HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands
About
Flash floods in Bangladesh's haor wetlands show up with almost no warning. They wreck the annual boro rice harvest. Current setups, built for riverine floods, miss backwater dynamics entirely. These basins are flat. Water does not behave like it does on the Brahmaputra. We built HaorFloodAlert, a deseasonalized machine learning ensemble that forecasts 72-hour flood probability for the Sunamganj Haor (approximately 8,000 km2). Temperature was acting as a seasonal cheat code - it inflated accuracy by 6.9 pp just because floods happen in warm months. We caught that. We also built an upstream Barak River Sentinel-1 SAR proxy from Silchar, Assam, giving about 36 hours of lead time. Otsu-thresholded SAR change detection validates at 84-91 percent spatial match. The operational ensemble (RF 0.5625 + XGBoost 0.4375) hits 89.6 percent LOOCV accuracy, 87.5 percent recall, and 0.943 AUC-ROC on 77 real Sentinel-1 events. A three-tier alert pipeline and a BRRI-calibrated boro rice damage estimator are included.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Haor Flood Prediction | Sunamganj Haor Bangladesh Backwater (LOOCV) | Accuracy89.6 | 1 | |
| Flash Flood Prediction | NE Haor Bangladesh Flash (LOOCV) | -- | 1 | |
| Flood Prediction | National Bangladesh Riverine | -- | 1 | |
| Flood Susceptibility Mapping | Coastal region Bangladesh Riverine | -- | 1 | |
| Flood Susceptibility Mapping | SE Hilly region Bangladesh Flash | -- | 1 | |
| Post-event Flood Mapping | Coastal region Bangladesh Cyclone (Post-event) | -- | 1 |