Quantifying the Relative Importance of Factors Controlling Soil Erosion in the Mountainous Region of Nghe An Province, Vietnam
Main Article Content
Abstract
Soil erosion is one of the geomorphological - environmental processes that strongly affect ecosystems and sustainable development in mountainous regions. This study applies a machine learning model (XGBoost) in combination with the Shapley Additive Explanations (SHAP) method to evaluate the relative importance (weights) of natural and anthropogenic factors influencing soil erosion in the mountainous areas of Nghe An Province. The results reveal that Land Cover (0.12) and Geological conditions (0.10) are the most important factors, followed by Slope and Elevation (0.06), and Rainfall and Aspect (0.05). Other factors, such as distance to faults, NDVI, and curvature, show relatively lower impacts (0.02 - 0.03). These findings highlight the dominant roles of surface cover and geological conditions in controlling soil erosion risk, while also demonstrating the potential of SHAP for explaining predictive models of soil erosion hazard.
Keywords
Soil erosion, XGBoost, SHAP, Machine learning, Mountainous Nghe An
Article Details
References
Geological influence factors of soil erosion in Changting County, Fujian Province and the countermeasures to prevent and control. Hydrogeology & Engineering Geology, 47(6), 26-35.
Liu, M., Zhang, Q., Ge, S., Mason, R. P., Luo, Y., He, Y., Xie, H., Sa, R., Chen, L., & Wang, X. (2019). Rapid increase in the lateral transport of trace elements induced by soil erosion in major karst regions in China. Environmental Science & Technology, 53(8), 4206-4214. https://doi.org/10.1021/acs.est.8b06143
Lundberg, S. M., & Lee, S.I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (pp. 4765-4774). Curran Associates, Inc.
Morgan, R. P. C. (2009). Soil erosion and conservation. John Wiley & Sons.
Nguyen, C. Q., Tran, T. T., Nguyen, T. T. T., Nguyen, T. H. T., Astarkhanova, T. S., Van Vu, L., Dau, K. T., Nguyen, H. N., Pham, G. H., Nguyen, D. D., Prakash, I., & Pham, B. (2024). Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam. Journal of Hydroinformatics, 26(1), 72-87.
Nguyen, T. T. H., Tran, T. T., Sarzhanovna, A. T., Thuy, H. T., Luong, V. V., Du, T. D., Tai, D. K., The, H. A., Thanh, N. N., Duong, P. T., Ha, V. T. T., & Khanh, V. T. N. (2023). Potential risks of soil erosion in North-Central Vietnam using remote sensing and GIS. Revista Brasileira de Engenharia Agrícola e Ambiental, 27(11), 910-916. https://doi.org/10.1590/1807-1929/agriambi.v27n11p910-916
Nguyễn Văn Khiết. (2014). Nghiên cứu xác định vai trò của một số yếu tố liên quan đến xói mòn đất ở nước ta. Tạp chí Khoa học Lâm nghiệp, (1), 3145-3153.
Nohara, Y., Matsumoto, K., Soejima, H., & Nakashima, N. (2019). Explanation of machine learning models using improved Shapley additive explanation. In Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (p. 546). Association for Computing Machinery.
Pham, G. H., Pham, B. T. T., Hoang, K. O. T., Tran, T. T., & Hoang Nguyen Duc Chi. (2026). GIS based soil erosion susceptibility assessment using deep learning models: A case study in the mountainous region of Nghe An, Vietnam. Journal of Science and Transport Technology, 6(1), 67-86.
Pimentel, D. (2006). Soil erosion: A food and environmental threat. Environment, Development and Sustainability, 8(1), 119-137.
Ranzi, R., Le, T. H., & Rulli, M. C. (2012). A RUSLE approach to model suspended sediment load in the Lo River (Vietnam): Effects of reservoirs and land use changes. Journal of Hydrology, 422-423, 17-29.
Wischmeier, W. H., & Smith, D. D. (1978). Predicting rainfall erosion losses: A guide to conservation planning (Agriculture Handbook No. 537). U.S. Department of Agriculture, Science and Education Administration.