Sub-watershed prioritization using morphometric analysis, principal component analysis, hypsometric analysis, land use/land cover analysis, and machine learning approaches in the Peddavagu River Basin, India

Abstract

Water resource management is critical in the face of climate change to reduce water scarcity and meet the demands of an expanding population. Prioritization of watersheds has gained significance in natural resource management, particularly in the context of watershed management. This study prioritizes sub-watersheds for the Peddavagu basin using five methods. The four methods mentioned above can be estimated utilizing remote sensing (RS) and geographic information system (GIS) approaches, while linear discriminant analysis (LDA) is estimated using machine learning techniques. The catchment resulted in the formation of 13 sub-watersheds. The quantitative measurements of morphometric analysis, including linear, relief, and areal, were considered, and 18 morphometric characteristics were chosen to rank and prioritize sub-watersheds. Principal component analysis (PCA) was used to rank and prioritize sub-watersheds based on four highly correlated morphometric parameters. The land use/land cover (LULC) analysis used four features to prioritize sub-watersheds. The LDA analysis used two features to prioritize sub-watersheds. Using hypsometric integral (HI) values, prioritization has been done. Sub-watersheds were prioritized. Based on five methods, the sub-watersheds were classified as low, medium, and high. Among the sub-watersheds identified as high priority, immediate priority is assigned to SW10. Decision-makers in the research region can use the findings to plan and implement watershed management techniques. HIGHLIGHTS A novel machine learning, specifically a linear discriminant analysis technique, was proposed for the prioritization of watersheds.; SW10 stands out as the top choice for ensuring efficient watershed management as per requirements.; The study's outcomes provide decision-making authorities with valuable information to guide the implementation of sustainable watershed management initiatives.;

Keywords

• ha
• lda
• lulc
• morphometric analysis
• pca