HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands

TL;DR

HaorFloodAlert is a deseasonalized machine learning ensemble that accurately predicts 72-hour flood probability in Bangladesh's haor wetlands, incorporating SAR data and a rice damage estimator.

Contribution

The paper introduces a novel deseasonalized ML ensemble for flood prediction that accounts for seasonal effects and integrates SAR data for early warning in Bangladesh.

Findings

Achieved 89.6% LOOCV accuracy and 87.5% recall in flood prediction.

Validated SAR change detection with 84-91% spatial match.

Improved flood prediction accuracy by removing seasonal bias using temperature.

Abstract

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.