Rainfall⁃Induced Landslide Susceptibility Assessment Based on Collaborative Sample Optimization Using Multi⁃Source Remote Sensing Interpretation and Physical Model Simulation

Luo Jing; Song Chen; Pei Xiangjun; Yan Rui; Liu Ziqiang; Li Guobing; Wu Jingang; Liu Hongyang

doi:10.3799/dqkx.2026.271

您当前的位置：

首页 >

文章列表页 >

Rainfall⁃Induced Landslide Susceptibility Assessment Based on Collaborative Sample Optimization Using Multi⁃Source Remote Sensing Interpretation and Physical Model Simulation

更新时间：2026-10-15

- Rainfall⁃Induced Landslide Susceptibility Assessment Based on Collaborative Sample Optimization Using Multi⁃Source Remote Sensing Interpretation and Physical Model Simulation
- Earth Science Vol. 51, Issue 9, Pages: 3469-3483(2026)
- 作者机构：
  
  1.成都理工大学地质灾害防治与地质环境保护全国重点实验室，四川成都 610059
  2.天府永兴实验室，四川成都 610213
  3.北京市市政工程设计研究总院有限公司，北京 100089
- 作者简介：
- 基金信息：
- DOI：10.3799/dqkx.2026.271
  CLC： P642.22
- Received：21 April 2026，
  
  Published：30 September 2026
- 稿件说明：
移动端阅览
罗璟，宋琛，裴向军，严睿，刘自强，李郭兵，吴金刚，刘洪洋，2026.多源遥感解译与物理模型反演协同优化样本的降雨滑坡易发性评价方法.地球科学，51（9）：3469-3483.

Luo Jing，Song Chen，Pei Xiangjun，Yan Rui，Liu Ziqiang，Li Guobing，Wu Jingang，Liu Hongyang，2026.Rainfall⁃Induced Landslide Susceptibility Assessment Based on Collaborative Sample Optimization Using Multi⁃Source Remote Sensing Interpretation and Physical Model Simulation.Earth Science，51（9）：3469-3483.
罗璟，宋琛，裴向军，严睿，刘自强，李郭兵，吴金刚，刘洪洋，2026.多源遥感解译与物理模型反演协同优化样本的降雨滑坡易发性评价方法.地球科学，51（9）：3469-3483. DOI： 10.3799/dqkx.2026.271.

Luo Jing，Song Chen，Pei Xiangjun，Yan Rui，Liu Ziqiang，Li Guobing，Wu Jingang，Liu Hongyang，2026.Rainfall⁃Induced Landslide Susceptibility Assessment Based on Collaborative Sample Optimization Using Multi⁃Source Remote Sensing Interpretation and Physical Model Simulation.Earth Science，51（9）：3469-3483. DOI： 10.3799/dqkx.2026.271.

摘要

全球气候变化背景下，极端降雨事件频发，山区降雨滑坡风险不断加剧，准确开展滑坡易发性评价尤为重要，而样本质量是影响机器学习评价可靠性的关键因素.本文以涞宝高速沿线受北京“23·7”极端降雨影响较为严重的路段为研究区，利用DInSAR、NDVI和光学遥感影像开展地质灾害解译；采用TRIGRS-Scoops3D模型分析降雨入渗条件下的斜坡稳定性，并据此优化负样本筛选；进一步构建逻辑回归（LR）、随机森林（RF）、支持向量机（SVM）和XGBoost易发性评价模型，结合ROC曲线及相关性能指标综合评估模型预测能力，并结合SHAP方法解析各评价因子的贡献.结果表明：北京“23·7”极端降雨事件在研究区共诱发地质灾害466处，其中滑坡345处，主要分布于地形起伏较大、沟谷切割明显的山地斜坡；TRIGRS-Scoops3D模型对潜在失稳区具有较好的识别能力，其不稳定区内滑坡点占比为90.43%，%

class

为80.09%，较TRIGRS模型分别提高15.36%和9.43%；基于物理模型优化负样本后，XGBoost模型综合性能最优，AUC为0.956；SVM和RF模型次之，AUC分别为0.906和0.899；LR模型相对较低，AUC为0.861；SHAP分析进一步表明，坡度和降雨是控制研究区降雨滑坡易发性的主控因素.研究结果可为复杂山区降雨滑坡易发性评价及山区交通工程地质灾害防控提供参考.

Abstract

Against the background of global climate change

increasingly frequent extreme rainfall events have intensified the risk of rainfall-induced landslides in mountainous regions

highlighting the importance of accurate landslide susceptibility assessment. The quality of training samples

particularly negative sample selection

is a key factor affecting the reliability of machine learning-based susceptibility models. This study focuses on a section of the Laibao Expressway severely affected by the Beijing “23·7

” extreme rainfall event. DInSAR

NDVI

and optical remote sensing imagery were integrated to identify geological hazards. The coupled TRIGRS-Scoops3D model was then used to evaluate slope stability under rainfall infiltration conditions

and the results were used to optimize negative sample selection. Logistic regression (LR)

random forest (RF)

support vector machine (SVM)

and XGBoost models were further developed for landslide susceptibility assessment. Their predictive performance was evaluated using receiver operating characteristic (ROC) curves and related performance metrics

while SHAP analysis was used to quantify the contributions of conditioning factors. The results show that the Beijing “23·7” extreme rainfall event triggered 466 geological hazards

including 345 landslides

mainly distributed on mountainous slopes with pronounced topographic relief and strong valley incision. The TRIGRS-Scoops3D model showed capability in identifying potentially unstable areas

with 90.43% of the observed landslides falling within unstable zones and a %

class

value of 80.09%

representing improvements of 15.36% and 9.43%

respectively

over the TRIGRS model. After negative sample selection was optimized using the physics-based model

XGBoost achieved the best performance

with an AUC of 0.956

followed by SVM and RF with AUC values of 0.906 and 0.899

respectively

while LR yielded a relatively lower AUC of 0.861. SHAP analysis further indicated that slope gradient and rainfall were the dominant factors controlling rainfall-induced landslide susceptibility in the study area. The findings provide a useful reference for landslide susceptibility assessment in complex mountainous regions and for geological hazard prevention and mitigation along mountainous transportation corridors.

关键词

Keywords

references

Alvioli, M., Spiga, D., Baum, L.R., 2016. Evaluation of the Parallel Performance of the TRIGRS v2.1 Model for Rainfall⁃Induced Landslides. PeerJ PrePrints , 4e2206. https://peerj.com/preprints/2206v2/

Bai, S. B., Lü, G. N., Sheng, Y. H., et al., 2005. Analysis of Landslide Causative Factors Using GIS in the Three Gorges Reservoir Area, China. Journal of Mountain Research , 23 ( 1 ): 63 - 70 (in Chinese with English abstract) .

Berardino, P., Fornaro, G., Lanari, R., et al., 2002. A New Algorithm for Surface Deformation Monitoring Based on Small Baseline Differential SAR Interferograms. IEEE Transactions on Geoscience and Remote Sensing , 40 ( 11 ): 2375 - 2383 . https://doi.org/10.1109/TGRS.2002.803792

Breiman, L., 2001. Random Forests. Machine Learning , 45 ( 1 ): 5 - 32 . https://doi.org/10.1023/A:1010933404324

Bui, D. T., Tsangaratos, P., Nguyen, V. T., et al., 2020. Comparing the Prediction Performance of a Deep Learning Neural Network Model with Conventional Machine Learning Models in Landslide Susceptibility Assessment. CATENA , 188 : 104426. https://doi.org/10.1016/j.catena.2019.104426

Chang, J. Y., Bao, H., Wu, F. Q., et al., 2015. Discussion on Stability of Shallow Landslide under Rainfall. Rock and Soil Mechanics , 36 ( 4 ): 995 - 1001 (in Chinese with English abstract) .

Chang, M., Xu, Q., Wang, Y. S., et al., 2024. Development Characteristics and Disaster⁃Causing Mechanisms of the “8·3” Catastrophic Flash Flood and Debris Flow in Guzan, Kangding, Sichuan Province. Geomatics and Information Science of Wuhan University , 49 ( 11 ): 2136 - 2144 (in Chinese with English abstract) .

Chen, T. Q., Guestrin, C., 2016. XGBoost: A Scalable Tree Boosting System. The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco. https://doi.org/10.1145/2939672.2939785

Cortes, C., Vapnik, V., 1995. Support⁃Vector Networks. Machine Learning , 20 ( 3 ): 273 - 297 . https://doi.org/10.1007/BF00994018

Dong, X. J., Xu, Q., She, J. X., et al., 2020. Preliminary Study on Interpretation of Geological Hazards in Jiuzhaigou Based on Multi⁃Source Remote Sensing Data. Geomatics and Information Science of Wuhan University , 45 ( 3 ): 432 - 441 (in Chinese with English abstract) .

Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., et al., 2019. Evaluation of Different Machine Learning Methods and Deep⁃Learning Convolutional Neural Networks for Landslide Detection. Remote Sensing , 11 (2): 196. https://doi.org/10.3390/rs11020196

He, J. Y., 2021. Stability Analysis of Rainfall⁃Induced Shallow Landslide: Based on TRIGRS Model and Scoops3D Model (Dissertation). Northwest University, Xi’an (in Chinese with English abstract) .

Hosmer, D. W., Lemeshow, S., Sturdivant, R. X., 2013. Applied Logistic Regression (3rd Edition). Wiley, Hoboken. https://doi.org/10.1002/9781118548387

Huang, F. M., Xiong, H. W., Jiang, S. H., et al., 2024. Modelling Landslide Susceptibility Prediction: A Review and Construction of Semi⁃Supervised Imbalanced Theory. Earth⁃Science Reviews , 250 : 104700. https://doi.org/10.1016/j.earscirev.2024.104700

Huang, R. Q., Qi, G. Q., 2002. The Effect of Unsaturated Soil Suction on Slope Stability. Journal of Engineering Geology , 10 ( 4 ): 343 - 348 (in Chinese with English abstract) .

Huang, R. Q., Xu, Q., Qi, G. Q., 2007. Evaluation and Prediction of Rainfall and Reservoir⁃Induced Landslides. Science Press, Beijing (in Chinese) .

Jia, Z., Cheng, Z. J., Chang, Z. L., et al., 2026. Non⁃ Landslide Sample for Landslide Susceptibility Prediction Modeling: A Review of Selection Strategies and Their Influence Rules. Journal of Rock Mechanics and Geotechnical Engineering , 18 ( 4 ): 2859 - 2880 . https://doi.org/10.1016/j.jrmge.2025.12.011

Li, H. Q., Sun, H. Y., Sun, X. M., et al., 2009. Influence of Rainfall Infiltration on Slopes by Physical Model Test. Chinese Journal of Geotechnical Engineering , 31 ( 4 ): 589 - 594 (in Chinese with English abstract) .

Liao, M. S., 2014. Principles and Applications of InSAR. Beijing: Science Press (in Chinese) .

Liu, L. L., Duan, C., Xu, C., et al., 2026. A Physically⁃ Informed Negative Sampling Strategy for Earthquake⁃ Induced Landslide Susceptibility Assessment. Earth Science , Online (in Chinese with English abstract) . https://link.cnki.net/urlid/42.1874.P.20260323.1513.002

Liu, S. W., Guo, D. H., Chen, W. T., et al., 2012. The Application of Airborne Lidar Technology in Landslide Investigation and Monitoring of Three Gorges Reservoir Area. Geology in China , 39 ( 2 ): 507 - 517 (in Chinese with English abstract) .

Ma, H. C., 2011. Review on Applications of LiDAR Mapping Technology to Geosciences. Earth Science , 36 ( 2 ): 347 - 354 (in Chinese with English abstract) .

Merghadi, A., Yunus, A. P., Dou, J., et al., 2020. Machine Learning Methods for Landslide Susceptibility Studies: A Comparative Overview of Algorithm Performance. Earth⁃Science Reviews , 207 : 103225. https://doi.org/1 0.1016/j.earscirev.2020.103225

Muntohar, A. S., Liao, H. J., 2010. Rainfall Infiltration: Infinite Slope Model for Landslides Triggering by Rainstorm. Natural Hazards , 54 ( 3 ): 967 - 984 . https://doi.org/10.1007/s11069⁃010⁃9518⁃5

Nan, Y., Zhai, S. H., Li, Y., et al., 2024. Analysis on the Characteristics of Geological Disasters and Effectiveness of Early Warning Duiring Heavy Rainfall on “23·7” in Beijing. The Chinese Journal of Geological Hazard and Control , 35 ( 2 ): 66 - 73 (in Chinese with English abstract) .

Nichol, J. E., Shaker, A., Wong, M. S., 2006. Application of High⁃Resolution Stereo Satellite Images to Detailed Landslide Hazard Assessment. Geomorphology , 76(1-2): 68-75. https://doi.org/10.1016/j.geomorph.2005.10.001

Qian, J. Y., Zhang, G., Zhang, J. M., et al., 2009. Centrifuge Model Tests of Cohesive Soil Slopes during Rainfall. Journal of Tsinghua University ( Science and Technology ), 49 ( 6 ): 829 - 833 (in Chinese with English abstract) .

Tian, Y., Gao, B., Yin, H., et al., 2024. Handling Imbalanced Samples in Landslide Susceptibility Evaluation. Hydrogeology & Engineering Geology , 51 ( 6 ): 171 - 181 (in Chinese with English abstract) .

Tralli, D. M., Blom, R. G., Zlotnicki, V., et al., 2005. Satellite Remote Sensing of Earthquake, Volcano, Flood, Landslide and Coastal Inundation Hazards. ISPRS Journal of Photogrammetry and Remote Sensing , 59 ( 4 ): 185 - 198 . https://doi.org/10.1016/j.isprsjprs.2005.02.002

Wu, B., Shi, Z. M., Zheng, H. C., et al., 2024. Impact of Sampling for Landslide Susceptibility Assessment Using Interpretable Machine Learning Models. Bulletin of Engineering Geology and the Environment , 83 (11): 461. https://doi.org/10.1007/s10064⁃024⁃03980⁃8

Xin, X., Zhang, F. Y., 2018. Application of a 3D Deterministic Model for Predicting Shallow Loess Landslide Stability. Chinese Journal of Engineering , 40 ( 4 ): 397 - 406 (in Chinese with English abstract) .

Zhang, Q. Y., 2023. The Cause and Enlightenment of the “23.7” Extremely Rainstorm Disaster in Fangshan District of Beijing City. China Flood & Drought Management , 33 ( 10 ): 43 - 47 (in Chinese with English abstract) .

Zhang, S., Wang, F. W., 2019. Three⁃Dimensional Seismic Slope Stability Ass essment with the Application of Scoops3D and GIS: A Case Study in Atsuma, Hokkaido. Geoenvironmental Disasters , 6 (1): 9. https://doi.org/10.1186/s40677⁃019⁃0125⁃9

Zhao, C. Y., Lu, Z., 2018. Remote Sensing of Landslides—A Review. Remote Sensing , 10 (2): 279. https://doi.org/10.3390/rs10020279

Zheng, L. J., Li, X. Z., Yao, J., et al., 2023. Dynamic Prediction of Spatiotemporal Stability of Potential Landslides Based on the TRIGRS and Scoops3D Coupling Model. Journal of Natural Disasters , 32 ( 2 ): 199 - 209 (in Chinese with English abstract) .

Zhou, X. T., 2022. Recognition and Dynamic Susceptibility Assessment of Landslides Based on Multi⁃Source Data (Dissertation). East China University of Technology, Nanchang (in Chinese with English abstract) .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Machine Learning Solution for Landslide Susceptibility Based on Hydrographic Division: Case Study of Fengjie County in Chongqing

Interpretable Prediction of Rock Strength: A Study Based on the COA⁃LightGBM⁃SHAP Framework

Modeling and Uncertainty in Landslide Susceptibility Prediction Considering Coupling Mode of Landslide Types

Landslide Susceptibility Mapping Based on AI Technology

An XGBoost⁃Based Onsite PGV Prediction Model

Related Author

He Yuwei

Liu Songlin

Chen Bolin

Zhang Wengang

Wang Luqi

Zhang Yan

Yang Qilai

Luo Jing

Related Institution

School of Civil Engineering， Chongqing University

National Joint Engineering Research Center of Geohazards Prevention in the Reservoir Areas， Chongqing University

Chongqing Institute of Geology and Mineral Resources

Shaanxi Xingtong Supervision and Consulting Co.， Ltd.

School of Infrastructure Engineering， Nanchang University

AI问答

⁰