Abstract. Soil erosion represents a major environmental issue that threatens ecosystem integrity and land sustainability, making the development of reliable susceptibility models crucial for supporting mitigation and management policies. This study evaluates the potential of three machine learning algorithms Weighted Subspace Random Forest (WSRF), Regularized Random Forest (RRF), and Naive Bayes (NB) for soil erosion susceptibility mapping in the Pardo River watershed, situated between the states of São Paulo and Minas Gerais, Brazil. A total of 120 sampling locations, including erosion and non-erosion occurrences, were identified through field surveys and high-resolution imagery obtained from Google Earth Pro. Initially, fifteen conditioning factors related to erosion processes were considered; however, after applying multicollinearity and relevance analyses, thirteen variables were retained for the final modeling framework. To evaluate model robustness, the dataset was randomly partitioned into training (70%) and testing (30%) subsets. Model performance was assessed using statistical indicators, including accuracy and AUC-ROC metrics. The NB, RRF, and WSRF models achieved accuracy values of 0.87, 0.89, and 0.88, respectively, while the corresponding AUC-ROC values reached 0.93, 0.96, and 0.95. Among the evaluated approaches, RRF yielded the highest predictive performance, demonstrating the effectiveness of machine learning techniques for supporting sustainable land management and erosion-prone area conservation. In addition, the proposed methodological framework offers a transferable approach for future susceptibility studies and contributes to expanding geospatial modeling applications across different environmental settings.
Francisco Hélter Fernandes do Amaral, A. Velástegui-Montoya, Éder Mileno Silva De Paula· ISPRS Annals of the Photogra...· 0 citations
Abstract. Mining is a strategic driver of economic development, yet it generates substantial impacts on landscape structure, soil integrity, and water systems. During ecological restoration, slope erosion remains a critical challenge for ensuring long-term geomorphological stability and ecosystem recovery. This study evaluates erosion dynamics on restored mining slopes by integrating Geographic Information Systems (GIS) and Unmanned Aerial Systems (UAS) for high-resolution terrain monitoring and quantification of soil loss. Research was conducted at the Lázaro quarry (Tarragona, Spain) using a fixed-wing UAS equipped with a multispectral camera to produce detailed orthophotos and Digital Elevation Models (DEMs), which were compared with historical LiDAR data. Height Difference Models (HDMs) and volumetric calculations were applied to quantify erosion and deposition. Statistical assessment included descriptive indicators, error metrics (ME, MAE, RMSE), distribution parameters (median, IQR, skewness), and spatial autocorrelation (Moran’s I). Three modelling approaches were developed and compared: a ridge-derived DEM (DEMp), a filtered DEM (DEMf), and a LiDAR-based DEM (DEMl). Their performance was evaluated in terms of accuracy, spatial resolution, and capacity to represent erosional microtopography. Results indicate that DEMp provides the most reliable volume estimates and best preserves pre-erosion morphology. In contrast, DEMf smooths surface detail, whereas DEMl provides an overview representation due to its lower spatial resolution. Overall, the integration of UAS photogrammetry and geospatial analysis proves effective for monitoring restored slopes, supporting precise erosion quantification and improved environmental management toward long-term landscape stability.
Mónica López Moncada, Joan-Cristian Padró, Vicenç Carabassa et al.· The International Archives o...· 0 citations
