are specialized microorganisms that thrive under severe conditions, such as extreme temperatures, pH levels, and pressures. These organisms are fascinating subjects for scientific research and promising candidates for diverse biotechnological applications. Saudi Arabia's harsh environments, from deserts to volcanic areas, are home to these resilient organisms. These unique settings, resembling extraterrestrial landscapes, provide exceptional opportunities to leverage extremophiles for biotechnological innovations. Our project aligns with Saudi Vision 2030's goal of promoting sustainable economic growth. Our project seeks to tap into this potential by developing a multidisciplinary framework that combines advanced isolation techniques, omics technologies, and state-of-the-art facilities at KAUST. We aim to isolate novel microbial strains, explore our culture collection, and uncover their metabolic functions to pave the way for new biotechnological applications and enhance our understanding of life's adaptability. Our research extends to evaluating these extremophiles' potential to support sustainable goals on Earth and their implications in astrobiology and space research. Complementing this, our ongoing study of space-related microorganisms further expands the scope and impact of our research.

BAS/1/1096-01-01

junia.schultz@kaust.edu.sa

Microbiology, Extremophiles, Astrobiology, Biotechnology

Microbiology

-Isolation and Characterization of Novel Extremophile Species: Deliver a curated collection of newly isolated extremophile species from Saudi Arabia's unique environments, such as volcanic regions, hot springs, hydrothermal vents, and hyper-arid deserts, among others. This deliverable involves using advanced isolation techniques to culture these organisms, followed by genomic and phenotypic characterization to understand their unique adaptations and capabilities. We are aiming for further biotechnological exploration and contributing to the global extremophile database. -Functional Genomics and Metabolic Pathway Analysis: Conduct comprehensive omics analyses (genomics, transcriptomics, proteomics, metabolomics) to elucidate the metabolic pathways and biological functions that enable extremophiles to survive under extreme conditions. This deliverable aims to identify genes, proteins, and metabolites associated with resilience to extreme environmental stresses, which could be harnessed for biotechnological applications such as bioremediation, pharmaceuticals, or industrial enzymes. -Development of Biotechnological Applications and Sustainability Assessment: Utilize the data from the isolation and omics studies to develop biotechnological applications that leverage the unique properties of extremophiles. This could include engineering extremophilic enzymes for industrial processes that require high temperatures or acidic conditions or developing extremophile-based biofilters for environmental cleanup. Additionally, assess these applications' sustainability and economic viability in alignment with Saudi Vision 2030's objectives for economic diversification and environmental sustainability. This deliverable would also explore the potential implications of extremophile research in astrobiology and space exploration, enhancing our understanding of life's possibilities beyond Earth.

BioScience

Biological and Environmental Sciences and Engineering

Predicting Bacterial Antimicrobial Resistance Phenotypes from Genomic Biomarkers

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Danesh Moradigaravand

Design and performance evaluation of various emerging 6G wireless communication technologies

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Mohamed-Slim Alouini

Explainable Artifical Intelligence Methods for Wellbore Damage Zone Prediction

Program:

Energy Resources and Petroleum Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Thomas Finkbeiner

Despite the overwhelming interest in artificial intelligence, a key hurdle remains for the large-scale adoption of ML-solutions; this is the “black-box” nature of the predictions where a model returns a value but with no obvious reasoning or tracking process of how the value was obtained. In this project, we shall focus on looking inside the black-box and producing not only the model’s prediction but also the reasoning the model took to deliver a given predicted value. This project aims to address this challenge through the use of eXplainable Artificial Intelligence (XAI) methodologies. The selected student will get the opportunity to work at the forefront of artificial intelligence methods, identifying how models come up with the solutions they offer and utilising that to further enhance the methods. To illustrate the benefit of XAI, we will focus on the use case of interpreting natural and induced damage zones at the wellbore wall and in the near wellbore region (e.g., natural fractures, drilling-induced tensile fractures, wellbore breakouts) from electrical, optical and acoustic well image logs. Naturally occurring fracture and fault systems play a key role in governing subsurface flow. Often, major flow paths are associated with large faults and their damage zones. Thus, detailed characterization of pre-existing fault and fracture networks, in terms of orientation, intensity and aperture, is vitally important for several industrial applications, such as water supply, hydrocarbon production, geothermal energy production, radioactive waste management, and carbon capture and storage. Drilling induced damage (drilling-induced tensile fractures and stress-induced borehole breakouts) can be of primary importance to depict the subsurface in-situ stress orientation and magnitude and, thus, for an optimal planning of well trajectory and monitoring of the wellbore stability. The numerical analysis will begin by training multiple ML models to predict the presence of a damaged zone and whether it is an open or closed fault. A range of models will be considered from highly interpretable decision trees to highly complex convolutional neural networks. Numerous XAI components will be investigated to provide a reasoning behind each models’ predicted values. This reasoning will be compared against our knowledge of the geological systems, allowing us to analyse if there is a physical meaning behind the model. This aids our understanding if and when we can trust a model’s prediction and the value of using it. The workflow developed in this project will be directly applicable to all ML-assisted log interpretation algorithms. A key outcome from this internship is to provide us with a clear understanding of which ML method is most suitable for wellbore damage zone prediction from wellbore image logs.

BAS/1/1421-01-01

claire.birnie@kaust.edu.sa

Computer Vision; eXplainable AI; Machine Learning, wellbore damage zone interpretation

Engineering or Computer Science

1. Algorithm development with Python to import digitized wellbore image log and related damage zone interpretations; 2. Develop a ML model for damage zone identification, under guidance; 3. Investigate explainable AI methodologies to determine how the ML model arrives at a given prediction; 4. Analyse the XAI results and tie these results to physical interpretations made by petrophysicists; 5. Assist with manuscript write-ups for publication.

Energy Resources and Petroleum Engineering

Physical Sciences and Engineering

Ali I. Al-Naimi Petroleum Engineering Research Center

Learning to Cooperate in Multi-robot Task Allocation

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Shinkyu Park

Imagine robots self-organizing into large groups to assist people with physically demanding tasks, leveraging their core capabilities in perception, manipulation, and navigation to interact with the physical world. To successfully complete a given mission as a team, these robots must make their own decisions to allocate and carry out tasks defined in the mission and cooperate with one another when the task requires it. We realize this capability in multirobot systems through a learning-based paradigm, designing computational models to train a large number of robots to work as a team. Achieving a high level of autonomy in distributed information processing, decision-making, and collaborative manipulation is crucial. To enable a high level of cooperation among a large number of robots, the project aims to build computational models based on deep reinforcement learning (DRL). These models are designed to enhance the robots' ability to cooperate in carrying out multiple tasks using their perception, manipulation, and navigation skills. Additionally, the project's goal is to implement these models on a multi-robot platform and validate the effectiveness of the models through lab experiments.

BAS/1/1695-01-01

shinkyu.park@kaust.edu.sa

Robotics, Machine Learning, Reinforcement Learning

Electrical and Computer Enginnering

The main objective of this project is to implement multi-agent DRL in a team of mobile manipulators and validate our DRL implementation through lab experiments. Students are expected to collaborate with lab members to explore new ideas and implement them on physical robotic systems. To fulfill the requirements of the project, students should have solid experience working with robotic systems and the Robot Operating System, as well as confidence in C++/Python programming. Experience with reinforcement learning is a plus. The model design and experiment reports are expected to be delivered at the end of the internship program.

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Polkadot Graph Analysis

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Roberto Di Pietro

Encrypted Traffic Classification

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Roberto Di Pietro

A notable trend in the rapidly evolving mobile technology domain is the increasing reliance on encrypted network packets to strengthen privacy and security. Nevertheless, certain unencrypted elements, such as packet size and other critical Internet functionalities, remain exposed despite this encryption. This project is dedicated to harnessing these aspects by developing a tool adept at classifying encrypted network packets. Utilising Deep Learning models, the tool is designed to categorise the traffic on a network and deduce the types of applications on mobile phones. Positioned at the intersection of network security and AI-driven analysis, this innovative project emphasises developing and refining cutting-edge deep-learning models. These models are specifically designed to pinpoint the applications generating network traffic despite encryption. This capability is made possible by identifying unique patterns and traits within the data flow indicative of specific applications installed on a smartphone. This project is committed to privacy, and ethical considerations are a vital aspect of this project. While encrypted packets bolster security, the ability of tools to categorise their contents and deduce installed applications poses privacy challenges. The project addresses these concerns by offering a solution that respects user privacy while yielding valuable insights into network traffic. Therefore, the project approaches these challenges with a solution that respects user privacy while providing valuable insights into network traffic. This balance of privacy with technological advancement sets a new standard in network traffic analysis, underscoring the project's innovative and conscientious approach.

BAS/1/1701-01-01

roberto.dipietro@kaust.edu.sa

Security, Encrypted traffic, Classification, Machine Learning

Computer Science

The expected outcome of this project is twofold. The student is expected to design an innovative tool that can efficiently categorise mobile traffic by application and deduce the specific applications installed on each smartphone. Secondly, the student will work closely with team members to develop this tool and comprehensively analyse the traffic data gathered.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Resilient Computing and Cybersecurity Center

Materials Engineering for Soil Amendment in Saudi Arabia

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Himanshu Mishra

Modeling human early development with stem cell-based integrated embryo-like models

Biological and Environmental Sciences and Engineering

Faculty Name:

Mo Li

A peculiarity of human reproduction is the high rate of developmental failure before and after the time of embryo implantation. Understanding why early pregnancy failures occur is a significant question in the field but remains challenging due to the technical and ethical complexities involved in studying these developmental stages. Pluripotent stem cells have recently been used to construct various early developmental models that hold great promise in unlocking the mysteries of early human development and facilitating new reproductive therapies. Human blastoids are one such valuable model for studying early human development. They can be derived from naïve pluripotent stem cells and consist of all three lineages of the preimplantation blastocyst. Current methods using static batch culture to generate human blastoids have limitations, including (i) low yield, (ii) the need for cell aggregation, which complicates genetic or drug screens, (iii) reproducibility issues due to an uncontrolled cellular environment, and (iv) the requirement for Aggrewell or similar confinements that can exert unnatural geometrical strains on blastoids. Additionally, current blastoid models exhibit instabilities in the development of post-implantation lineages. The candidates of this VSRP project are expected to work on developing methods for large-scale production of human blastoids under strict environmental control, improving post-implantation lineage differentiation of blastoids, and characterizing gene expression in a spatially resolved manner in single cells. The successful outcome of the project is expected to significantly advance the development of in vitro human embryo models that faithfully recapitulate specific intricacies of embryogenesis. These models have the potential to be translated into applications in regenerative medicine, disease modeling, and personalized therapies.

BAS/1/1080-01-01

arun.chandrasekaran@kaust.edu.sa

blastoid, pluripotent stem cell, human development, reproductive biology, embryogenesis, regenerative medicine

stem cell, developmental biology, bioengineering

1. Developing methods for large-scale production of human blastoids under strict environmental control 2. Improving post-implantation lineage differentiation of blastoids 3. characterizing gene expression in blastoids in a spatially-resolved manner in single cells

BioEngineering

Biological and Environmental Sciences and Engineering

Parameter-free optimization, universal prediction, and Kolmogorov complexity

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Francesco Orabona

Training dynamics of Adam

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Francesco Orabona

Coral Microbiology and probiotics

Program:

Marine Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Raquel Peixoto

Natural Deep Eutectic Solvents for water remediation

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Geert-Jan Witkamp

Light-induced metal ion (de)complexation

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Andreia Farinha

Bioaccumulation of emerging contaminants in Red Sea coral reef organisms

Program:

Marine Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Susana Carvalho

Joint models for longitudinal and survival data

Program:

Statistics

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Haavard Rue

Continuous-mode SandX Rector Automation

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Himanshu Mishra

Reactions of lung surfactants at the air–water interface

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Himanshu Mishra

Quantifying microbial diagenesis in shallow marine carbonate sediment using CT-scan

Program:

Earth Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Volker Vahrenkamp

Geochemical investigation and abrasion experiments to decipher the origin of lime mud

Faculty Name:

Volker Vahrenkamp

Impact of mangrove ecosystems on carbonate sediment: integration of carbonate chemistry and petrography.

Faculty Name:

Volker Vahrenkamp

Unraveling the molecular basis of coral symbiosis and bleaching

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Manuel Aranda Lastra

Coral-algae symbiosis is essential for the survival and growth of corals and for the functioning of coral reef ecosystems. However, this symbiosis can be disrupted by various environmental stressors, such as high temperature, pollution, or disease. When this happens, the corals lose their algae and turn white, a phenomenon known as coral bleaching. Bleached corals are more vulnerable to mortality and may not recover their symbionts if the stress persists. Understanding the interactions between coral hosts and their algal symbionts under different environmental conditions is crucial for developing conservation strategies. At KAUST, we study these interactions at different levels, from the molecular underpinnings to the ecological contexts. We seek motivated students who want to learn more about this symbiotic relationship. The students will be able to learn various techniques and skills related to coral biology, molecular biology, and bioinformatics.

BAS/1/1036-01-01

guoxin.cui@kaust.edu.sa

coral symbiosis, coral bleaching, stress response

Ecological Genomics

This interdisciplinary project comprises wet-lab work (80%) and soft skills (20%). Soft skills are not mandatory but can be acquired during the project through the intern's initiative. The project deliverables include: 1) Regular plan for growth and proliferation of sea anemones 2) Setting up experiments 3) Optimize existing protocols (nucleic acid extraction, HCR, FISH, etc.) 4) Basic data analysis (RNASeq, DNAseq,) 5) Consolidated report at the end of the internship The intern is expected to have experience in the following areas: 1) Basic wet laboratory skills 2) Animal care procedures 3) Molecular biology techniques such as RNA isolation and DNA isolation 4) Basic knowledge of UNIX and soft skills (considered advantageous) Overall, the intern should be proactive, eager to broaden their interests and meet with the principal investigator every two weeks to discuss research progress.

BioScience

Biological and Environmental Sciences and Engineering

Graduate or Undergraduate

Red Sea Research Center

Coral reef ecology in a changing environment

Program:

Marine Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Maggie Johnson

Coral reefs are ecologically important ecosystems that are threatened by local human impacts, such as nutrient pollution and overfishing, and by global environmental change, such as ocean acidification and ocean warming. As a result, coral reefs have been in decline across the planet. In order to understand the future for coral reefs in the Red Sea, we must first understand the current status of reefs along the coast of Saudi Arabia, and then identify potential impacts of various environmental stressors. The goal of this project is to contribute to the broader research goals of the Global Change Ecology lab at KAUST, under the supervision of Professor Maggie Johnson. We are seeking students interested in studying coral reef community structure and function in present day conditions, monitoring how reefs in the Red Sea are changing over space and time, and contributing to field and lab experiments that aim to identify impacts of different environmental stressors on key reef species. This research presents the opportunity to develop projects tailored to the specific interests of students. Examples of possible projects include, but are not limited to, quantifying the cover and health of corals and algae on central Red Sea coral reefs, deploying instruments and analyzing data to evaluate variability in important environmental parameters (temperature, pH, dissolved oxygen), and conducting targeted field and lab experiments to identify effects of warming temperatures (or changing pH or dissolved oxygen) on calcifying algae and corals. This is an exciting opportunity to contribute to ongoing work and to develop new research projects in the area of human and environmental impacts on coral reefs. The Global Change Ecology lab is committed to building an inclusive community and research environment and encourages applicants from all walks of life.

BAS/1/1102-01-01

lucia.bravo@kaust.edu.sa

Red Sea, Coral Reef, Ecology, Marine Science, Global Change, Human Impacts, Coral, Seaweed, Ocean Acidification, Ocean Warming, Deoxygenation, Overfishing, Nutrient Pollution

Marine Science, Benthic Ecology, Coral Reef Ecology, Phycology

The student is expected to contribute to the research goals of the project, and to lead or participate as a co-author in a peer-reviewed scientific publication.

Marine Science

Biological and Environmental Sciences and Engineering

Graduate or Undergraduate

Red Sea Research Center

Deep Learning for Visual Computing (Computer Vision, Machine Learning, Graphics)

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Peter Wonka

Safety-Guaranteed Planning and Control for Autonomous Underwater Robots

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Shinkyu Park

With 2000km of coral reef and marine life surrounding it, the Red Sea is a rich and diverse ecosystem. Due to its ecological and economic importance, persistent monitoring of its key areas is critical for marine biology research, economic development, and environmental protection. However, long-term survey and observation of extensive marine environments are extremely labor-intensive and hence require new technological development. There have been a numerous efforts made in research and development of robots designed to autonomously survey and collect data in remote areas that are hard to access by human divers or require long-term and repeated monitoring. However, there remain technical challenges in implementing long-term autonomy in underwater robotics to allow a robot to navigate in close proximity of marine lives over an extended period of time while ensuring absolute safety and not interfering with their natural habitats. In this project, we explore learning-based planning/control approaches that combine optimization-based design and data-driven machine learning methods. Leveraging the optimal feedback control and reinforcement learning, we aim to develop a framework that enables the robot to 1) learn how the environmental characteristics (light condition, current speed, etc.) affect its navigation performance and 2) adaptively revise its control policies to safely and graciously navigate around marine habitats.

BAS/1/1695-01-01

shinkyu.park@kaust.edu.sa

Robotics, Feedback Control Systems, Optimization, Machine Learning

We adopt computational methods from optimization and reinforcement learning to design libraries that allow robots of various types to safely navigate in underwater environments for automated data collection applications. The students are expected to collaborate with the lab members to explore creative ideas and implement them on the underwater robot being developed in the robotics lab at KAUST. To fulfill the requirements of the project, the students are expected to have experience working with robotic systems/software and confidence in Python programming. Software library design and experiment reports are expected to be delivered at the end of the internship program.

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

How does Federated Learning work in the real world?

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Marco Canini

Federated learning (FL) is a novel paradigm enabling distributed machine learning (ML) model training, while ensuring that training data remains on individual clients. The increasing need for privacy makes FL a highly promising method spearheading the future of ML. Although theoretically elegant, FL faces significant hurdles when it comes to real-world implementation. The key obstacle towards wider proliferation of FL is an inherent heterogeneity of real-world settings. Clients that may participate in FL range from computationally limited Internet of Things (IoT) devices, over low-end smartphones, to high-end multicore GPU-powered smartphones and beyond. Furthermore, devices may host a range of different applications that are simultaneously competing for hosts’ limited resources. In this work we will for the first time quantify the effects of heterogeneity on FL performance in a real-world testbed. We will first conduct a survey of edge devices that are suitable for FL and assemble a representative, yet diverse, testbed at our KAUST premises. Building upon the existing open-source solutions, we will then program a FL training framework enabling rapid prototyping, experimentation, and measurements within our testbed. We will then conduct a set of experiments geared towards profiling the effect of device hardware, software, and usage heterogeneity of FL training accuracy, convergence time, fairness, and energy use. Finally, we will analyze the results and extract guidelines for efficient FL in heterogeneous environments.

- Physical testbed comprising a range of IoT and mobile devices. - Programming framework for FL experimentation and evaluation. - Executable scenarios encompassing different use-cases and levels of the underlying system heterogeneity. - Report on the experimental results with metrics designed to profile the effect of system heterogeneity on holistic performance of FL. - Guidelines for advancing FL in heterogeneous environments.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Resilient Computing and Cybersecurity Center

Dexterous Robot Manipulation using Physics Engine

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Shinkyu Park

With the advance in sensing, actuation, and mechanical design, the robots are becoming more capable of performing complex and high-precision tasks ranging from autonomous driving in urban cities to handling packages in fulfillment centers. Control and planning of robot motion in real-world environments require high-fidelity models to simulate how the robot's motion impacts physical objects before they take action. Many well-established approaches in robotics rely on mathematical models due to their analytic tractability; however as robotic systems become complex and are required to interact in physical environments, we face limitations in finding analytically tractable models and begin to resort to new models that leverage the powerful computational resources embodied in robotic systems. To address the challenges in robot operation in physical environments, in this project, we explore the idea of building computational models based on physics engines and design feedback algorithms to autotune parameters of the model whenever the robot detects the discrepancy between the simulation and its experience in the physical world -- to reduce the sim-to-real gap. As key applications, we imagine to apply outcomes of the project to enable robotic manipulators to carry out the tasks in assembly lines and research laboratories that are labor-intensive and require dexterous skills.

BAS/1/1695-01-01

shinkyu.park@kaust.edu.sa

Robotics, Physics Simulation, Feedback System Design, Computer Science

Electrical and Computer Enginnering

This project aims to adopt a physics engine to build computational model and examine the fidelity of the model through experiments with manipulators in the robotics lab at KAUST. The students are expected to collaborate with the lab members to explore creative ideas and implement them on physical robotic systems. To fulfill the requirements of the project, the students are expected to have experience working with robotic systems/software and confidence in Python programming. The model design and experiment reports are expected to be delivered at the end of the internship program.

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Siliciclastics in Al Wajh carbonate lagoon

Program:

Earth Science and Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Volker Vahrenkamp

Seeing the invisible – air flow around droplet upon impact

Program:

Mechanical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Daniel Daniel

Engineering an isothermal amplification strategy for ultrasensivite and quantitative detection of microRNA cancer biomarkers

Program:

BioEngineering

Program:

Materials Science & Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Dana Alsulaiman

MicroRNA (miRNA) are short (~22 nt) non-coding RNA that have emerged as highly promising diagnostic and prognostic biomarkers due to their gene regulatory functions and dysregulated expression profiles in many diseases including cancer. While promising, their absolute quantification is challenging due to their short lengths, low circulating concentrations, and high sequence homology among family members. The gold standard method for miRNA detection, based on reverse-transcription qPCR, involves complex multistep procedures and requires thermal cycling, trained personnel and bulky equipment. This project aims to develop a novel quantitative and isothermal strategy for ultrasensitive detection of miRNA at the point-of-care, i.e. in a simple, cost-effective and efficient manner from minute volumes of a patient's biological fluid sample. This project will include advancements in biomolecular engineering, biomaterials development, and biochemistry. Ultimately, this project will lead to the development of highly sensitive point-of-care biosensors for cancer diagnosis, prognosis or monitoring based on multiplex detection of microRNA cancer biomarkers from a minimally-invasive 'liquid biopsy' test.

BAS/1/1426-01-01

erol.hasan@kaust.edu.sa

microRNA, cancer, diagnostics, biosensing, biomarkers

Bioengineering and Material Science

The aim of the project will be to deliver the following main objectives: - Develop an isothermal amplification methodology and strategy for miRNA detection - Characterize the analytical performance of the developed assay (sensitivity, specificity, dynamic range, etc) - Optimize the analytical performance and validate the assay with synthetic and clinical samples - Submit a report on the preliminary results which will be used as a platform for a peer-reviewed research article

BioEngineering

Physical Sciences and Engineering

Graduate or Undergraduate

Unraveling the molecular basis of immune signaling

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Stefan Arold

Protein Synthetic Biology

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Stefan Arold

Contextualized Embeddings for Biomedical Data

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Ricardo Henao Giraldo

Characterization of IL11-deficiency in humans

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Bruno Reversade

Security analysis of Docker-based containerized environments

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paulo Esteves-Verissimo

Operating System (OS) virtualization, also known as container-based virtualization, has gained momentum over the past few years thanks to its lightweight nature and support for agility. However, its compelling features come at the price of a reduced isolation level compared to the traditional host-based virtualization techniques, exposing workloads to various faults, such as container escape. Those faults might be manifested as host OS bugs, container runtime vulnerabilities, and/or poor container deployment choices and profile configuration. The latter aspect is particularly critical as deployment and security configuration choices often need to be relaxed to meet the operational requirements of running applications leading hence to a widened attack surface. For example, if a container configured to be run with full privilege (or even with an extended set of capabilities) gets compromised, the latter might take control both of the hosting machine and the co-residing containers. The objective of this project is to perform a security assessment of containerized environments in order to unveil potentially dangerous container deployment and configuration options. This would enable identifying critical containers to closely monitor their behavior and detect erroneous security states as they occur. For more concrete discussions, we consider Docker, which stands out as the most adopted container technology.

BAS/1/1696-01-01

ali.shoker@kaust.edu.sa

Virtualization, container security, Docker, Linux privileges,

Security, OS cybersecurity, virtualization, Docker

The expected outcome of this project is twofold. First, the student should come up with several real-life scenarios showcasing how potentially dangerous Docker container configuration and deployment options might be exploited in case of container compromise. Second, the student will collaborate with the team members to write a paper summarizing the findings exemplified by the previously defined scenarios.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Resilient Computing and Cybersecurity Center

Monitoring containerized environments for security state error detection

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paulo Esteves-Verissimo

Operating System (OS) virtualization, also known as container-based virtualization, has gained momentum over the past few years thanks to its lightweight nature and support for agility. However, its compelling features come at the price of a reduced isolation level compared to the traditional host-based virtualization techniques, exposing workloads to various threats, such as container escape. In those threats, compromised or rogue containers might exploit existing vulnerabilities or poor container deployment choices to successfully inject security state errors (e.g., breaking out of the namespace isolation mechanisms and running as a root at the host level). To effectively detect those security state errors, we would like to monitor containers at the system call level as the latter accurately maps processes to their activities. Hence, the objective of this project is firstly to study and compare existing monitoring tools (generic such as strace, or container-specific such as sysdig) and select the most suitable one according to a set of criteria (e.g., resource consumption, offered monitoring options). Secondly, the chosen monitoring tool will be instrumented for different scenarios (benign and anomalous settings) to generate relevant datasets capturing the behavior of containers with respect to a set of planned (malicious and benign) activities within a time window. The datasets will be subsequently vetted to extract critical system calls and execution paths that need to receive attention in the runtime detection process.

BAS/1/1696-01-01

ali.shoker@kaust.edu.sa

Containers, Docker security, container monitoring

Operating Systems, Security, Containers

Put in place and document an efficient container monitoring mechanism that will be used subsequently in conjunction with an error detection artifact to uncover erroneous security states in Docker-based containerized environments. Using the established monitoring mechanism, the student will run a set of planned container activities and build datasets that will be used for system call and execution path analysis.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Resilient Computing and Cybersecurity Center

Trees, Algebras, and Differential Equations: Extending the B-series.jl package for numerical analysis of initial value problems

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

David Ketcheson

Seawater Reverse osmosis (SWRO) pretreatment impact on microbial growth potential

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Johannes Vrouwenvelder

ClO2 for biofouling control in Seawater Reverse Osmosis

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Johannes Vrouwenvelder

Breaking the Vehicle Over-The-Air Update System

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paulo Esteves-Verissimo

A modern vehicle is composed of around 100 Electronic Control Unit (ECU) connected via several types of networks. An ECU is an embedded device, similar to a RaspberryPI, running an operating system, e.g., Linux-based or real-time OS, on top of which different software and firmware may run, depending on the application. Due to the imperfection of humans, software can have faults and vulnerabilities, which can lead to catastrophic failures that threatens human lives. This makes the manufacturers liable to such failures and thus often caused millions of vehicles recalls for repair. A smart solution is to take advantage of the vehicle connectivity to the Internet and surrounding and perform Over-The-Air (OTA) software and firmware when needed, very similar to smart phone software updates. It is clear that this process is critical and can have negative consequences if the OTA update system unreliable and insecure. We have introduced an OTA protocol and corresponding Proof of Concept (PoC) implementation that ensure an end-to-end chain of trust between all stakeholders: the manufacturer, suppliers, brokers, and the vehicle.

BAS/1/1696-01-01

ali.shoker@kaust.edu.sa

The Update Framework, Chain-of-Trust, Security, Over the Air software/firmware updates.

Connected Vehicles, Autonomous Vehicles, Software updates, Over-the-Air (OTA), security

The goal of this project is to demonstrate some attacks by running the PoC on embedded devices or even in a real vehicle. The role of the intern will be to understand the system and extend the demos we have already done in software, and experiment them empirically on real relevant devices. The objectives are to (1) raise awareness to the consequences of not doing OTA updates right, (2) to gauge if our system is secure empirically (3), and to improve it if is not.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Resilient Computing and Cybersecurity Center

Vehicle Intrusion Resilience Systems in Action

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paulo Esteves-Verissimo

A modern vehicle is composed of around 100 Electronic Control Unit (ECU) connected via several types of networks. An ECU is an embedded device, similar to a RaspberryPI, running an operating system, e.g., Linux-based or real-time OS, on top of which different software and firmware may run, depending on the application. Due to the imperfection of humans, software can have faults and intrusions, which can lead to catastrophic failures that threatens human lives. A Fault and Intrusion Resilient System (FIRS) is a vehicle middleware that can mask the effect of a failure or intrusion. Contrary to Intrusion Detection and Protection Systems, FIRS ensures the continuation of the function despite intrusions. FIRS works as follows: it allows an application to run different replicas on different ECUs simultaneously. For each function executed by the application, an agreement is collected from a majority of ECUs through the (in-vehicle) network, and the corresponding output is returned. As long as the majority is not compromised, the integrity of the returned output is guaranteed despite the existence of faults or intrusions in the rest of ECUs. We have an implementation of a FIRS protocol that we are experimenting on Omnet++ simulator.

BAS/1/1696-01-01

ali.shoker@kaust.edu.sa

Intrusion Resilience Systems (IRS) for modern vehicles, CAN Vehicular networks,

Intrusion Resilience, Intrusion detection and prevention, Vehicular networks, CAN, Byzantine Fault Tolerance

The goal of this project is to create a demo that validates the FIRS on a real hardware and software. The intern will build a small testbed of networked embedded devices, e.g., RaspberryPIs or ECUs. Two network types are of particular importance: (1) the widely used broadcast-based Control Area Network (CAN), can be built using RaspberryPIs and CAN transceivers; and (2) the more recent efficient Ethernet for Automotive that, as the name indicates, has similarities to the Ethernet protocols in IT networks. The objectives of the work are to understand how FIRS behaves empirically, build the small testbed for validation, and demonstrate the work in a sub-real environment.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Resilient Computing and Cybersecurity Center

Rejuvenation of Diverse FPGA Softcores in a SoC

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paulo Esteves-Verissimo

A field-programmable gate array (FPGA) is an integrated circuit designed to be reconfigured by the user after manufacturing to build a System-on-Chip (SoC) embedded device. The needed logic is usually implemented as a software image and then instantiated on the FPGA to inherit the nice properties of hardware, like higher speed and better security. Unfortunately, since the image itself, e.g., a Softcore that represents a Processing Unit, is a software, it is prone to faults and vulnerabilities that manifest after instantiation on the FPGA. Unfortunately, an Advanced Persistent Threat (APT) is possible if a determined adversary managed to discover a new vulnerability to initiate a zero-day, leaving no chance for classical detection and prevention tools to recover. In addition, the softcore can include bugs and glitches that manifest only at run time. Fault and Intrusion Tolerance (FIT) is a technique used to make a process resilient to such attacks by masking them. A FIT protocol replicates the processors, i.e., a softcore in our case, by running three versions simultaneously, and collecting a majority agreement (or consensus) on each operation. If the majority (e.g., 2/3 processors) did not fail at the same instant, the fault is masked, and the SoC continues operation as designed. This requires some level of diversity in the running softcore to increase the chances of independence of failures.

BAS/1/1696-01-01

ali.shoker@kaust.edu.sa

FPGA, Microblaze, RISC-V, Openpiton, Fault and Intrusion Tolerance

FPGA, System on Chip, Replication

The goal of this project is to experiment running an FIT we are implementing on a diverse softcores, e.g., Microblaze, RISC-V, Openpiton, etc., on an FPGA and simulate some fault or attacks. We are experimenting the concept on a Xilinx Zinc board using equivalent replicas. The objectives are to check the feasibility of running the FIT with different softcore types and evaluate the behavior in action. The intern will acquire all this knowledge and publish the results by working with a team of experts.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Resilient Computing and Cybersecurity Center

Useful Bitcoin Mining with a Matrix-based Puzzle

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paulo Esteves-Verissimo

Cryptocurrency and blockchain technologies are increasingly gaining adoption since the introduction of Bitcoin, being distributed, authority-free, and secure. Proof of Work (PoW) is at the heart of blockchain’s security, asset generation, and maintenance. In most cryptocurrencies, and mainly Bitcoin, the “work” a miner must do is to solve a cryptographic puzzle: to find a random nonce that once (cryptographically) SHA-256 hashed with a perspective block header, returns a 32 Bytes number having a leading pre-defined number of zeros (called difficulty). This puzzle represents the PoW, and lives forever in the blockchain (together with the block), allowing for future verifications. The main property of this puzzle is being very hard to solve, but easy to verify. Unfortunately, solving the puzzle is a very controversial being computation-hungry process that manifests in very high energy consumption (e.g., similar to the total electricity consumption of Denmark in 2020). Although other environment-friendly solutions are being suggested, e.g., Proof of Stake, the Bitcoin community has no plans to change the mining method using cryptographic puzzle. Shutting done the Bitcoin network is not an option either because it can disrupt the global economy with a market cap of around half trillion dollars as per today. Proof of eXercise (PoX) is an alternative puzzle that is getting more acceptance in academia. PoX suggests a matrix-based puzzle, e.g., matrix product and determinant calculation, that has close security properties to the cryptographic puzzle, but has at the same time useful benefits for the community, e.g., DNA and RNA sequencing, protein structure analysis, im-age processing, data mining [16], computational geometry, surface matching, space model analysis, etc. While computing the matrix product is very hard (which is required by design), its verification is also hard, making it infeasible. PoX proposes a probabilistic verification protocol that challenges the miner to only give the results of selected columns x rows multiplication for verification, thus making verification easy. Since selection is random, the miner cannot guess the columns x rows apriori, and thus must have computed the matrix correctly.

BAS/1/1696-01-01

ali.shoker@kaust.edu.sa

Bitcoin, Proof of eXercise, Bitcoin mining, Matrix product

Supercomputing, Blockchain, Cryptocurrency

The goal of the project is to experiment the feasibility of this matrix-based puzzle empirically on the Sheheen super computer at KAUST. The intern will work with RC3 experts and Shaheen engineers to realize the experiments. The objectives of the project are to present to the community evidences that the proposed PoX puzzle is a reasonable alternative to the cryptographic puzzle from the security and monetization perspectives (e.g., the miner has more incentives since it gets paid by the problem proponent as well and by getting the coins while mining). The results of the project will be published or commercialized.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Resilient Computing and Cybersecurity Center

Advanced Breach and Attack Simulation using ML

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paulo Esteves-Verissimo

Achieving sustainable urban greening through the integration of anaerobic membrane bioreactor and nature-based biofiltration landscaping gardens.

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Peiying Hong

Integrating microbial electrolysis cell with anaerobic digestion to enhance resource recovery from waste activated sludge

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Pascal Saikaly

Tackling the challenges of NO-Laser Induced Fluorescence technique in hydrogen detonation

Program:

Mechanical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Deanna Lacoste

Compared to classical constant volume or constant pressure thermodynamic cycles, the detonation regime of combustion could increase by 40% the efficiency of engines. In line with the Paris agreement, identifying more efficient combustion processes is one of the strategies to limit CO2 emissions that contribute to climate change. For transportation, researchers focus on obtaining and controlling a self-sustained detonation in a specific engine (PDE or RDE). While the measurement of temperature and chemical species is of current practice in conventional combustion process (flames, engines, etc…), the experimental characterization of detonation relies on the determination of the detonation velocity, global pressure, and density gradient structure. These information are limited to validate numerical simulations and to be confident in the phenomenological comprehension extracted from it. While planar laser-induced fluorescence of hydroxyl radical (NO-PLIF) is a powerful technique to characterize reaction fronts, previous studies have shown significant limitations of this technique for detonation visualization. Not only restricted to reaction front visualization, this technique is also of interest as it can give access to 2-D temperature measurements in detonations. Objectives: The main objective of the project is to overcome the current limitations of the NO-PLIF imaging of detonation. This numerical investigation is based on a preexisting PLIF model that will be used (i) to identify the sensitive parameters (excitation line, laser energy, gas composition, etc…) of the PLIF intensity and (ii) to recommend experimental conditions to maximize the overall image quality.

BAS/1/1396-01-01

mhedine.alicherif@kaust.edu.sa

Detonation front; Laser diagnostics; Numerical simulations; Spectroscopic analysis

Combustion; shock waves

First, the student will have to become familiar with the principle of the NO-PLIF technique and the particularities associated with its usage on detonations, which has high pressure and temperature variations, high-speed flow (up to 2000m/s), etc… Second, the sensitivity analysis of the fluorescence signal will be conducted to identify the most sensitive parameters of the PLIF signal. Third, optimal operating conditions (≠ maximizing the fluorescence signal) will be identified and tested experimentally. Due to both the strong non-linearities between the PLIF signal intensity and each parameter involved, machine-learning approaches may be used to facilitate the identification of the optimal operating conditions.

Mechanical Engineering

Physical Sciences and Engineering

Graduate or Undergraduate

Clean Combustion Research Center

Scaling Graph Neural Networks to 1000s of GPUs

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Panagiotis Kalnis

Statistical and machine learning methods for health and environmental applications.

Program:

Statistics

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Paula Moraga

Egocentric Video Understanding

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Bernard Ghanem

Have you ever imagined having a robot that cooks every meal for you? Have you ever dreamt about experiencing a different world in the Metaverse? Have you ever expected to have your glasses tell you where you left your keys and how to navigate to your favorite restaurant step by step? If yes, egocentric video understanding is what can lead you there. Egocentric videos are videos recorded from the first-person point of view, with the camera mounted on the head (e.g., GoPro) or smart glasses worn alongside the eyes (e.g., Google glasses), and they are what you actually see in your eyes. We need the AI system to automatically analyze and understand this type of videos to achieve the goals mentioned above. There are two key aspects in this problem: 1) large egocentric video data to fuel AI solutions; 2) effective techniques to generate correct predictions. For the first aspect, our IVUL group has devoted two years’ effort, together with 12 other universities as well as Meta (formerly Facebook), to achieve the largest egocentric video dataset called Ego4D. It contains 3000+ hours of egocentric video, spanning hundreds of scenarios captured by nearly 1000 unique camera wearers. Ego4D also defines various research tasks for egocentric video understanding, ranging from querying past memory, interpreting current behaviors, and forecasting future tendencies. For example, given a sentence “where and when did I last see my keys?”, the AI system returns the most recent video clip showing where your keys are. Or, the AI system automatically summarizes the video by telling you who is talking and what is his/her main point. Or the AI system predicts where you are walking to and what you are doing in the following minutes or even hours. For the second aspect, though Ego4D contains baseline solutions to each task, these solutions are far from practical for real-world application. There are two main challenges here. First, current solutions adopt techniques from video understanding tasks for third-person videos (where activities are recorded from a “spectator” view), which are dramatically different from egocentric videos in terms of recording perspective, camera motion, video continuity, etc. As a consequence, representations learned from third-person videos are not optimal to represent egocentric videos. We need to investigate novel feature representations specific to egocentric videos, or explore ways to smartly transfer the knowledge from third-person videos to egocentric videos. Second, egocentric videos pose new challenges for conventional methods due to their characteristics, such as noisy head motion, long videos and fragment actions. We need to address these challenges and improve the performance with novel techniques. In a nutshell, Ego4D is putting an apron on the robot and knocking on the door of the Metaverse, while at the same time, it is unveiling fresh challenges, which AI researchers are the key. It’s time to hop on board and contribute to this grand effort!

BAS/1/1653-01-01

bernard.ghanem@kaust.edu.sa

egocentric video; video understanding; computer vision;

Computer Vision; Machine Learning

(i) Effective feature representations of egocentric videos that benefit downstream tasks of egocentric videos, such as episodic memory, future anticipation; (ii) Novel techniques to transfer/translate between egocentric videos and exocentric videos; (iii) Improvement to retrieve ‘moments’ from past videos using a category, sentence or an object; (iv) Improvement to identify speaking faces in an egocentric video and summarize the speech.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Visual Computing Center

Next Generation Continual Learning

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Bernard Ghanem

One of the most impressive abilities of human beings is the incremental learning ability. Since birth, we are always learning continuously without forgetting previously acquired knowledge that is useful for us. Could you imagine the amount of real-world applications that could be developed if we extended this human ability to modern-day AI systems (especially deep neural networks)? Modern deep neural networks adapt their parameters based on large-scale datasets to achieve state-of-the-art performance on specific computer vision tasks. However, due to legal and technical constraints and huge label diversity, deep learning models in real-world scenarios would rarely be trained just once time. Instead, they could be trained sequentially in several disjoint computer vision tasks without considering the data from previous tasks (because it may no longer be available for example). Therefore, these networks should learn incrementally without forgetting the previously learned knowledge. This is known as Continual Learning (CL). Currently, there are two families of CL methods. The first is rehearsal or memory-based methods, which select and store the most relevant samples to remember the current task when the following tasks are learned. The second group involves regularized methods that penalize changes to the most relevant parameters for the previous tasks. While the main studied challenge in the literature is learning with the least amount of forgetting on previous tasks, there are several other unexplored factors that affect learning from a stream of data. For instance, How fast is the learner in adapting the parameters of the model when receiving a new batch of data? If the learner is too slow (expensive training routine), then samples from the stream could be missed and not trained on. Thus, how can we benchmark different continual learning methods under budget constraint training? Furthermore, most continual learning benchmarks are focusing solely on the image domain leaving the more challenging video data unstudied. In the video domain, one of the main issues has been the lack of realistic, challenging, and standardized evaluation setups, making direct comparisons hard to establish. Therefore, our group IVUL has developed vCLIMB, a novel video class incremental learning benchmark, to promote and facilitate research on continual learning in the video domain. Video CL comes with unique challenges. (1) Memory-based methods developed in the image domain are not scalable to store full-resolution videos, so novel methods are needed to select representative frames to store in memory. (2) Untrimmed videos have background frames that contain less helpful information, thus making the selection process more challenging. (3) The temporal information is unique to video data, and both memory-based and regularization-based methods need to mitigate forgetting while also integrating key information from this temporal dimension.

BAS/1/1653-01-01

bernard.ghanem@kaust.edu.sa

continual learning; online learning

machine learning; computer vision

(i) A novel memory sampling strategy that learns to select a different number of relevant frames per video to reduce memory consumption while the performance remains almost the same; (ii) Novel training techniques/schemes to reduce forgetting. (iii) Benchmarking different continual learning methods on more practical metrics.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Visual Computing Center

Graph Neural Networks for Science and Engineering

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Bernard Ghanem

Lots of data in scientific and engineering applications come with natural graph structures such as molecules in Chemistry, proteins in Biology, particles in Physics, planets in Astronomy, Bulk and MOF materials in Material Science, social and citation networks in Data Science, point clouds and meshes in Computer Vision and Graphics and so on. To model the information of such objects with complex structures, Graph Machine Learning, especially Graph Neural Networks (GNNs), has been proven as one of the most promising tools. Graph neural networks are deep learning architectures that can be trained to represent graphs with node features and edge features. For example, a molecule can be represented by a graph, where each atom is a node in the graph, and each bond is an edge. The atom numbers and types of chemical bonds are the associated node and edge features respectively. A GNN model can be trained to predict the quantum properties by learning on density functional theory (DFT) datasets which has huge potential to advance scientific discovery. Our group at IVUL have developed methods for graphs in 3D vision, videos, data mining, and fundamental science. We have developed GNNs with more than 100 layers with DeepGCNs (ICCV’2019, TPAMI’2021), and PU-GCN (CVPR’2021) for 3D point clouds segmentation and generation, G-TAD (CVPR'2020), VLG-Net (ICCVW’2021), MAAS (ICCV’2021) and VSGN (ICCV’2021) for large-scale video understanding, and DeeperGCN (arXiv’2020), 1000-layer GNN (ICML’2021) and FLAG (CVPR'2022) for node, link and graph level property prediction on Open Graph Benchmark (OGB) datasets which have graphs span nature, society and information domains. Are you excited about working on complex graph-structured data to make advances in biology, chemistry, physics, computer science, and so on? Would you like to use artificial intelligence to make fast predictions about the 3D structure of molecules, thereby speeding up the drug discovery process? Are you motivated by applications to precision medicine, and would like to create AI that learns to recommend what specific drug is suitable for a particular patient? Or perhaps you are more interested in higher-level abstractions, and would like to build an AI-based partial differential equation solver. All of these complex problems can be modeled through graph-structured data, and research in Graph Neural Networks can bring us closer to solving them. GNN has untapped potential in tackling graph based problems in Science and Engineering. However, more work is needed to explore the unique challenges to each scientific domain. In this project, you will have the chance to learn how to build large-scale graph neural networks and apply them to scientific and engineering applications.

BAS/1/1653-01-01

bernard.ghanem@kaust.edu.sa

graph neural networks

machine learning, AI for science

(i) Identifying the ground challenges of graph based problems in Science and Engineering; (ii) Collecting or processing the desired data into graph formats; (iii) Proposing novel GNN architectures and training techniques to tackle the challenges of learning on these graph data; (iv) Training and evaluating the proposed methods on specific metrics; (v) Producing well-performing and reproducible results and releasing the modular and reusable codebase to the research community.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Visual Computing Center

Next Generation 3D Understanding

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Bernard Ghanem

We are living in a 3D world. A broad range of critical applications such as autonomous driving, augmented reality, robotics, medical imaging, and drug discover rely on accurate representation of the three-dimensional data. While enormous efforts have been devoted to images and languages processing, it is still at an early stage to apply deep learning to 3D, despite their great research values. Here, we launch the project of next generation 3D understanding, and want to appeal more young talents like you to make this happen. We are particularly interested in two topics of the next generation 3D understanding: 1) a large-scale pretrained foundation 3D understanding model; 2) a vision generalist model that connects 2D and 3D vision data such as images, point clouds, and RGB-D. For the first topic, you might have heard that the trillion-parameter AI language model Switch Transformer by Google Brain excels across nature language processing tasks, and you might also know about the recent model Imagen with over 2 billion parameters can produce Photorealistic images from texts. Both of them are great examples of the power of large-scale models. Unfortunately, in 3D understanding, even the largest well-known network is still with less than 100 million parameters. How to increase the scale of 3D models in order to further unveil the power of deep learning in 3D application is a promising research direction. For the second topic, as a human, we can understand vision data despite its modality (2D or 3D). It is a step towards general artificial intelligence in computer vision to propose a single model that is able to have all knowledge about vision including 2D (images, videos), 3D (point clouds, RGB-D). This is an interesting topic but is under explored in the community. Our group at IVUL has put tremendous efforts and gained significant achievements in both topics. For the large-scale pretrained foundation model, our group is the first in the world that successfully trained a model with over 100 layers that achieved state-of-the-art performance in 2019 (DeepGCNs-ICCV19’). We broke our own record to 1000 layers in 2021 (GNN1000-ICML21’). Recently, we also propose scalable 3D networks with high inference speed in 2020s (ASSANet-NeurIPS21’, PointNeXt-arXiv22’). For the vision generalist model, our group has published impactful papers that involve understanding both view-images and point clouds (MVTN-ICCV21’, VointCloud-arXiv21’). Moreover, we have multiple ongoing projects in both directions. If you want to become a part in next generation 3D understanding, do not hesitate to join this project and achieve more with us!

BAS/1/1653-01-01

bernard.ghanem@kaust.edu.sa

3D computer vision

(i) proposing a new large-scale foundation model for 3D understanding; (ii) proposing self supervision techniques for training large-scale 3D models with limited data; (iii) proposing novel generalist vision models that are able to tackle both 2D and 3D understanding; (iv) proposing novel techniques for training this cross-modality generalist vision model.

All Programs

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Visual Computing Center

Enzymatic Synthesis – Enzyme Characterization and Cascade Engineering

Biocatalytic Amine Synthesis

The Development of Organic Transformations via Photocatalysis

Electro-catalyzed C-C and C-X bond cross-couplings

Program:

Chemistry

Division:

Physical Sciences and Engineering

Faculty Name:

Magnus Rueping

Functional metagenomics: AI-based analysis of complex microbial interactions

Program:

BioEngineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Robert Hoehndorf

Neuro-symbolic AI algorithms

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Robert Hoehndorf

Symbolic, logic-based languages are inherently interpretable by humans. Symbols are entities standing for other entities and can be combined to form more complex expressions. Symbol systems are therefore well suited to explain and answer questions of “how” and “why” an intelligent agent (human or artificial) arrived at a decision. Knowledge-based systems based on logic have traditionally been used successfully in question answering (formulated as computing entailments, i.e., statements that must be true if all the axioms are assumed to be true) and can generate novel and “surprising” answers through deductive inference. However, they are not well suited to dealing with incomplete or noisy information or identifying patterns from unstructured data. Machine learning methods, in particular neural networks, can deal with noisy and incomplete data substantially better than symbolic, logic-based methods. However, they operate mainly as black boxes which do not make the logic underlying a decision making process available. Neuro-symbolic methods in Artificial Intelligence aim to combine logic-based AI methods and neural methods to overcome the limitations of both. The aim of the project is the identify, implement, evaluate, and improve neuro-symbolic methods. The baselines and experiments will focus on one of two possible areas of application: biomedical data where a large number of knowledge bases has been developed, or common sense knowledge.

BAS/1/1659-01-01

robert.hoehndorf@kaust.edu.sa

neuro-symbolic, Artificial Intelligence, machine learning, Semantic Web, logic, bioinformatics, common sense reasoning, automated reasoning, knowledge graph, knowledge representation

Artificial Intelligence

Month 1: identification of algorithm, technical presentation Month 2: implementation, baseline experiments Month 3: algorithm evaluation Month 4: analysis, improvement and tuning Month 5: experimental results, theoretical results Month 6: write-up

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Computational Bioscience Research Center

Iproved oil recvery from carbonates

Program:

Energy Resources and Petroleum Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Tadeusz Patzek

Nanovisualization

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Ivan Viola

During the research internship students will learn about the nanovisualization technology which combines computer graphics and visualization for nano-structures in life sciences and biotechnology. Nanovisualization poses several new technological challenges that are not reflected in the state of the art computer graphics and 3D visualization as of today. The underlying domain requires new techniques for multi-scale, multi-instance, dense, three-dimensional models which we never subject of technological advances in 3D graphics before. These scenes are of gigantic sizes and unmatched complexity. Therefore the task in nanovisualization is to thoroughly revisit all technological aspects of rendering, visualization, navigation, user interaction, and modeling in order to offer algorithmic solutions that address new requirements associated with the nano and microscopic scales.Throughout their stay, students will be working in team with researchers on specific assignment for a particular scientific work or solving a technical challenge in the field of computer graphics and visualization. Nanovisualization is one of the key components in creating, studying, and understanding scale-wise small (but complex) systems. As such it will become a key technology in the upcoming industrial revolution that will be heavily associated with the nano scale.The benefit for the students is to get familiar with nanovisualization research field, which is worldwide uniquely offered at KAUST. They will be integrated in working on a very important problems so far untouched in graphics and visualization that are very relevant for many societal challenges from the health, food, and energy sectors.

ASP/1/1669-01-01

ivan.viola@kaust.edu.sa

Nanovisualization

computer science, applied mathematics, physics

Students should work on an internship project and should implement a clearly specified task. It is expected that students are familiar with computer graphics and visualization and can document advanced skills in graphics programming

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Undergraduate

Visual Computing Center

Formation of hydrogen peroxide in water microdroplet

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Himanshu Mishra

Recent reports on the formation of hydrogen peroxide (H2O2) in water microdroplets produced via pneumatic spraying [1] or capillary condensation [2] have garnered significant attention. How covalent bonds in water could break under such mild conditions challenges our textbook understanding of physical chemistry and the water substance. While there is no definitive answer, it has been speculated that ultrahigh electric fields at the air-water interface are responsible for this chemical transformation. We are carrying out a comprehensive experimental investigation of H2O2 formation in (i) water microdroplets sprayed over a range of liquid flow-rates, the (shearing) air flow rates, and the air composition (ii) water microdroplets condensed on hydrophobic substrates formed via hot water or humidifier under controlled air composition. Our experimental results have challenged the putative claims of spontaneous H2O2 generation on the water surface [3, 4]. Additionally, new scientific questions along this theme have emerged that the VSRP intern will contribute to. References: 1. Lee, J. K.; Walker, K. L.; Han, H. S.; Kang, J.; Prinz, F. B.; Waymouth, R. M.; Nam, H. G.; Zare, R. N., Spontaneous generation of hydrogen peroxide from aqueous microdroplets. P Natl Acad Sci USA 2019, 116 (39), 19294-19298. 2. Lee, J. K.; Han, H. S.; Chaikasetsin, S.; Marron, D. P.; Waymouth, R. M.; Prinz, F. B.; Zare, R. N., Condensing water vapor to droplets generates hydrogen peroxide. P Natl Acad Sci USA 2020, 117 (49), 30934-30941. 3. Gallo Jr, A.; Musskopf, N. H.; Liu, X.; Yang, Z.; Petry, J.; Zhang, P.; Thoroddsen, S.; Im, H.; Mishra, H., On the formation of hydrogen peroxide in water microdroplets. Chemical Science 2022, 13 (9), 2574-2583. 4. Musskopf, N. H.; Gallo, A.; Zhang, P.; Petry, J.; Mishra, H., The Air–Water Interface of Water Microdroplets Formed by Ultrasonication or Condensation Does Not Produce H2O2. The Journal of Physical Chemistry Letters 2021, 12 (46), 11422-11429.

BAS/1/1070-01-01

peng.zhang@kaust.edu.sa

Physical Chemistry, Electrochemistry, Analytical Chemistry, Microfluidics, high-speed imaging, chemical kinetics

• The intern will conduct a comprehensive experimental investigation of H2O2 formation in (i) water microdroplets sprayed over a range of liquid flow-rates, the (shearing) air flow rates, and the air composition (ii) water microdroplets condensed on hydrophobic substrates formed via hot water or humidifier under controlled air composition. This will also entail a comparative assessment of the various H2O2 detection kits/assays available. • Glovebox experiments will be deployed to quantify H2O2 formation in water microdroplets as a function of the air-borne ozone (O3) concentration. • Effects of atmospherically relevant O3(g) concentrations (10–100 ppb) on the formation of H2O2(aq) will be evaluated. • Effects of the gas–liquid surface area, mixing, and contact duration will be quantified.

Environmental Science and Engineering

Biological and Environmental Sciences and Engineering

Graduate or Undergraduate

Water Desalination and Reuse Center

Growth and characterization of 2D materials using sputtering

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Nazek Elatab

Dissecting the molecular basis of the neurodevelopmental features associated with Klinefelter syndrome

Program:

BioEngineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Antonio Adamo

Integrated silicon photonics

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Yating Wan

Integrated silicon photonics has sparked a significant ramp-up of investment in both academia and industry as a scalable, power-efficient, and eco-friendly solution. At the heart of this platform is the light source, which in itself, has been the focus of research and development extensively. We tackle this from two perspectives: device-level and system-wide points of view. In the former, the different routes taken in integrating on-chip lasers are explored from different material systems to the chosen integration methodologies. In the latter, we seek system-wide applications that show great prospects in incorporating photonic integrated circuits (PIC) with on-chip lasers and active devices, namely, optical communications and interconnects, optical phased array-based LiDAR, sensors for chemical and biological analysis, integrated quantum technologies, and finally, optical computing. By leveraging the myriad inherent attractive features of integrated silicon photonics, we aim to inspire further development in incorporating PICs with on-chip lasers in, but not limited to, these applications for substantial performance gains, green solutions, and mass-production. In this VSRP program, students will have the opportunity to learn the latest device design and fabrication of the integrated silicon photonics chips, and explore the applications based on their own interests. The project needs 3-6 months to be completed. Successful students can likely publish their results in prestigious scientific venues and get enrolled in the Ph.D program in Integrated Photonics Lab.

BAS/1/1700-01-01

alkhazraji_e@jic.edu.sa

integrated Si photonics

photonics Engineering, Physics, Mathematics

The students are expected to acquire the basic knowledge of the design of the integrated silicon photonics chips, proficient skills of device designs using simulation tools, hand-on experimental experiences of optoelectronic device characterizations, and conference/journal publications.

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Integration of reservoir simulation with deep learning for subsurface reservoir management

Program:

Energy Resources and Petroleum Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Bicheng Yan

Protein design based on AlphaFold2

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Xin Gao

3D printing of smart composites for wireless structural health monitoring

Program:

Mechanical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Gilles Lubineau

Digital Outcrop Model-based analysis of fracture network

Program:

Earth Science and Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Volker Vahrenkamp

Capturing adhesion molecules in action through imaging

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Jasmeen Merzaban

Cell adhesion occurs through spatio-temporally regulated interactions that are mediated by multiple intra- and inter-cellular components. Physiologically, shear forces on flowing cells orchestrate these interactions. The conventional assay used to study the effect of shear flow on cell adhesion is the parallel plate flow chamber (PPFC) assay, which records videos of cells rolling in flow and adhering to adhesion molecules on cells (eg. endothelial) or immobilized to a surface. However, due to the limited spatial resolution and sensitivity of these assays, nanoscopic molecular level mechanisms of selectin-selectin ligand interactions and their role in leukocyte (neutrophils, HSCs, T-cells) migration can’t be assessed. Recent developments in super resolution and single-molecule fluorescence imaging techniques allow for the visualization of individual molecules with nanometer spatial resolution and millisecond temporal resolution. Furthermore, advanced super-resolution microscopy provides unique opportunities to obtain information about nanometer-scale conformational dynamics of protein complexes as well as nanoscale architectures of biological samples. In collaboration with S. Habuchi (BESE, KAUST), whose research focuses on the development of tools and materials for fluorescence molecular imaging, we optimized the PPFC assay to image the cell using super resolution fluorescence microscopy. This allows us to image single molecular ligand architecture on the cell surface and determine how the ligand distribution was influenced as a result of rolling on selectin (E-/P-selectin) surfaces, both to each other (clustering) and to other selectin ligands. To characterize the dynamics of ligand distribution, we also developed real-time live cell imaging of these ligands under shear flow and are able to beautifully observe long, thin, flexible structures protruding out from the rear (tethers) and the front (slings) sides of the cell as it rolls over selectin expressing surfaces. For this project, these novel-imaging tools, combined with molecular, cellular and proteomic technologies will be used to further understand the cellular landscape that results before, during and following the migration of model cells such as hematopoietic stem cells.

BAS/1/1005-01-01

jasmeen.merzaban@kaust.edu.sa

Selectins, cell migration, metastasis, glycobiology

Cell Biology and Imaging

- overall goal is to develop a platform for imaging cells in flow over tissue samples expressing selectins - growth and maintenance of cell lines and primary cells - prepare and stain tissue sections for selectins (E-/P-/L-selectin) - prepare and stain cells lines for selectin ligands - run flow assays and use super resolution imaging under the supervision of an experienced PhD student

BioScience

Biological and Environmental Sciences and Engineering

Graduate or Undergraduate

Machine learning for wireless communication systems

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Ahmed Eltawil

At the CCSL, we are engaged in research and teaching on wireless communication methods for future wireless communication systems. In future wireless communication 5G and beyond, an extremely high number of heterogeneous devices, such as smartphones, sensors, robots, and vehicles, will communicate with each other. Consequently, the need for higher data rates and lower latency will increase significantly, posing major challenges for the resource allocation. Deep learning and data-driven algorithm approximation schemes have recently received significant attention as means to perform resource allocation with reduced complexity in 5G and beyond networks. This project considers the challenging case of Reflective Intelligent System (RIS) assisted, mmWave, frequency selective, massive MIMO systems with hybrid architecture and develops deep-learning based resource allocation frameworks. In these frameworks, prior data-set observations and deep neural network models will be leveraged to learn the mapping from received measurements to channels, beamformers and power allocations. Furthermore, deep neural networks will be used to approximate the optimization problems by selecting the suitable parameters that minimize the approximation error. The usage of a deep neural network framework reduces the computational complexity and processing overhead, since it only requires a limited number of layers of matrix-vector multiplications which can reduce processing time substantially.

BAS/1/1686-01-01

ahmed.eltawil@kaust.edu.sa

Machine Learning, MIMO, Wireless, ML

Electrical and Computer Engineering

Goal: This project aims to improve the overall performance on emerging and beyond 5G wireless systems in boosting system capacity with improved robustness and high data rates, via a low-cost, low-latency, and green implementation. For this purpose, deep learning or machine learning methods shall be applied, which can adapt to the dynamic changes of the wireless communication system and its environment and exploit the past experience to improve the future performance of the system. A report detailing system design and simulation results are expected at the end of the program.

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Graduate or Undergraduate

Identifying novel Cas variants for pathogen diagnostics

Program:

BioEngineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Magdy Mahfouz

Investigating the carrier dynamics of emerging wide band gap semiconductor for novel optoelectronic applications

Program:

Marine Science

Program:

Materials Science & Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Iman Roqan

Studying fundamental sciences is the key factor for technological development, as this allows the researchers to better understand the natural phenomena behind human discoveries. In the context of semiconductor innovation, for example, the physics principles of carrier recombination and the importance of quantum mechanics, including carrier quantum confinement, localization, and their effects on the carrier wavefunction, need to be studied in order to ensure efficient semiconductor-based devices. Mainly, technology based on wide bandgap semiconductors as high-energy optoelectronics based on these materials that operate at the deep UV and UV spectral ranges got scientists attention due to their use for many applications in different fields, such as medical treatment, astronomy investigations, material analysis, missile detection, space communications, security systems, and x-ray imaging. Due to the lack of suitable substrates, the emitting devices still need further enhancement. For example, no commercial laser diode operates in the UV spectral range below 375 eV. Therefore, in this project, this issue will be addressed to enhance the emission of these materials. The project will focus on studying the fundamental physics of the carrier dynamics of wide-bandgap semiconductors such as III-nitrides and oxides. Several structures will be investigated experimentally and theoretically for developing wide bandgap semiconductor-based materials, one of which is carrier confinement using different novel approaches. The project goals will be achieved by employing time-integrated photoluminescence (PL) using CW lasers as well as time-resolved PL using ultrafast oscillators attached to streak camera or photon-counting detection systems. In addition, PL excitation will be used to understand the origin of the emitted light using a Xe lamp attached to a fluorescence system. The theoretical simulation of emitting devices will be carried out by analytical code, such as Lumerical.

BAS/1/1319-01-01

iman.roqan@kaust.edu.sa

Wide bandgap semiconductor, LED, laser diode, emitting devices, DUV

Optical spectroscopy of semiconductors

- Be familiar with advanced optical spectroscopy techniques - Understanding the fundamentals of optical properties of semiconductor - Understanding the carrier dynamics of semiconductor - Achieving theoretical and experimental results of the novel semiconductor structure - Analyzing the carrier dynamic outputs - Finally, concluding the desired projects

Marine Science

Physical Sciences and Engineering

Graduate or Undergraduate

Safeguarding our daily bread from wheat rust diseases

Program:

Plant Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Brande Wulff

Wheat rusts are destructive diseases of wheat, which throughout recorded history have caused devastating epidemics almost wherever wheat is grown. The wild ancestors of domesticated wheat represent a rich source of genetic variation with huge potential for improving disease resistance. Deploying this genetic diversity into elite, cultivated wheat by traditional breeding takes many years for just a single resistance gene. However, the molecular identification (cloning) of resistance genes opens up new possibilities for accelerated breeding by marker-assisted selection and genetic engineering [Refs. 1,2]. The Wulff lab has established a suite of molecular plant breeding technologies that significantly reduce costs and accelerate plant growth [Refs. 3,4], gene discovery [Refs. 5,6,7,8,9] and gene cloning [Refs. 7,8,9,10]. You will use our tools, structured germplasm, and sequence resources to characterize novel candidate rust resistance genes. You will be supervised by Brande Wulff and receive training and co-supervision from a team of Postdocs and PhD students with expertise in bioinformatics, mathematics, scripting, genetics, plant pathogen interactions, wheat husbandry and crossing. KAUST is a vibrant place to discuss and plan science. You will become part of the larger KAUST community and alumni, which we hope will have lasting positive impacts on your future career. References [1] Dhugga & Wulff (2018). Science 361:451-452. [2] Luo et al (2021) Nature Biotechnology 39:561-566. [3] Watson et al (2017) Nature Plants 4:23-29. [4] Ghosh et al (2018) Nature Protocols 13:2944-2963. [5] Steuernagel et al (2015) Bioinformatics 31:1665-7. [6] Steuernagel et al (2020) Plant Physiology 183:468-482. [7] Arora et al (2018) Nature Biotechnology 2:139-143. [8] Gaurav et al. (2020) bioRxiv doi.org/10.1101/2021.01.31.428788. [9] Steuernagel et al (2016). Nature Biotechnology 34:652-5. [10] Sánchez-Martín et al (2016). Genome Biology 17:221.

BAS/1/1091‐01‐01

brande.wulff@kaust.edu.sa

Wheat, wheat rust, resistance genes, GWAS, bioinformatics, plant disease, cloning, food security

Plant genetics

Research experience including learning of one or more techniques employed in the lab, the generation of original data, design of figure(s), and presentation of results at lab meeting.

Plant Science

Biological and Environmental Sciences and Engineering

Graduate or Undergraduate

Center for Desert Agriculture

Design and 3D print a continuous flow reactor

Program:

Chemical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Carlos Grande

Modelling tools for advanced separation processes

Program:

Chemical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Carlos Grande

Modeling Fluid Flow and Transport in Porous Media by Physics-driven Simulation Approaches

Program:

Energy Resources and Petroleum Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Bicheng Yan

Fully 3D Printed Flexible ECG Patch with Dry Electrodes

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Nazek Elatab

Efficient pricing of high-dimensional (multi-assets) European Options

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Raul Tempone

The student will work on designing new numerical methods based on hierarchical adaptive sparse grids quadratures combined with Fourier techniques for efficient pricing of high-dimensional (multi-assets) European Options. Specifically, the student will contemplate the possibility of finding a heuristic framework for an optimal choice of the integration contour (damping parameter) which controls the analyticity of the integrand in the Fourier space and hence accelerate the performance of the quadrature methods. He will also develop a systematic comparison between hierarchical deterministic quadrature methods, Tensor Product (TP) quadrature, Smolyak (SM) Sparse Grids quadrature, and Adaptive Sparse Grids (ASG) quadrature to numerically evaluate the option price under different pricing dynamics, Geometric Brownian Motion (GBM), Variance Gamma (VG) and Normal Inverse Gaussian (NIG) for different multi-asset payoff functions such as Basket Call/Put and Rainbow options. The student is also asked to elaborate a comparison in terms of computational complexity against the quadrature methods for different dimensions, and various combination of parameter sets within the mentioned pricing models.

400000024

chiheb.benhammouda@kaust.edu.sa

Multi-Asset Option Pricing, Fourier Transform, Lewis Valuation Approach, Damping Parameters, Lévy models, Hierarchical Adaptive Sparse Grids Quadrature, Monte Carlo

Computational Finance, Computational Mathematics, Numerical Analysis

As the main project deliverable, we expect a scientific report (eventually a research manuscript) including a detailed description and analysis of the proposed methodology developed within the course of the internship and providing all numerical experiments to showcase the versatility of the proposed heuristic framework. The working environment the student will use should include a GIT repository shared with the project collaborators in which he includes all project-related materials such as progress reports, codes, figures, and important references from the literature to facilitate the supervision task and communicate ideas more effectively.

Applied Mathematics and Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Undergraduate

Resilient Models for Attacks Detection in Cyber-Physical Systems

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Charalambos Konstantinou

The goal of this project is developing methods to merge Machine Learning (ML) with physics-based models to create control algorithms can significantly enhance the resiliency of Cyber-Physical Systems (CPS). The approach will combine recent results in ML with control theory via constrained optimization to create novel systems and methods for protecting CPS from malicious cyber intruders via detection and prevention strategies. Specifically, the research project focuses on (1) refining the offline/online training and execution algorithms of ML models through physics-based constrained optimization, (2) developing secure estimation and control algorithms that are significantly more resilient to cyber-attacks than the state-of-the-art counterparts, and (3) improving the distributed resiliency for networked systems supporting multi-agent autonomous systems.

BAS/1/1692-01-01

charalambos.konstantinou@kaust.edu.sa

Cyber-physical systems, resiliency, cybersecurity, control methods, machine learning, physics-based methods.

Electrical and Computer Engineering/Computer Science

The goal of this internship is to analyze and improve existing data-driven and physics-based algorithms for attack detection in CPS. The student will be expected to learn about existing solutions, as well as the challenges and requirements to applying such techniques in their settings. With guidance of other team members, the student will then find new solutions for improving algorithmic resiliency in order to reduce cyber-risks related to the CPS operation. Candidates should be motivated to work on research-oriented problems with a team and develop new solutions. They should have a strong background in controls, in particular with regards to machine learning and power systems. They are also expected to be proficient in MATLAB/Simulink.

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Undergraduate

Real-Time (co-)Simulation for Cybersecurity

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Charalambos Konstantinou

Regaining Trust in IoT

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Charalambos Konstantinou

Cyber-Secure Integration of Renewable Energy Sources

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Charalambos Konstantinou

Ransomware in Industrial Control Systems

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Charalambos Konstantinou

Machine learning techniques for divergence-free field reconstruction

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Raul Tempone

Machine Learning and Dynamical Systems

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Raul Tempone

Numerical approximation of partial differential equations

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Daniele Boffi

Causal and Fair Machine Learning

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Di Wang

Robust/Differentially Private Machine Learning

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Di Wang

Foundations of Private and Fair Statistics

Program:

Statistics

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Di Wang

Protocol development for biomass quantification in membrane autopsies

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Johannes Vrouwenvelder

Statistical models based on stochastic partial differential equations

Program:

Statistics

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

David Bolin

Continual Learning

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Mohamed Elhoseiny

Imagination Inspired Vision

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Mohamed Elhoseiny

Microfluidics-based single-molecule fluorescence imaging of nanoscopic cellular interactions

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Satoshi Habuchi

Impacts of UV radiation on corals and other organisms in the Red Sea

Program:

Marine Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Susana Agusti

Biological stability of chlorinated and non-chlorinated drinking water

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Johannes Vrouwenvelder

Characterization of biofilm growthrate in a membrane system

Program:

Environmental Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Johannes Vrouwenvelder

Gradient compression for distributed training of machine learning models

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Peter Richtarik

Federated Learning

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Peter Richtarik

Towards a Principled Understanding of Deep Learning

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Peter Richtarik

Topics in Machine Learning and Optimization

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Peter Richtarik

Molecular mechanisms underlying growth and defense in plants

Program:

Plant Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Ikram Blilou

Spatio temporal analysis of expression of genes controlling assymetric stem cell division and tissue patterning in plants

Program:

Plant Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Ikram Blilou

Experimental study of carbon-free combustion

Program:

Mechanical Engineering

Division:

Physical Sciences and Engineering

Faculty Name:

Gaetano Magnotti

Salinity Tolerance of Plants

Program:

Plant Science

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Mark Tester

Inverse Problems in Imaging

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Wolfgang Heidrich

Computational Cameras

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Wolfgang Heidrich

Fouling in Membrane Filtration Systems

Program:

Earth Science and Engineering

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Johannes Vrouwenvelder

Cutting-edge research on materials, devices, or physics of the third-generation semiconductor

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Xiaohang Li

The wide bandgap semiconductors, also known as the third-generation semiconductors, have enormous potentials to revolutionize almost every industry on the planet and in space. Because of the unique and superior properties, they can be made in ultra-efficient, ultra-sensitive and ultra-reliable optical and electronic devices. Despite being in the early phrase of development and commercialization, the third-generation semiconductors have already resulted in industries worth of hundreds of billions USD and creating numerous jobs, as well as 2014 Nobel Prize in Physics. Opening your phone, computers and anything using electricity, you will likely find plenty of them. More potentials are to be unlocked by smart and hard-working researchers such as you. This VSRP project is offered by the Advanced Semiconductor Laboratory, a world-leading laboratory with state-of-the-art facilities in the third-generation semiconductor research. The VSRP students will have the opportunity to learn the latest materials, devices, and physics of the third-generation semiconductor as well as the combination with other exciting things such as 2D materials and quantum photonics. More importantly, every VSRP student will have his/her own project to solve a key problem. The project needs 4-6 months to be completed. It is going to be an exciting period with intense training and research work both theoretically and experimentally. Successful students can likely publish their results in prestigious scientific venues.

BAS/1/1664-01-01

xiaohang.li@kaust.edu.sa

cutting-edge-research-on-materials-devices-or-physics-of-the-third-generation-semiconductor-semiconductor, photonics, electronics, integrated circuits.

Electrical/Electronic Engineering, Physics, Material Science, Chemistry

In research, no deliverables can be compared with a patent or a peer-review paper. In the past, all the VSRP students can generate patents or publish first-authored or co-authored papers in prestigious journals. The publication record has help strengthened their credentials greatly for future career development. Therefore, the incoming VSRP students are expected to do the same. PS: one example can be found here: https://goo.gl/8sorGf

Electrical Engineering

Computer, Electrical and Mathematical Sciences and Engineering

Complex optoelectronics materials and phenomena

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Andrea Fratalocchi

An iPSCs-based approach to model Type Two Diabetes in-vitro

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Antonio Adamo

Screening for Carotenoid-Derived Signaling Molecules

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Salim Al-Babili

Machine Learning for Graphs

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Jesper Tegner

Machine Learning for Biological and Medical Imaging

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Jesper Tegner

Algorithmic Information Theory for Machine Intelligence

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Jesper Tegner

We recently developed numerical and computational techniques to use algorithmic information theory (AIT) to the analysis of networks. For publications see google scholar(https://scholar.google.com/citations?hl=sv&user=_DUppAgAAAAJ&view_op=list_works&sortby=pubdate).Subprojects include to-         Develop python packages for AIT analysis of large-scalenetworks-         Develop new AIT network embedding algorithms-         Analyze Convolutional Networks a representational learning usingAIT-         Quantify and benchmark AIT network analysis with othertechniques-         Large-scale computation of AIT networks using a supercomputer(Shaheen)Newand improved numerical approximation of algorithmic complexity using massive computations of Turing Machines on Shaheen(supercomputer)

ASP/1/1669-01-01

jesper.tegner@kaust.edu.sa

algorithmic-information-theory-for-machine-intelligence-Machine Learning, Artificial Intelligence, Entropy, Complexity

Computer Science, Applied Mathematics

Individual projects will be tailored and narrowly designed from the above palette according to interest of the student, technical proficiency, and level of study. We expect you (a) to bring enthusiasm, creativity, and hard work, (b) give lab seminars on your work, and (c) produce a final written report. In return this facilitates your critical thinking, presentations skills, and scientific writing. Your research, in collaboration and with support of team members, may lead to scientific publications. You will also get a good hands-on perspective at the frontier of machine intelligence and its applications in an interdisciplinary research group and environment.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Learning Generative Causal Models from Sparse Temporal Observations during Cellular Reprogramming

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Jesper Tegner

Recent work on stem cells and different mature specialized cells in different systems/organs (neurons, blood cells,) has revealed a stunning plasticity and capacity of reprogramming cells. For example, mature cells can be reprogrammed into pluripotent stem cells, and exciting work on engineered design of tissues and organs (organoids) are underway. On the one hand the community has since the sequencing of the human genome produced very efficient tools to read off the corresponding molecular events accompanying reprogramming and engineering of cells. Recently, the discovery of the CRISPR techniques has equipped us with unprecedented opportunities for precise writing or editing of the genomes. These developments in fundamental biology and biotechnology are currently opening new tools and perspectives of vital significance for drug development, regenerative medicine, synthetic biology, and personalized medicine. Yet, in essence all these efforts require and would be greatly facilitated if we could advance from correlative data-analysis to a predictive discovery of which interventions (edits, engineering) are producing which effects. Thus, we are facing the fundamental problem on how to discover causal relations from data, or in other words, can we derive quantitative predictive laws fromdata?We offer internships forseveral highly motivatedbachelor (B.Sc.) ormaster (M.Sc.) students who will explore this fundamental question primarily from a computational standpoint. This includes using high-performance simulations of dynamical models, and design of algorithms in a controlled in-silico environment. For example, to identify (a) efficient algorithms for generation of ensembles of dynamical models, (b) use supervised deep learning algorithms for pattern discovery in large-scale simulation data-sets, (c) to perform deep data-driven analysis of computational models in biology, (d) pursue investigations of transfer entropy and related techniques for system identification. These tools will be tested utilizing rich and recent molecular data on cellular reprogramming.

BAS/1/1078-01-01

jesper.tegner@kaust.edu.sa

learning-generative-causal-models-from-sparse-temporal-observations-during-cellular-reprogramming-Causality, Machine Learning, Stem Cells

computer science, mathematical modeling, machine learning, systems biology, bioscience

Individual projects will be tailored and narrowly designed from the above palette according to interest of the student, technical proficiency, and level of study. The project is suitable for candidates fascinated by dynamical causal systems, be it computational or those we find in the natural world, i.e. living cells. We expect you (a) to bring enthusiasm, creativity, and hard work, (b) give lab seminars on your work, and (c) produce a final written report.In returnthis facilitates your critical thinking, presentations skills, and scientific writing.Yourresearch, in collaboration and with support of team members, may lead to scientific publications. We publish avidly in both bioscience and computational sciences, not for the fame but rather as steps aiming to and motivated both by our quest of asking fundamental questions of relevance to human nature and discovery of transformative intelligent technologies inspired from nature. You will get a good hands-on perspective on the frontiers in dynamical systems and bioscience using state-of-the-art simulation and machine learning tools.

BioScience

Biological and Environmental Sciences and Engineering

Deep Learning and Machine Intelligence for Single Cell Genomics

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Jesper Tegner

Single cell biology and genomics in particular are currently transforming the biosciences. Single cell RNA sequencing (scRNAseq), method of the year 2013 (Nature Methods), has now matured and large amounts of scRNAseq are now available. These data, characterizing living systems at an unprecedented level of resolution, hold the promise to set the stage for a fundamental quantitative understanding of living systems with special reference to genomic regulation and collective computation. Yet, there are a number of open problems on how to think about these data and how to pragmatically analyze them.In parallel, we have witnessed a rapid development in machine learning. The rise of computation, such as supercomputers (shaheen@KAUST) and GPU based techniques, in conjunction with data explosion (often referred to as big data), has fuelled the development of new techniques aiming for machine intelligence. In particular, techniques inspired from livings systems, such as deep convolutional networks, currently experience a renaissance. Driving forces include not only data and computation but also the availability of suite of open source platforms (e.g. Theano, Caffe, Torch7, TensorFlow) supporting machine-learning algorithms. These algorithms represent industry standard for processing images, speech, text, and runs on the majority of services and devices provided by Google, Amazon, Facebook, to name a few big players, as well as a numerous startups.We offer internships for several highly motivated bachelor (B.Sc.) or master (M.Sc.) students who will identify (a) appropriate supervised deep learning architectures and training algorithms for scRNAseq data, (b) explore generative adversarial network (GANs) techniques for estimation of high-dimensional data distribution in the single cell gene expression space. This work will be used to develop new techniques and to address open problems in single cell genomics such as pseudo-temporal ordering of single cell data, clustering of data, investigate representations, transfer learning, and unsupervised feature discovery.

BAS/1/1078-01-01

jesper.tegner@kaust.edu.sa

deep-learning-and-machine-intelligence-for-single-cell-genomics-Machine Learning, Artificial Intelligence, Genomics

computer science, bioscience, machine learning, systems biology, artificial intelligence

Individual projects will be tailored and narrowly designed from the above palette according to interest of the student, technical proficiency, and level of study. The project is suitable for candidates fascinated of living systems, interested in cutting edge bioscience, and artificial intelligence for science and not for discovering cats in YouTube. We expect you (a) to bring enthusiasm, creativity, and hard work, (b) give lab seminars on your work, and (c) produce a final written report.In returnthis facilitates your critical thinking, presentations skills, and scientific writing.Yourresearch, in collaboration and with support of team members, may lead to scientific publications. We publish avidly in both bioscience and computational sciences, not for the fame but rather as steps aiming to and motivated both by our quest of asking fundamental questions of relevance to human nature and discovery of transformative intelligent technologies inspired from nature. You will also get a good hands-on perspective at the frontier of bioscience and machine intelligence in an interdisciplinary research group and environment.

BioScience

Biological and Environmental Sciences and Engineering

Brain Inspired Computing

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Khaled Nabil Salama

Biomedical Sensors

Program:

Electrical Engineering

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Khaled Nabil Salama

Novel Micro-optical structures on optical fiber tip with two-photon lithography

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Carlo Liberale

Development of a novel Stimulated Raman Scattering microscopy system

Program:

BioScience

Division:

Biological and Environmental Sciences and Engineering

Faculty Name:

Carlo Liberale

Theoretical and numerical study on complex materials

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Ying Wu

Classification of long non-coding RNAs

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Xin Gao

Long non-coding RNAs (lncRNAs) have been found to perform various functions in a wide variety of important biological processes. To make easier interpretation of lncRNA functions and conduct deep mining on these transcribed sequences, it is important to classify lncRNAs into different groups. lncRNA classification attracts much attention recently. The main technical difficulties are 1) the limited number of known lncRNAs (small training sample size), and 2) the very different lengths of lncRNAs. This project is to apply and further improve the string kernel algorithms developed in Prof. Gao’s group to the lncRNA classification problem.

BAS/1/1624-01-01

xin.gao@kaust.edu.sa

Long non-coding RNAs (lncRNAs) have been found to perform various functions

Computer science, bioinformatics, electrical engineering, applied mathematics

The visiting student for this project is expected to finish the following deliverables:1.      Give a throughout literature review on lncRNA classification methods and potential machine learning methods that can be applied to this problem. 2.      Get familiar with the string kernel algorithms developed in Prof. Gao’s group. 3.      Gather an lncRNA dataset to be used as the benchmark set for this research. 4.      Conduct a comprehensive comparative study of the state-of-the-art methods on the benchmark set. 5.      Apply the string kernel algorithms on lncRNA classification and evaluate the performance. 6.      If necessary, improve the string kernel algorithms to achieve better performance.Write a report to summarize the results.

Computer Science

Computer, Electrical and Mathematical Sciences and Engineering

Computational Bioscience Research Center

Nonlinear Partial Differential Models

Program:

Applied Mathematics and Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Diogo Gomes

Novel Pincer complexes for catalysis

Program:

Chemistry

Division:

Physical Sciences and Engineering

Faculty Name:

Kuo-Wei Huang

Role of non-classical hydrogen bonding in organocatalysis

Program:

Chemistry

Division:

Physical Sciences and Engineering

Faculty Name:

Kuo-Wei Huang

Deep Learning for Visual Computing

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Peter Wonka

Computer Graphics, Computer Vision, and Visualization

Program:

Computer Science

Division:

Computer, Electrical and Mathematical Sciences and Engineering

Faculty Name:

Peter Wonka

Deep-sea sediments off the Al Wajh Carbonate Platform, Red Sea - Sample preparation and analysis

Screening semiconductors for photoelectrochemical transistors

Sustainable membrane materials and separation processes for pharmaceuticals and the environment

Improving Solar Corona Simulations with Advanced Boundary Conditions

Laser-based Sensor for Environmental Monitoring

Zero-carbon Fuels, e-Fuels and Biofuels: Analysis, Experiments and Modelling

Understanding the stability pathways of Tin based perovskties

Understanding the energetics of organic semiconductors in photovoltaics

Optimal strategies for resource-task network problems

Non-terrestrial Communication System for Aerial-based Object Recognition and Positioning

Leveraging Non-Terrestrial Platforms

Solar cells with Unconventional Shapes

Conservative Linear Multistep Methods For Time-dependent PDEs

Statistical Inference for High Dimensional Models with Applications to Imaging Genetics

Conceptual design of membrane processes

Investigating the Design and Engineering of Nanobodies for Advanced Biomedical Applications

Cell-free Protein Synthesis of Next-Generation Therapeutics

Nanobiomarine: Integrating Nanowire-Enhanced Beneficial Microorganisms for Advanced Coral Restoration

Large-Scale Volumetric Mesh Visualization and Analysis

Membrane development for sustainable separations

Uncovering and Addressing Bias in LLM Interactions

Accelerated simulation of reactive flows using deep neural networks

Unlocking the Secrets of the Extreme Microbiome: Biotechnological Frontiers on Earth and Beyond

Predicting Bacterial Antimicrobial Resistance Phenotypes from Genomic Biomarkers

Design and performance evaluation of various emerging 6G wireless communication technologies

Explainable Artifical Intelligence Methods for Wellbore Damage Zone Prediction

Learning to Cooperate in Multi-robot Task Allocation

Polkadot Graph Analysis

Encrypted Traffic Classification

Materials Engineering for Soil Amendment in Saudi Arabia

Modeling human early development with stem cell-based integrated embryo-like models

Parameter-free optimization, universal prediction, and Kolmogorov complexity

Training dynamics of Adam

Coral Microbiology and probiotics

Natural Deep Eutectic Solvents for water remediation

Light-induced metal ion (de)complexation

Bioaccumulation of emerging contaminants in Red Sea coral reef organisms

Joint models for longitudinal and survival data

Continuous-mode SandX Rector Automation

Reactions of lung surfactants at the air–water interface

Quantifying microbial diagenesis in shallow marine carbonate sediment using CT-scan

Geochemical investigation and abrasion experiments to decipher the origin of lime mud

Impact of mangrove ecosystems on carbonate sediment: integration of carbonate chemistry and petrography.

Unraveling the molecular basis of coral symbiosis and bleaching

Coral reef ecology in a changing environment

Deep Learning for Visual Computing (Computer Vision, Machine Learning, Graphics)

Safety-Guaranteed Planning and Control for Autonomous Underwater Robots

How does Federated Learning work in the real world?

Dexterous Robot Manipulation using Physics Engine

Siliciclastics in Al Wajh carbonate lagoon

Seeing the invisible – air flow around droplet upon impact

Engineering an isothermal amplification strategy for ultrasensivite and quantitative detection of microRNA cancer biomarkers

Unraveling the molecular basis of immune signaling

Protein Synthetic Biology

Contextualized Embeddings for Biomedical Data

Characterization of IL11-deficiency in humans

Security analysis of Docker-based containerized environments

Monitoring containerized environments for security state error detection

Trees, Algebras, and Differential Equations: Extending the B-series.jl package for numerical analysis of initial value problems

Seawater Reverse osmosis (SWRO) pretreatment impact on microbial growth potential

ClO2 for biofouling control in Seawater Reverse Osmosis

Breaking the Vehicle Over-The-Air Update System

Vehicle Intrusion Resilience Systems in Action

Rejuvenation of Diverse FPGA Softcores in a SoC

Useful Bitcoin Mining with a Matrix-based Puzzle

Advanced Breach and Attack Simulation using ML

Achieving sustainable urban greening through the integration of anaerobic membrane bioreactor and nature-based biofiltration landscaping gardens.

Integrating microbial electrolysis cell with anaerobic digestion to enhance resource recovery from waste activated sludge

Tackling the challenges of NO-Laser Induced Fluorescence technique in hydrogen detonation

Scaling Graph Neural Networks to 1000s of GPUs

Statistical and machine learning methods for health and environmental applications.

Egocentric Video Understanding

Next Generation Continual Learning

Graph Neural Networks for Science and Engineering

Next Generation 3D Understanding

Enzymatic Synthesis – Enzyme Characterization and Cascade Engineering

Biocatalytic Amine Synthesis

The Development of Organic Transformations via Photocatalysis

Electro-catalyzed C-C and C-X bond cross-couplings

Functional metagenomics: AI-based analysis of complex microbial interactions