HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910237090381824 |
|---|---|
| author | Koli, Salma Hoque Talukdar Jely, Fahima Haque Talukder Alim, Md. Samiul Hossen, Md. Zakir |
| author_facet | Koli, Salma Hoque Talukdar Jely, Fahima Haque Talukder Alim, Md. Samiul Hossen, Md. Zakir |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20167 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands Koli, Salma Hoque Talukdar Jely, Fahima Haque Talukder Alim, Md. Samiul Hossen, Md. Zakir Artificial Intelligence Machine Learning 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. |
| title | HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.20167 |