Soil Erosion Assessment Using RUSLE & ANN Models and Identify Correlation by Landslide Frequency Ratio Method: A Case Study of Kalu River Catchment of Sri Lanka

Abstract

Soil erosion is a significant environmental concern that can have adverse effects on agricultural productivity and natural resource sustainability. This research focuses on assessing soil erosion in the Kalu River catchment of Sri Lanka using the Revised Universal Soil Loss Equation (RUSLE) and Artificial Neural Network (ANN) models. The study aims to quantify yearly soil loss between 2000 and 2020 and identify the spatial pattern of soil erosion risk. The results of the study indicate that the K factor, LS factor, P factor, C factor, and R factor have varying levels of influence on soil erosion. An ANN model is used to accurately predict soil erosion, but the RUSLE model is found to be more effective in evaluating soil erosion susceptibility in the specific study area. The research also examines the variation in soil erosion among sub-catchments within the Kalu River catchment. Sub-catchment A10 exhibits the highest soil erosion value, while A4 has the lowest. The Landslide Frequency Ratio (LFR) is employed to establish a correlation between soil erosion hazard classes and landslide frequency. High-priority areas for soil conservation measures are identified based on LFR values, soil erosion rates, and land-use change. The findings underscore the importance of estimating soil erosion rates, creating soil erosion hazard zonation maps, and prioritizing areas for soil conservation practices and sustainable land management. Policymakers, land-use planners, and farmers can utilize this research to make informed decisions and promote sustainable land-use practices. The study contributes to the understanding of soil erosion factors and provides valuable insights for future research in other regions.