首页|University of Cadi Ayyad Researchers Provide New Study Findings on Machine Learn ing (Analysis of Soil Water Erosion Risk Using Machine Learning Techniques - A C ase Study of Ourika Watershed in Morocco)
University of Cadi Ayyad Researchers Provide New Study Findings on Machine Learn ing (Analysis of Soil Water Erosion Risk Using Machine Learning Techniques - A C ase Study of Ourika Watershed in Morocco)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Research findings on artificial intell igence are discussed in a new report. According to news originating from Marrake ch, Morocco, by NewsRx correspondents, research stated, "Soil erosion is a major environmental problem with detrimental consequences. In this article, we presen t a detailed study on the analysis of soil water erosion using Machine Learning (ML) techniques in the Oued Ourika watershed. We collected data on various facto rs that may influence the mechanisms of soil water erosion events." Our news reporters obtained a quote from the research from University of Cadi Ay yad: "Subsequently, we developed machine learning models to predict the potentia l for soil water erosion based on these factors. Finally, field studies were con ducted compared to the obtained results. A historical inventory of water erosion has been created through fieldwork, satellite imagery, and historical water ero sion events. Models were constructed using the training data, and their performa nce and accuracy in predicting susceptibility to water erosion were evaluated us ing the validation data. This data division allowed for a fair assessment of the models' ability to make accurate predictions. Using a Geographic Information Sy stem (GIS) and programming in the R language, four supervised machine learning a lgorithms were applied, including K-Nearest Neighbor (KNN), Extreme Gradient Boo sting (XGB), Random Forest (RF), and Naive Bayes (NB). The results show that the NB model exhibited the highest accuracy in predicting and evaluating the effect iveness of these algorithms in forecasting susceptibility to water erosion in th e study area. Accuracy was assessed using the Area Under the Curve (AUC) metric, with an AUC of 98%. The XGB algorithm had an AUC of 96% , followed by RF with an AUC of 87%, and KNN with an AUC of 84% . Thus, the Naive Bayes model proved to be the best for determining susceptibili ty to water erosion in the study area. The analysis of water erosion reveals tha t 43% of the total area of the Oued Ourika watershed is exposed to a high to very high risk of erosion in the Ourika region. These findings can as sist regional and local authorities in reducing the risk of water erosion and im plementing effective measures to prevent potential damages."
University of Cadi AyyadMarrakechMor occoAfricaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
