This PhD project at the University of Bristol addresses the urgent global challenge of flood risk by developing a physics-informed AI framework that leverages high-resolution satellite data from the SWOT mission. Floods are among the most destructive natural hazards, causing extensive human, economic, and infrastructural losses worldwide. Traditional flood models often lack the real-time data and computational efficiency required for accurate, global-scale forecasting. This research aims to bridge the gap between flood hazard observation and real-world risk assessment for vulnerable communities and economies. The project will integrate SWOT satellite data with other remote sensing products (such as Sentinel-1/2) and static datasets (topography, land use) to derive key hydrological variables like water level, slope, and discharge. The core innovation is a physics-informed AI model that combines deep learning with hydrodynamic principles, ensuring predictions are both data-driven and physically plausible. Socio-economic vulnerability will be assessed by integrating global datasets on population density, economic activity, and infrastructure, using indices to translate flood hazard into quantifiable risk for different communities and sectors. Validation will involve comparisons with official hazard maps, historical flood records, and economic loss data, while sensitivity analyses will explore how socio-economic assumptions affect hotspot identification. The outcome will be high-resolution risk maps that support equitable disaster management and climate adaptation, empowering decision-makers to identify vulnerability hotspots and prioritize resilient infrastructure. The project is supervised by Dr. Ce Zhang, Prof. Jeff Neal, and Prof. Peter M. Atkinson in the School of Geographical Sciences. Funding is provided through the FLOOD-CDT studentship, covering stipend, tuition fees, and research support. Applicants should have a strong background in relevant disciplines and an interest in AI, remote sensing, and data analysis. Applications are open for a September 2026 start, with a deadline of January 8, 2026.