Rapid flood inundation mapping for effective management: A machine learning and pixel-based classification approach in Feni District, Bangladesh

This research highlights the efficacy of integrating Sentinel-1 SAR data with pixel-based classification and ML methods for expedited flood mapping in the Feni District during the August2024 floods. This research introduces a novel methodology for expedited flood inundation mapping, using the August 2022, 2023, and especially the 2024 flood events in the Feni District as the primary case study. Effective flood management requires precise and timely flood mapping methodologies to adopt disaster risk reduction strategies and enable efficient response efforts. T

The research confirms the efficacy of these techniques for real-time flood monitoring and underscores the importance of dependable training samples and flexible thresholds. However, the RF classifier is sensitive to training data quality and may struggle with misclassification in highly heterogeneous flood landscapes, particularly when reference data are limited. These findings highlight the critical importance of satellite imagery and ML in improving flood response and management tactics in Bangladesh, a nation with heightened risks from climate change-induced flooding. F