A Cloud-Based Geo-AI Framework for Automated High-Resolution Flood Mapping with Explainable Machine Learning
Z. Cong, Mirza Waleed, S. Ullah, F. Tahir, S. G. Al-Ghamdi
Scientific Reports
Abstract
This study presents a hybrid cloud-local Geo-AI framework for high-resolution flood mapping. It combines multi-source data processing in Google Earth Engine with local machine-learning benchmarking and interpretation. Applied to the 2022 Pakistan floods, the workflow derives training samples from Sentinel-1 time-series statistics, compares 17 algorithms, and uses SHAP to interpret influential predictors. Spatial comparison with an external flood product identifies areas of agreement and discrepancy. Further evaluation across regions and of end-to-end operational latency remains necessary.

Research topics (7)
- Flood Mapping
- Cloud Computing
- Geo-AI
- Explainable AI
- Machine Learning
- Google Earth Engine
- Remote Sensing
Cite This Paper
Related Publications
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
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
2026 · International Journal of Applied Earth Observation and Geoinformation
BAM: A Physics-Informed Self-Supervised Framework for Near-Real-Time Wildfire Burned Area Mapping from Multi-Source Earth Observation