article · International Soil and Water Conservation Research
Gully erosion is a major natural hazard in arid and semi-arid regions that damages ecosystems and human well-being. To identify priority areas for intervention, four hybrid machine learning models combined with the weight of evidence technique were developed to map gully erosion susceptibility in the El Ouaar watershed within Morocco's Souss plain. The models evaluated were Multilayer Perceptron, K Nearest Neighbours, Logistic Regression, and Random Forest. Using geographic information systems and remote sensing data, the models analysed twelve conditioning variables, such as slope, rainfall, lithology, and land use, across 314 identified gully points. Testing demonstrated that the Random Forest hybrid model delivered the highest predictive accuracy, followed closely by the K Nearest Neighbours hybrid model. These susceptibility maps offer planners practical resources for targeting conservation interventions.
Gully erosion severely degrades landscapes and disrupts ecosystem services in dry environments. Accurate susceptibility maps enable local authorities, land managers, and environmental planners to identify high-risk zones quickly. This spatial insight ensures that soil and water conservation measures are targeted where they are most urgently required, helping to protect vulnerable communities and natural resources.
The models offer applied decision-making tools for regional land planners, environmental consultancies, and water basin management authorities. Demonstrated at watershed level using regional survey and satellite data, this applied and tested method could be integrated into commercial geographic information software or risk assessment platforms to direct erosion mitigation resources efficiently.
AI-generated from the published abstract. Always read the original work before citing.
Gully erosion is one of the main natural hazards, especially in arid and semi-arid regions, destroying ecosystem service and human well-being. Thus, gully erosion susceptibility maps (GESM) are urgently needed for identifying priority areas on which appropriate measurements should be considered. Here, we proposed four new hybrid Machine learning models, namely weight of evidence -Multilayer Perceptron (MLP- WoE), weight of evidence –K Nearest neighbours (KNN- WoE), weight of evidence - Logistic regression (LR- WoE), and weight of evidence - Random Forest (RF- WoE), for mapping gully erosion exploring the opportunities of GIS tools and Remote sensing techniques in the El Ouaar watershed located in the Souss plain in Morocco. Inputs of the developed models are composed of the dependent (i.e., gully erosion points) and a set of independent variables. In this study, a total of 314 gully erosion points were randomly split into 70% for the training stage (220 gullies) and 30% for the validation stage (94 gullies) sets were identified in the study area. 12 conditioning variables including elevation, slope, plane curvature, rainfall, distance to road, distance to stream, distance to fault, TWI, lithology, NDVI, and LU/LC were used based on their importance for gully erosion susceptibility mapping. We evaluate the performance of the above models based on the following statistical metrics: Accuracy, precision, and Area under curve (AUC) values of receiver operating characteristics (ROC). The results indicate the RF- WoE model showed good accuracy with (AUC = 0.8), followed by KNN-WoE (AUC = 0.796), then MLP-WoE (AUC = 0.729) and LR-WoE (AUC = 0.655), respectively. Gully erosion susceptibility maps provide information and valuable tool for decision-makers and planners to identify areas where urgent and appropriate interventions should be applied.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.iswcr.2023.09.008
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
