Landslide Susceptibility Assessment in Jinning District, Kunming City, Yunnan Province Based on Multi-Model Comparison
DOI:
https://doi.org/10.54097/hd5fz844Keywords:
Landslide Susceptibility, Support Vector Machine, XGBoost, Decision Tree, Convolutional Neural Network, Random Forest, Geological DisasterAbstract
Landslides occur frequently in Jinning District of Kunming City, Yunnan Province, where complex geological conditions make susceptibility assessment a challenging task. In this study, 13 evaluation factors were selected and five machine learning models—Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB), Decision Tree (DT), Convolutional Neural Network (CNN), and Random Forest (RF)—were applied to map landslide susceptibility. Pearson correlation coefficients were calculated to examine the relationships among factors, and model performance was compared using AUC, Accuracy, Precision, Recall, F1-Score, and MCC. The susceptibility maps were then divided into five classes so that the area and landslide proportions of each zone could be compared. Among the five models, XGB achieved the best overall performance, with an AUC of 0.9106 and an MCC of 0.6059. Its very high susceptibility zone covers 13.07% of the study area yet contains 52.33% of the recorded landslides, a concentration that no other model matched. Elevation, slope, and distance to rivers were positively correlated with susceptibility and can be regarded as the dominant controlling factors. These findings offer a scientific reference for landslide risk management in Jinning District and confirm that machine learning models are effective for geological disaster susceptibility assessment.
Downloads
References
[1] Calvello, M., & Pecoraro, G. (2018). FraneItalia: A catalog of recent Italian landslides. Geoenvironmental Disasters, 5(1), 13. https://doi.org/10.1186/s40677-018-0105-5. DOI: https://doi.org/10.1186/s40677-018-0105-5
[2] Haque, U., Blum, P., da Silva, P., Andersen, P., Pilz, J., Chalov, S., Malet, J., Auflič, M., Andres, N., Poyiadji, E., Lamas, P., Zhang, W., Peshevski, I., & Pétursson, H. (2016). Fatal landslides in Europe. Landslides, 13(6), 1545–1554. https://doi.org/10.1007/s10346-016-0689-3. DOI: https://doi.org/10.1007/s10346-016-0689-3
[3] Huang, W., Ding, M., Li, Z., Zhuang, J., Yang, J., Li, X., Meng, L., Zhang, H., & Dong, Y. (2022). An efficient user friendly integration tool for landslide susceptibility mapping based on support vector machines: SVM LSM toolbox. Remote Sensing, 14(14), 3408. https://doi.org/10.3390/rs14143408. DOI: https://doi.org/10.3390/rs14143408
[4] Zhang, J., Qian, J., Lu, Y., Li, X., & Song, Z. (2024). Study on landslide susceptibility based on multi model coupling: A case study of Sichuan Province, China. Sustainability, 16(16), 6803. https://doi.org/10.3390/su16166803. DOI: https://doi.org/10.3390/su16166803
[5] Kim, J. C., Lee, S., Jung, H. S., & Lee, S. (2018). Landslide susceptibility mapping using random forest and boosted tree models in Pyeong Chang, Korea. Geocarto International, 33(9), 1000–1015. https://doi.org/10.1080/10106049.2017.1323964. DOI: https://doi.org/10.1080/10106049.2017.1323964
[6] Meng, S., Shi, Z., Li, G., Peng, M., Liu, L., Zheng, H., & Zhou, C. (2024). A novel deep learning framework for landslide susceptibility assessment using improved deep belief networks with the intelligent optimization algorithm. Computers and Geotechnics, 167, 106106. https://doi.org/10.1016/j.compgeo.2024.106106. DOI: https://doi.org/10.1016/j.compgeo.2024.106106
[7] Pourghasemi, H. R., Pradhan, B., & Gokceoglu, C. (2012). Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed, Iran. Natural Hazards, 63(3), 965–996. https://doi.org/10.1007/s11069-012-0217-2. DOI: https://doi.org/10.1007/s11069-012-0217-2
[8] Ercanoglu, M., Gokceoglu, C., & Van Asch, W. J. (2004). Landslide susceptibility zoning of North of Yenice (NW Turkey) by multivariate statistical techniques. Natural Hazards, 32(1), 1–23. https://doi.org/10.1023/B:NHAZ.0000026786.85589.4a. DOI: https://doi.org/10.1023/B:NHAZ.0000026786.85589.4a
[9] Tsangaratos, P., & Benardos, A. (2014). Estimating landslide susceptibility through an artificial neural network classifier. Natural Hazards, 74(3), 1489–1516. https://doi.org/10.1007/s11069-014-1259-z. DOI: https://doi.org/10.1007/s11069-014-1245-x
[10] Huang, F., Chen, J., Liu, W., Huang, J., Hong, H., & Chen, W. (2022). Regional rainfall induced landslide hazard warning based on landslide susceptibility mapping and a critical rainfall threshold. Geomorphology, 408, 108236. https://doi.org/10.1016/j.geomorph.2022.108236. DOI: https://doi.org/10.1016/j.geomorph.2022.108236
[11] Shu, Y., Zheng, G., & Yan, X. (2022). Application of multiple geographical units convolutional neural network based on neighborhood effects in urban waterlogging risk assessment in the city of Guangzhou, China. Physics and Chemistry of the Earth, 126, 103054. https://doi.org/10.1016/j.pce.2022.103054. DOI: https://doi.org/10.1016/j.pce.2021.103054
[12] Rohan, T., Shelef, E., Mirus, B., & Coleman, T. (2023). Prolonged influence of urbanization on landslide susceptibility. Landslides, 20(7), 1433–1447. https://doi.org/10.1007/s10346-023-02050-6. DOI: https://doi.org/10.1007/s10346-023-02050-6
[13] Xiong, H., Ma, C., Li, M., Tan, J., & Wang, Y. (2023). Landslide susceptibility prediction considering land use change and human activity: A case study under rapid urban expansion and afforestation in China. Science of The Total Environment, 866, 161430. https://doi.org/10.1016/j.scitotenv.2023.161430. DOI: https://doi.org/10.1016/j.scitotenv.2023.161430
[14] Wang, X., Nie, W., Xie, W., & Zhang, Y. (2024). Incremental learning random forest model based landslide susceptibility analysis: A case of Ganzhou City, China. Earth Science Informatics, 17(2), 1645–1661. https://doi.org/10.1007/s12145-024-01267-1. DOI: https://doi.org/10.1007/s12145-024-01229-2
[15] Nandi, A., Mandal, A., Wilson, M., & Smith, D. (2016). Flood hazard mapping in Jamaica using principal component analysis and logistic regression. Environmental Earth Sciences, 75(6), 465. https://doi.org/10.1007/s12042-016-2262-3. DOI: https://doi.org/10.1007/s12665-016-5323-0
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
