Water erosion causes the displacement of soil particles from higher to lower elevations, and this process intensifies when land use and vegetation cover change, such as through the conversion of forests into pastures or agricultural fields. Identifying priority areas for soil and water conservation practices is essential for promoting sustainable agriculture. Equally important is identifying the most influential factors driving erosion, as understanding these can guide effective land management strategies. Machine learning techniques, such as Random Forest, are valuable tools for analyzing large datasets and assessing the importance of variables. The primary aim of this study was to estimate soil losses due to land-use changes in the Peixe Angical Reservoir drainage basin using the Revised Universal Soil Loss Equation (RUSLE) within a Geographic Information System (GIS) framework, and to identify priority areas for soil conservation. Additionally, the study aimed to evaluate the contribution and importance of the RUSLE model factors (R, K, LS, and C) to soil loss using the Random Forest regression algorithm. Soil losses were computed for the chronological scenarios (1990, 2000, 2010, and 2017), using rasters with 90 m resolution to calculate the product of the R, K, LS, and C factors, along with the P factor. These soil losses were classified into erosion risk categories, ranging from very low (0 to 2.5 Mg ha-1 yr-1) to extremely high (greater than 100 Mg ha-1 yr-1). Soil losses in the basin increased over time. The Random Forest algorithm was applied to evaluate the importance of each factor. Rainfall erosivity was found to vary spatially, ranging from 7,047.64 MJ mm ha-1 h-1 yr-1 to 11,348.5 MJ mm ha-1 h-1 yr-1, while the LS factor exhibited values ranging from near 0 to over 20. Litholic Neosol (Entisol) was the predominant soil type in the drainage basin. In terms of land use, forests accounted for the largest portion of the basin: 55.60% in 1990, 51.31% in 2000, 48.88% in 2010, and 48.21% in 2017. The C factor, which reflects vegetation cover, was the most significant contributor to soil loss, accounting for 44.8% in 1990, 43.5% in 2000, 44.2% in 2010, and 44.4% in 2017, followed by the K factor (soil erodibility). These assessment techniques can be utilized in guiding conservation planning, thereby supporting sustainable land use practices.
Read full abstract