Flood susceptibility mapping using Sentinel 1 and frequency ratio technique in Jinjiram River watershed, India

Advancing flood risk assessment: Multitemporal SAR-based flood inventory generation using transfer learning and hybrid fuzzy-AHP-machine learning for flood susceptibility mapping in the Mahananda River Basin

The Mahananda River basin, located in Eastern India, faces escalating flood risks due to its complex hydrology and geomorphology, threatening socioeconomic and environmental stability. This study presents a novel approach to flood susceptibility (FS) mapping and updates the region's flood inventory. Multitemporal Sentinel-1 (S1) SAR images (2020-2022) were processed using a U-Net transfer learning model to generate a water body frequency map, which was integrated with the Global Flood Dataset (2000-2018) and refined through grid-based classification to create an updated flood inventory. Eleven geospatial layers, including elevation, slope, soil moisture, precipitation, soil type, NDVI, Land Use Land Cover (LULC), geomorphology, wind speed, drainage density, and runoff, were used as flood conditioning factors (FCFs) to develop a hybrid FS mapping approach. This approach integrates the Fuzzy Analytic Hierarchy Process (FuzzyAHP) with six machine learning (ML) algorithms to create hybrid models FuzzyAHP-RF, FuzzyAHP-XGB, FuzzyAHP-GBM, FuzzyAHP-avNNet, FuzzyAHP-AdaBoost, and FuzzyAHP-PLS. Future flood trends (1990-2030) were projected using CMIP6 data under SSP2-4.5 and SSP5-8.5 scenarios with MIROC6 and EC-Earth3 ensembles. The SHAP algorithm identified LULC, NDVI, and soil type as the most influential FCFs, contributing over 60 % to flood susceptibility. Results show that 31.10 % of the basin is highly susceptible to flooding, with the western regions at greatest risk due to low elevation and high drainage density. Future projections indicate that 30.69 % of the area will remain highly vulnerable, with a slight increase under SSP5-8.5. Among the models, FuzzyAHP-XGB achieved the highest accuracy (AUC = 0.970), outperforming FuzzyAHP-GBM (AUC = 0.968) and FuzzyAHP-RF (AUC = 0.965). The experimental results showed that the proposed approach can provide a spatially well-distributed flood inventory derived from freely available remote sensing (RS) datasets and a robust framework for long-term flood risk assessment using hybrid ML techniques. These findings offer critical insights for improving flood risk management and mitigation strategies in the Mahananda River basin.

Optimum flood inundation mapping in mountainous regions using Sentinel-1 data and a GIS-based multi-criteria approach: a case study of Tlawng river basin, Mizoram, India

Floods pose a significant global threat, impacting populations and infrastructure worldwide. However, mapping flood inundation solely with SAR data faces challenges in hilly terrain. To address this, the study integrates SAR data with a GIS-based multi-criteria approach (MCA), incorporating various indices and parameters, to enhance the accuracy of identifying potential flood zones. The findings demonstrate the effectiveness of this approach, with high accuracy validated using GPS data and a physics-based 3-step method. The results also indicate a high level of accuracy, with an area under the curve (AUC) value of 0.92 when comparing Sentinel-1 SAR and optical data during the process of extracting permanent water bodies. The Sentinel-1 SAR-derived flood extent was found to be 9.56 m horizontally distant from the observed maximum flood mark, while the physics-based 3-step approach estimated the inundation extent to be 9.28 m away. However, both methods accurately matched the vertical elevation of 40 m above mean sea level (MSL). The findings underscore the effectiveness of SAR data and GIS-based MCA in monitoring and mapping floods in challenging terrains, offering practical implications for flood management strategies in Tlawng river basin.

Evaluation of urban flood susceptibility through integrated Bivariate statistics and Geospatial technology

Flood disasters are frequent natural disasters that occur annually during the monsoon season and significantly impact urban areas. This area is characterized by impermeable concrete surfaces, which increase runoff and are particularly susceptible to flooding. Therefore, this study aims to adopt Bi-variate statistical methods such as frequency ratio (FR) and weight of evidence (WOE) to map flood susceptibility in an urbanized watershed. The study area encompasses an urbanized watershed surrounding the Chennai Metropolitan area in southern India. The essential parameters considered for flood susceptibility zonation include geomorphology, soil, land use/land cover (LU/LC), rainfall, drainage, slope, aspect, Topographic Wetness Index (TWI), and Normalized Difference Vegetation Index (NDVI). The flood susceptibility map was derived using 70% of randomly selected flood areas from the flood inventory database, and the other 30% was used for validation using the area under curve (AUC) method. The AUC method produced a frequency ratio of 0.806 and a weight of evidence value of 0.865 contributing to the zonation of the three classes. The study further investigates the impact of urbanization on flood susceptibility and is further classified into high, moderate, and low flood risk zones. With the abrupt change in climatic scenarios, there is an increase in the risk of flash floods. The results of this study can be used by policymakers and planners in developing a preparedness system to mitigate economic, human, and property losses due to floods in any urbanized watershed.