Artificial intelligence (AI) is changing how we extract information from Earth observation data. Satellite constellations and unmanned aerial vehicles (UAVs) now collect imagery at a volume, frequency and spatial detail that traditional analysis methods struggle to handle. AI methods turn these data into timely and accurate information on vegetation, ecosystems and agricultural systems. This capability is especially valuable in arid regions such as Saudi Arabia, where ground observations are sparse and environmental change is rapid. The field is advancing on three connected fronts. Deep learning models (i.e., convolutional networks and vision transformers) are now state of the art for many tasks, including image classification, segmentation, object detection and the estimation of biophysical variables. Geospatial foundation models, pretrained on large image archives often drawn from several sensors, can be adapted to new tasks and regions with fewer labelled samples. More recently, applications built on large language models (LLMs) have started to link imagery with natural language, so users can query, analyse and interpret remote sensing data through conversational and agent-based workflows. 

This internship is hosted by the Hydrology, Agriculture and Land Observation (HALO) group at KAUST, which uses UAV and satellite data to monitor natural and agricultural ecosystems across the Kingdom. The visiting student will support the design, training, evaluation and deployment of AI methods across ongoing group projects. Depending on the student's background and project needs, the work may span the full chain from data preparation to model development and application. The student will gain hands-on experience with large Earth observation datasets, KAUST high-performance computing resources, and field-collected reference data.

Keywords for web search
Remote sensing; Artificial intelligence; Deep learning; Geospatial foundation models; Large language models; UAV; Satellite imagery; Earth observation.

Viruses that replicate their own genomes need two enzymatic activities at the replication fork. They must unwind the DNA double helix and make the short RNA primers that start each new strand. Herpesviruses do both with a single machine: the helicase–primase complex. It is built from a helicase, a primase, and an accessory subunit and this assembly is essential for viral replication and a validated antiviral target. Inhibitor-bound structures exist for one herpesvirus, but for most family members the architecture of the machine and the basis of inhibitor sensitivity remain open questions.

Our lab studies molecular machines of human and viral DNA replication by cryo-EM. In this project, the student will build and refine atomic models of viral helicase–primase complexes into experimental cryo-EM maps, using AI-based structure prediction to generate starting models. These models will then be refined and validated in using standard structural biology tools. The refined models will show how the helicase and primase modules are arranged, trace the bound nucleic acid, and map the inhibitor-binding pocket, including the positions of known resistance mutations.

The work is mostly computational, but it sits inside an active experimental program. There is room to learn the bench side as well: expressing and purifying the subunits, reconstituting the complex, running activity assays, and preparing cryo-EM grids. How the time is split between modeling and bench work depends on the student's background and interests. No prior cryo-EM experience is needed. 

All cells in an organism share the same genetic blueprint, yet exhibit diverse identities and functions, ultimately culminating in a functional tissue system and, finally, an organism. What makes this remarkable phenomenon possible is, to a great extent, dictated by epigenetics: the chemical marks that decorate not only the genetic material but also its closely associated proteins, namely the histones. These modifications on chromatin modulate its dynamic structure and thereby influence gene expression programs that define cellular function.

This project aims to understand how metabolic changes influence chromatin organization and gene regulation. Notably, many of the substrates required for the deposition of epigenetic marks are derived directly from intracellular metabolic pathways. This intimate connection between metabolome and epigenome suggests that fluctuations in metabolite availability can have profound effects on chromatin organization and gene regulation.

We will analyze and integrate multi-omics datasets generated in the lab, including RNA-seq, ATAC-seq, ChIP-seq, and emerging single-cell multiome data. The goal is to connect these complementary datasets to build a coherent view of how chromatin structure and gene regulation respond to metabolic perturbations. The project combines computational analysis with biological interpretation to uncover regulatory mechanisms governing chromatin dynamics.

Very long, linear DNA molecules carry the inheritable and instructive information of an organisms’ genome that is at the foundation of life. To be packaged and protected, genomes are organized into chromatin. This process is not static but highly dynamic constituting a fundamental regulatory system. Different proteins of the linker histone family are crucial for organizing DNA into chromatin. Various, often sporadic findings point to changes in linker histone expression and/ or changes in their composition (aka mutation) to be linked to various diseases including diabetes, cardiovascular disease and cancer. We have set up different experimental systems to thoroughly analyze the role of linker histones in cell differentiation, organismal development and tissue homeostasis. In this VSRP project, we want to adopt lentiviruses for perturbing the expression of linker histones in human embryonic stem cells. We will engineer knockdown (using siRNA) and overexpression schemes to analyze how changes in the levels of linker histones affect cell pluripotency and stem cell differentiation. The work is embedded into two separate projects that investigate the role of linker histones in myogenesis, and neurodevelopment and besides specific experimentation offers broad insights into different aspects of epigenetics in health and disease.