Potential erosion and sedimentation based on land use change by using cellular automata-artificial neural network

Erosion and sedimentation are global environmental threats that cause land degradation, reduced agricultural productivity and increased flooding risks, leading to the loss of 75 billion tons of fertile soil annually. This study employs advanced remote sensing and machine learning techniques to analyze land use changes and their impacts on erosion and sedimentation at the sub-watershed level. Sentinel-2A images from multiple years were used and classified into 17 distinct land use classes through a supervised classification technique. The baseline land use data served as the foundation for future predictions, with a business-as-usual scenario modelled using cellular automata and artificial neural networks (CA-ANN). Land use factors were incorporated into the USLE model to generate an erosion map and to perform sediment retention analysis using the InVEST model. By 2025, over 35% of the total area is projected to experience significant deforestation, with forested areas being converted into orchards, shrubs, bare land, agricultural dry land and settlements. In 2022, forest area transformation resulted in a 25% increase in erosion and an 18% rise in sedimentation, with these figures expected to climb further by 2025. Our study recommends the CA-ANN model as a tool to predict land use changes and guide interventions, ensuring sustainable management of sub-watershed areas.