Hybrid regularization and weighted subspace algorithms with random forest model for assessing piping erosion in semi-arid ecosystem

Land degradation encompasses ecological, biological, and physical deterioration of land resulting from natural or anthropogenic factors, including soil erosion. Piping erosion, specifically in arid and semi-arid regions, is recognized as a significant cause of land degradation. Therefore, it is crucial to identify the influential factors and spatially model this phenomenon to effectively control it. This investigation aims to study the spatial modeling and evaluation of piping erosion using machine learning models: random forest (RF) and two hybrid models, regularized random forest (RRF) and weighted subspace random forest (WSRF), in the Khoshkrood watershed of Markazi Province, Iran. In this study, 70% of the 179 recorded locations of piping erosion were randomly selected for model construction, while the remaining 30% were used for model validation. Fourteen geo-environmental variables affecting piping erosion were used as independent factors for modeling. The performance of the machine learning models was evaluated using five criteria, including sensitivity, specificity, and area under the curve (AUC). The results demonstrated that all three models performed well in predicting piping erosion. The AUC values for the WSRF, RRF, and RF models were 80.93%, 80.43%, and 79.11%, respectively. Moreover, the analysis of relative variable importance revealed that elevation was the most influential variable across all three models. The findings emphasize the significance of utilizing machine learning models for predicting and managing land degradation phenomena. By identifying influential geo-environmental and employing accurate spatial models, effective control measures can be implemented to mitigate the adverse impacts of piping erosion in arid and semi-arid regions.