Susceptibility assessment of Landslide Disasters in Yunnan-Guizhou-Sichuan Region Based on GIS and RS
DOI:
https://doi.org/10.54097/zxfqy853Keywords:
Evaluation of susceptibility to landslide disasters Analytic Hierarchy Process Information volume model GIS, RSAbstract
This paper takes landslides in the Yunnan-Guizhou-Sichuan region as the research object. Based on grid and slope units respectively, the analytic Hierarchy Process (AHP) and information model are used to evaluate the susceptibility of landslides. The results show that all four evaluation results pass the rationality and accuracy tests, and the accuracy of the raster cell information volume model is the best. The study area as a whole is mainly composed of low-susceptibility zones, with a relatively small proportion of high-susceptibility zones. Spatially, it is generally lower in the west and higher in the east, concentrated in the middle. The spatial differentiation of susceptibility among Yunnan, Guizhou and Sichuan provinces is significant. In Yunnan, the susceptibility increases from south to north. In Guizhou, it is higher in the south and lower in the north. In Sichuan, it is higher in the west and lower in the east. In addition, by adopting the integrated comprehensive evaluation of multiple classifiers and standardizing the superimposed classification of the results of a single model, the evaluation accuracy has been significantly improved.
Downloads
References
[1] Guo G B, Tian T, Zhou Z G, Wang Z W, Li S. Landslide susceptibility assessment of Cangyuan County based on multiple machine learning algorithms [J]. Geospatial Information, 2026, 24(02): 64-67+73.
[2] Hong H Y, Wang D S, Zhu A X. Training sample sampling method for machine learning-based regional landslide susceptibility assessment [J]. Acta Geographica Sinica, 2024, 79(07): 1718-1736.
[3] Chen X Y, Shi Y, Zhao K, et al. Landslide susceptibility assessment based on CF combined with SSA-optimized SVM and RF models [C]//Journal of Xi'an University of Technology, 2024, 40: 121-131+142.
[4] Ai X Y, He P, Liang Y R, Wang S F, Han J H, Meng X Z, Zhong L, You Y, Fu C Y. IV-SVM-based landslide susceptibility prediction model along gathering pipelines in Yan'an gas field [J/OL]. Unconventional Oil and Gas, 2025, 12(01): 123-133.
[5] Cui Y L, Zhu L L, Xu M, et al. Negative sample selection by TSES method optimized with environmental factors and its application in landslide susceptibility assessment [C]//Bulletin of Geological Science and Technology, 2024, 43: 192-199.
[6] Chen H, Ji S J, Liu M, Zhang H Y, Tu K. Landslide susceptibility assessment of Badong-Zigui section in the Three Gorges Reservoir area based on InSAR and TabPFN model [J/OL]. China Earthquake Engineering Journal, 2026, 48(02): 251-264+296.
[7] Deng N D, Cui Y Y, Guo Y J. Landslide susceptibility assessment based on frequency ratio-random forest model [J]. Science Technology and Engineering, 2020, 20(34): 13990-13996.
[8] Chen B, Zhang C C, Li Z H, et al. Development characteristics and controlling factors of landslides induced by the '6·16' 2024 extreme rainstorm in Longyan, Fujian [C]//Journal of Wuhan University (Information Science Edition), 2024: 1-13.
[9] Fan Q, Ju N P, Xiang X Q, Huang J. Application of weight of evidence method in landslide susceptibility zoning: A case study of Tongzi River basin, Guizhou [J]. Journal of Catastrophology, 2015, 30(01): 124-129.
[10] Tan Y M, Guo D, Bai B X, et al. Geological hazard susceptibility assessment of Fuling district based on information value model [J]. Journal of Geo-Information Science, 2015, 17(12): 1554-1562.
[11] Cai S, Cheng X F. Comparative analysis of landslide susceptibility assessment using different models in Dabie mountain area, Anhui [C]//Journal of Anhui Normal University (Natural Science), 2024, 47: 152-160.
[12] Chen Y B, Xu S G, Chen M R. Comparative analysis of landslide susceptibility assessment models based on certainty factor method: A case study of surrounding areas of Baoshan basin, Yunnan [C]//The Chinese Journal of Geological Hazard and Control, 2024: 1-12.
[13] Gao H, Xia M Y, Wei T. Seismic landslide susceptibility assessment method based on Newmark method and random forest model [J/OL]. China Earthquake Engineering Journal, 2026, 48(02): 334-346.
[14] Chen Y P. Comprehensive evaluation of GIS-based landslide susceptibility in Guizhou using multiple models [J], 2010(02).
[15] Bai Q Y. Landslide stability analysis and optimization design of reinforcement engineering based on Monte Carlo method [J], 2018(01).
[16] Dai X A, Yao Y, Chen L, et al. Landslide susceptibility assessment model optimized by heterogeneous ensemble learning: A case study of Luding county [J]. Journal of Chengdu University of Technology (Natural Science Edition), 2024: 1-16.
[17] Deng R L, Zheng X C. Research on regional landslide early warning model based on susceptibility and critical rainfall threshold [D/OL]. Guangzhou University, 2023.
[18] He P, Tong L Q, Guo Z C, Liu C L, Tu J N, Wang S S, Xu J M. GIS-supported landslide susceptibility assessment in Zanda area, Xizang based on analytic hierarchy process [J]. Science Technology and Engineering, 2016, 16(25): 193-200.
[19] Chen H W, Sun Z X. Research on geological hazard susceptibility assessment based on improved information value model [D/OL]. East China University of Technology, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Applied Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
