Dynamic Land Degradation Assessment: Integrating Machine Learning with Landsat 8 OLI/TIRS for Enhanced Spectral, Terrain, and Land Cover Indices

Land degradation is a critical environmental issue with far-reaching implications for ecosystems and human well-being. This study aimed to develop a robust methodology for mapping land degradation susceptibility using machine learning algorithms (MLA) -based approaches. Utilizing satellite imagery from Landsat 8 OLI/TIRS and ground truth data, we employed a comprehensive set of spectral indices to quantify various land surface parameters and processes. The resultant Dynamic Land Degradation (DLD) map, derived through MLA, revealed a diverse range of degradation levels across the study area. Based on the MLA- approaches, we derived five multifaceted indices from eight different multiband indices, and a MLA-based formula was generated and performed for the preparation of the DLD map of the study area. Validation using Area Under the Curve Receiver Operating Characteristic (AUC ROC) analysis demonstrated high accuracy and reliability in classifying different degradation classes, with an AUC value of 0.863. Our findings highlight the effectiveness of the developed methodology in accurately identifying five categories of DLD map with an extent, Very Highly Safe Lands (129.67 km2), Highly Safe Lands (658.95 km2), Moderately Safe Lands (1181.86 km2), Highly Degraded Lands (1471.45 km2), and Very Highly Degraded Lands (1242.92 km2). This research contributes to advancing the field of environmental monitoring by providing a robust framework for assessing land degradation susceptibility at a regional scale. The derived DLD map serves as a valuable decision support tool for land managers, policymakers, and environmental practitioners, enabling targeted interventions based on specific degradation risk levels. By fostering sustainable land use practices and effective conservation measures, our research offers significant societal benefits, including improved land management strategies, enhanced ecosystem resilience, and informed decision-making for sustainable development.