Global Dynamic Landslide Susceptibility Modeling Based on ResNet18: Revealing Large-Scale Landslide Hazard Evolution Trends in China
Source abstract
Abstract
Large-scale and long-term landslide susceptibility assessments are crucial for revealing the patterns of landslide risk variation and for guiding the formulation of disaster prevention and mitigation policies at the national level. This study, through the establishment of a global dynamic landslide susceptibility model, uses the multi-dimensional analysis strategy and studies the development trend of China’s large-scale landslide susceptibility. First, a global landslide dataset consisting of 8023 large-scale landslide events triggered by rainfall and earthquakes between 2001 and 2020 was constructed based on the GEE (Google Earth Engine) platform. Secondly, a global dynamic landslide susceptibility model was developed using the ResNet18 (18-layer residual neural network) DL (deep learning) framework, incorporating both dynamic and static LCFs (landslide conditioning factors). The model was utilized to generate sequential large-scale landslide susceptibility maps for China from 2001 to 2022. Finally, the MK (Mann–Kendall) test was used to investigate the change trends in the large-scale landslide susceptibility of China. The results of the study are as follows. (1) The ResNet18 model outperformed SVMs (support vector machines) and CNNs (convolutional neural networks), with an AUC value of 0.9362. (2) SHAP (Shapley Additive Explanations) analyses revealed that precipitation played an important factor in the occurrence of landslides in China. In addition, profile curvature, NDVI, and distance to faults are thought to have a significant impact on landslide susceptibility. (3) The large-scale landslide susceptibility trends in China are complex and varied. Particular emphasis should be placed on Southwest China, including Chongqing, Guizhou, and Sichuan, which exhibit high landslide susceptibility and notable upward trends, and also consider Northwest China, including Shaanxi and Shanxi, which have high susceptibility but decreasing trends. These results provide valuable insights for disaster prevention and mitigation in China.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Landslides and related hazards · Fire effects on ecosystems · Tree Root and Stability Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, China
Big Data Center for Geosciences and Satellites, Chang’an University, Xi’an 710054, China
Key Laboratory of Loess, Xi’an 710054, China
Key Laboratory of Western China’s Mineral Resource and Geological Engineering, Ministry of Education, Xi’an 710054, China
Generic Technical Development Platform of Shaanxi Province for Imaging Geodesy, Xi’an 710021, China
School of Land Engineering, Chang’an University, Xi’an 710064, China
School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China
Funding
National Natural Science Foundation of China · Shaanxi Province Geoscience Big Data and Geohazard Prevention Innovation Team (2022) · Opening Fund of Key Laboratory of Smart Earth · Key R&D Program Projects in Zhejiang Province
References (66)
Show source-provided references
1. Global patterns of loss of life from landslides10.1130/G33217.1 ↗
2. Fatal landslides in Europe10.1007/s10346-016-0689-3 ↗
3. Comparison of landslide susceptibility mapping methodologies for Koyulhisar, Turkey: Conditional probability, logistic regression, artificial neural networks, and support vector machine10.1007/s12665-009-0394-9 ↗
4. Yang, X., Liu, R., Yang, M., Chen, J., Liu, T., Yang, Y., Chen, W., and Wang, Y. (2021). Incorporating landslide spatial information and correlated features among conditioning factors for landslide susceptibility mapping. Remote Sens., 13.10.3390/rs13112166 ↗
5. Li, L., and Lan, H. (2023). Bivariate landslide susceptibility analysis: Clarification, optimization, open software, and preliminary comparison. Remote Sens., 15.10.3390/rs15051418 ↗
6. Global fatal landslide occurrence from 2004 to 201610.5194/nhess-18-2161-2018 ↗
7. Landslide hazard spatial analysis and prediction using GIS in the Xiaojiang watershed, Yunnan, China10.1016/j.enggeo.2004.06.009 ↗
8. A modified frequency ratio method for landslide susceptibility assessment10.1007/s10346-016-0771-x ↗
9. Landslide susceptibility mapping and dynamic response along the Sichuan-Tibet transportation corridor using deep learning algorithms10.1016/j.catena.2022.106866 ↗
10. Convolutional neural network (CNN) with metaheuristic optimization algorithms for landslide susceptibility mapping in Icheon, South Korea10.1016/j.jenvman.2021.114367 ↗
11. Comparative analysis of five convolutional neural networks for landslide susceptibility assessment10.1007/s10064-023-03408-9 ↗
12. Enhancing landslide susceptibility mapping incorporating landslide typology via stacking ensemble machine learning in Three Gorges Reservoir, China10.1016/j.gsf.2024.101802 ↗
13. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
14. Global connections between El Nino and landslide impacts10.1038/s41467-021-22398-4 ↗
15. Evaluation of potential changes in landslide susceptibility and landslide occurrence frequency in China under climate change10.1016/j.scitotenv.2022.158049 ↗
16. Research on geological and surfacial processes and major disaster effects in the Yellow River Basin10.1007/s11430-021-9830-8 ↗
17. Analytical ‘decisiveness’ as a robust measure of the absolute importance of landslide predisposing factors10.1080/17538947.2024.2356161 ↗
18. A dynamic landslide hazard assessment system for Central America and Hispaniola10.5194/nhess-15-2257-2015 ↗
19. Lee, J.-J., Song, M.-S., Yun, H.-S., and Yum, S.-G. (2022). Dynamic landslide susceptibility analysis that combines rainfall period, accumulated rainfall, and geospatial information. Sci. Rep., 12.10.1038/s41598-022-21795-z ↗
20. A quick method of early landslide identification based on dynamic susceptibility analysis using M-SVM method: A case study10.1007/s10064-023-03440-9 ↗
21. Landslide susceptibility assessment method considering land use dynamic change
22. Deep learning forecast of rainfall-induced shallow landslides10.1038/s41467-023-38135-y ↗
23. Hydro-meteorological landslide triggering thresholds based on artificial neural networks using observed precipitation and ERA5-Land soil moisture10.1007/s10346-023-02132-5 ↗
24. Regional-scale spatiotemporal landslide probability assessment through machine learning and potential applications for operational warning systems: A case study in Kvam (Norway)10.1007/s10346-024-02287-9 ↗
25. Li, B., Liu, K., Wang, M., He, Q., Jiang, Z., Zhu, W., and Qiao, N. (2022). Global dynamic rainfall-induced landslide susceptibility mapping using machine learning. Remote Sens., 14.10.3390/rs14225795 ↗
26. Dynamic rainfall-induced landslide susceptibility: A step towards a unified forecasting system
27. Susceptibility evaluation and mapping of China’s landslides based on multi-source data10.1007/s11069-013-0759-y ↗
28. A heuristic approach to global landslide susceptibility mapping10.1007/s11069-017-2757-y ↗
29. Large-scale assessment of landslide hazard, vulnerability and risk in China10.1080/19475705.2018.1502690 ↗
30. National-scale data-driven rainfall induced landslide susceptibility mapping for China by accounting for incomplete landslide data10.1016/j.gsf.2021.101248 ↗
31. Assessment of landslide susceptibility and risk factors in China10.1007/s11069-021-04812-8 ↗
32. Juang, C.S., Stanley, T.A., and Kirschbaum, D.B. (2019). Using citizen science to expand the global map of landslides: Introducing the Cooperative Open Online Landslide Repository (COOLR). PLoS ONE, 14.10.1371/journal.pone.0218657 ↗
33. Spatial and temporal analysis of a global landslide catalog10.1016/j.geomorph.2015.03.016 ↗
34. A global landslide catalog for hazard applications: Method, results, and limitations10.1007/s11069-009-9401-4 ↗
35. Assessing the importance of conditioning factor selection in landslide susceptibility for the province of Belluno (region of Veneto, northeastern Italy)10.5194/nhess-22-1395-2022 ↗
36. Ado, M., Amitab, K., Maji, A.K., Jasińska, E., Gono, R., Leonowicz, Z., and Jasiński, M. (2022). Landslide susceptibility mapping using machine learning: A literature survey. Remote Sens., 14.10.3390/rs14133029 ↗
37. Land use and land cover as a conditioning factor in landslide susceptibility: A literature review10.1007/s10346-022-02020-4 ↗
38. Predicting global landslide spatiotemporal distribution: Integrating landslide susceptibility zoning techniques and real-time satellite rainfall estimates10.1016/S1001-6279(08)60022-0 ↗
39. Earth Resources Observation and Science (EROS) Center (2010). Courtesy of the US Geological Survey.
40. The new global lithological map database GLiM: A representation of rock properties at the Earth surface10.1029/2012GC004370 ↗
41. The GEM global active faults database10.1177/8755293020944182 ↗
42. Changes in land cover and shallow landslide activity: A case study in the Spanish Pyrenees10.1016/j.geomorph.2005.07.018 ↗
43. Effect of the normalized difference vegetation index (NDVI) on GIS-enabled bivariate and multivariate statistical models for landslide susceptibility mapping10.1007/s12524-023-01738-5 ↗
44. The influence of land use and land cover change on landslide susceptibility: A case study in Zhushan Town, Xuan’en County (Hubei, China)10.5194/nhess-19-2207-2019 ↗
45. Muñoz Sabater, J. (2019). ERA5-Land Monthly Averaged Data from 1950 to Present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS).
46. Google Earth Engine: Planetary-scale geospatial analysis for everyone10.1016/j.rse.2017.06.031 ↗
47. Wu, W., Zhang, Q., Singh, V.P., Wang, G., Zhao, J., Shen, Z., and Sun, S. (2022). A data-driven model on Google earth engine for landslide susceptibility assessment in the Hengduan Mountains, the Qinghai–Tibetan plateau. Remote Sens., 14.10.3390/rs14184662 ↗
48. Modelling landslide susceptibility prediction: A review and construction of semi-supervised imbalanced theory10.1016/j.earscirev.2024.104700 ↗
49. Investigating the effects of different landslide positioning techniques, landslide partitioning approaches, and presence-absence balances on landslide susceptibility mapping10.1016/j.catena.2019.104364 ↗
50. Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran10.1016/j.gsf.2020.06.013 ↗
51. Yao, J., Qin, S., Qiao, S., Che, W., Chen, Y., Su, G., and Miao, Q. (2020). Assessment of landslide susceptibility combining deep learning with semi-supervised learning in Jiaohe County, Jilin Province, China. Appl. Sci., 10.10.3390/app10165640 ↗
52. Spatial prediction models for shallow landslide hazards: A comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree10.1007/s10346-015-0557-6 ↗
53. Zhang, Y., and Yan, Q. (2022). Landslide susceptibility prediction based on high-trust non-landslide point selection. ISPRS Int. J. Geo-Inf., 11.10.3390/ijgi11070398 ↗
54. Landslide susceptibility modeling applying machine learning methods: A case study from Longju in the Three Gorges Reservoir area, China10.1016/j.cageo.2017.11.019 ↗
55. Luo, X., Lin, F., Zhu, S., Yu, M., Zhang, Z., Meng, L., and Peng, J. (2019). Mine landslide susceptibility assessment using IVM, ANN and SVM models considering the contribution of affecting factors. PLoS ONE, 14.10.1371/journal.pone.0215134 ↗
56. Huang, W., Ding, M., Li, Z., Zhuang, J., Yang, J., Li, X., Meng, L.e., Zhang, H., and Dong, Y. (2022). An efficient user-friendly integration tool for landslide susceptibility mapping based on support vector machines: SVM-LSM toolbox. Remote Sens., 14.10.3390/rs14143408 ↗
57. A generalized deep learning-based method for rapid co-seismic landslide mapping10.1109/JSTARS.2024.3457766 ↗
58. Shapley, L.S. (1953). A value for n-person games. Contributions to the Theory of Games II, Princeton University Press.10.1515/9781400881970-018 ↗
59. A unified approach to interpreting model predictions
60. An explainable AI (XAI) model for landslide susceptibility modeling10.1016/j.asoc.2023.110324 ↗
61. Molnar, C. (2020). Interpretable Machine Learning, Lulu.com.
62. Zhang, H., Loaiciga, H.A., and Sauter, T. (2024). A novel fusion-based methodology for drought forecasting. Remote Sens., 16.10.3390/rs16050828 ↗
63. Nonparametric tests against trend
64. Kendall, M.G. (1948). Rank Correlation Methods, Charles Griffin and Co., Ltd.
65. Spatial and temporal analysis of a fatal landslide inventory in China from 1950 to 201610.1007/s10346-018-1037-6 ↗
66. Spatiotemporal changes of landslide susceptibility in response to rainfall and its future prediction—A case study of Sichuan Province, China10.1016/j.ecoinf.2024.102862 ↗