A high-resolution global flood susceptibility dataset derived from multi-source earth observation and geospatial data
Mirza Waleed, Muhammad Sajjad, Sami G. Al-Ghamdi, Meng Gao
Scientific Data
Abstract
Floods are among the most damaging disasters worldwide, necessitating high-resolution modeling of where terrain and environmental conditions predispose societies to flooding. While geospatial data are invaluable for flood susceptibility mapping, comprehensive and globally consistent datasets remain scarce. We present the Global Flood Susceptibility Map (GFSM v1), a globally harmonized 30 m flood susceptibility dataset produced by incorporating multi-source flood conditioning factors accounting for topographic, hydrological, meteorological, and anthropogenic characteristics within a machine learning framework. A gradient-boosted tree model was trained on approximately 17,000 curated grid tiles with approximately 30.45 million training samples, using a global flood inundation dataset as training labels and nine conditioning factors. The model was deployed across 192 geopolitical and climate units to generate global pixel-level susceptibility. Rigorous cross-validation indicates strong predictive accuracy, with a median area under the curve of approximately 0.95, and the output captures localized flood-prone regions worldwide. GFSM v1 offers an open, high-resolution global resource to support informed flood risk management, particularly in data-sparse regions.

Research topics (7)
- Global Flood Susceptibility
- Earth Observation
- Machine Learning
- GeoAI
- Flood Risk
- Open Data
- Google Earth Engine
Research resources
- Explore the interactive GFSM dashboard
- Access the open GFSM v1 dataset on Zenodo
- View documentation, metadata, and reproducible examples on GitHub
GFSM v1 at a glance
GFSM v1 maps relative flood susceptibility in five classes at 30-meter resolution. The dataset covers approximately 80°N to 60°S and is distributed as tiled GeoTIFF files in World Mercator (EPSG:3395). The model uses nine flood-conditioning factors spanning topographic, hydrological, meteorological, vegetation, and anthropogenic characteristics.
GFSM is a susceptibility baseline rather than a real-time flood forecast or event-specific inundation model. It is intended for broad screening, comparative analysis, and exposure assessment alongside local observations, flood-defense information, drainage infrastructure, and jurisdiction-specific planning guidance.
Cite This Paper
Related Publications
2025 · International Journal of Disaster Risk Reduction
High-resolution flood susceptibility mapping and exposure assessment in Pakistan: An integrated artificial intelligence, machine learning and geospatial framework
2024 · Journal of Flood Risk Management (Wiley)
Advancing Flood Susceptibility Prediction: A Comparative Assessment and Scalability Analysis of Machine Learning Algorithms via Artificial Intelligence in High-Risk Regions of Pakistan
2026 · Scientific Reports
A Cloud-Based Geo-AI Framework for Automated High-Resolution Flood Mapping with Explainable Machine Learning