Identification of groundwater potential zones of Idukki district using remote sensing and GIS-based machine-learning approach

Abstract

Kerala's Idukki district, which is situated on the Western Ghats of India, is susceptible to flooding and landslides. As a result of the 2018 Kerala floods, this disaster-prone region experienced drought conditions. In order to lessen the effects of future disasters, it is also necessary to identify and evaluate the district's groundwater potential (GWP). This work used three machine-learning (ML) algorithms – Random Forest (RF), Adaptive Boosting (AdaBoost), and Gradient Boosting (GB) – to model and produce GWP zonation maps for the Idukki district. Fourteen conditioning factors include elevation, slope, curvature, Topographic Roughness Index, lineament density, soil, geology, geomorphology, Topographic Wetness Index, Sediment Transport Index, drainage density, rainfall, land-use/land-cover (LULC), and Normalised Difference Vegetation Index that were adopted as input parameters in the modelling. All showed prominence when they were examined for feature importance using the recursive feature elimination (RFE) method. The RF model outperformed the other two ML models in terms of fit, with an area under curve (AUC) value of 0.92, while the GB and AdaBoost models displayed less fit, with AUC values of 0.90 and 0.88, respectively. GWP maps produced by each model were reclassified into five zones – very high to very low – it was discovered that the zones were evenly spread throughout the Idukki region.