Advancing soil erosion prediction in Wadi Sahel-Soummam watershed Algeria: A comparative analysis of deep neural networks (DNN) and convolutional neural networks (CNN) models integrated with GIS

Abstract

This study employs adaptive deep learning (utilizing DNN and CNN approaches) to accurately predict soil erosion, a crucial aspect of sustainable soil resource management. The goal is to develop fuzzy logic models for erosion forecasting in a large watershed with limited in-puts, comparing them to predictions from the Revised Universal Soil Loss Equation (RUSLE). Integration of GIS enables analysis of satellite data, providing crucial details like land use, slope, rainfall distribution, and flow direction. This synergistic approach enhances erosion prediction capabilities and yields spatial erosion distributions. Producing precise erosion risk maps within GIS is crucial for prioritizing high-risk areas and implementing effective conservation methods in the Wadi Sahel watershed, Algeria. The assessment in the Oued Sahel-Soummam watershed involved overlaying five RUSLE factor maps using Arc GIS spatial analysis, resulting in an aver-age annual soil loss of 4.22 tons per hectare. The DNN and CNN models were integrated with GIS for detailed calculation of annual average soil loss (tons per hectare per year) and mapping erosion risk areas in Wadi Sahel-Soummam watershed. Using the CNN model, estimated annual soil loss in Sahel-Soummam wadi was about 4.00 tons per hectare per year, while the DNN model estimated around 4.13 tons per hectare per year. This study employed two deep learning models for erosion prediction, with the DNN model featuring six hidden layers performing no-tably better than the compared CNN model.