What question did this study set out to answer?

The research aims to assess flood susceptibility in the Koshi River Basin using SAR imagery and machine learning.

April 3, 2026Open Access

Geospatial analysis and machine learning for flood susceptibility mapping

Key Points

The research aims to assess flood susceptibility in the Koshi River Basin using SAR imagery and machine learning.
Conducted a multi-year flood analysis using Sentinel-1 SAR data (2019–2023).
Created a flood inventory with 375 flood and 375 non-flood points based on environmental and climatic factors.
Applied machine learning classifiers: bagging, random forest, support vector machine, and AdaBoost to generate susceptibility maps.
Evaluated model performance using accuracy, precision, recall, F1-score, and AUC metrics.
Bagging classifier achieved the highest performance metrics, including 94.52% accuracy.
Identified 6.185% of the basin as highly susceptible to flooding.
Strong model agreement between bagging and random forest indicated consistent performance, while rule-based methods showed limitations.

Abstract

ABSTRACT Graphical Abstract Sentinel-1 SAR–based flood analysis and machine learning workflow producing a flood susceptibility map for the Koshi River Basin. This study produces a multi-year flood susceptibility assessment for the Koshi River Basin, Nepal, by integrating Sentinel-1 SAR imagery with machine-learning and geographic information systems (GIS)-based approaches. Five-year (2019–2023) temporal flood analysis from Sentinel-1 GRD data was used for the preparation of flood inventory, consisting of 375 flood and 375 non-flood points by extracting multi-year composites alongside 11 environmental, topographic, climatic, and vegetation-based conditioning factors, which served as the foundation for training and validating the susceptibility models. The four machine learning (ML) classifiers: bagging, random forest (RF), support vector machine (SVM), and AdaBoost were evaluated against the weighted sum method. Bagging achieved the highest performance (accuracy 94.52%, precision 95.45%, recall 95.45%, F1-score 95.45%, and AUC 0.990) and identified 6.185% of the basin as highly susceptible to flooding. Strong agreement between bagging and RF (r = 0.76) indicated consistent model behaviour, while weaker correlations with the weighted sum method underscored limitations of rule-based approaches in capturing nonlinear flood processes. The combination of a multi-year SAR-based flood inventory and ensemble ML techniques demonstrates clear advantages in generating reliable susceptibility maps, providing actionable evidence to support land-use planning, disaster preparedness, and targeted flood mitigation.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper