Geohazard Susceptibility Assessment in Karst Terrain: A Novel Coupling Model Integrating Information Value and XGBoost Machine Learning in Guizhou Province, China
Source abstract
Abstract
In this study, the geological disasters in Guizhou Province serve as the research object, and a systematic susceptibility evaluation is conducted in light of the province’s prominent problems with frequent geological disasters. The current research primarily focuses on the application of a single model, often with deficiencies in factor interpretation. It has not yet systematically integrated the advantages of the traditional information model and multiple machine learning algorithms, nor introduced interpretable methods to analyze the disaster mechanism deeply. In this study, the information value (IV) model is combined with machine learning algorithms—logistic regression (LR), decision tree (DT), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost)—to construct a coupling model to evaluate the susceptibility to geological disasters. Combined with the Bayesian optimization algorithm, the geological disaster susceptibility evaluation model is built. The confusion matrix and receiver operating characteristic (ROC) curve were used to evaluate the model’s accuracy. The Shapley Additive exPlanations (SHAP) method is used to quantify the contribution of each influencing factor, thereby improving the transparency and credibility of the model. The results show that the coupling models, especially the IV-XGB model, achieved the best performance (AUC = 0.9448), which significantly identifies the northern Wujiang River Basin and the central karst core area as high-risk areas and clarifies the disaster-causing mechanism of “terrain–hydrology–human activities” coupling. The SHAP method further identified that NDVI, land use type, and elevation were the predominant controlling factors. This study presents a high-precision and interpretable modeling method for assessing susceptibility to geological disasters, providing a scientific basis for disaster prevention and control in Guizhou Province and similar geological conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Rock Mechanics and Modeling · Landslides and related hazards · Geoscience and Mining Technology
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Guizhou Emergency Management, Guizhou Normal University, Guiyang 550025, China
Funding
Guizhou Provincial Basic Research Program (Natural Science)
References (61)
Show source-provided references
1. Strategic Thinking on the Prevention and Response of Geological Disasters in China
2. Evaluation of Geological Hazard Susceptibility of Baiyin City Based on Multi-temporal InSAR Deformation Measurements
3. Disaster resilience in the geohazard-prone mountainous areas: Evidence from the Hengduan Mountain, southwest China10.1016/j.ijdrr.2025.105331 ↗
4. Guizhou Provincial Department of Natural Resources (2023, March 16). 2023 Geological Disaster Prevention and Control Plan of Guizhou Province. [EB/OL]. 16 March 2023, Available online: https://zrzy.guizhou.gov.cn/wzgb/zwgk/zdlyxxgk/dzkcgl/dzzhfz/202309/t20230921_82465226.html.
5. Analysis of Slope Deformation Characteristics and Stability under Underground Mining in Guizhou Mountainous Areas
6. Landslide Susceptibility Evaluation and Error Correction Based on InSAR and Random Forest
7. Review of Geological Hazard Susceptibility Evaluation Methods
8. Zhang, R., Zhang, D., Shu, B., and Chen, Y. (2025). Predicting the Spatial Distribution of Geological Hazards in Southern Sichuan, China, Using Machine Learning and ArcGIS. Land, 14.10.3390/land14030577 ↗
9. Wang, H., Xu, J., Tan, S., and Zhou, J. (2023). Landslide Susceptibility Evaluation Based on a Coupled Informative—Logistic Regression Model—Shuangbai County as an Example. Sustainability, 15.10.3390/su151612449 ↗
10. Landslide susceptibility evaluation based on BPNN and GIS: A case of Guojiaba in the Three Gorges Reservoir Area10.1080/13658816.2014.992436 ↗
11. Yuan, X., Liu, C., Nie, R., Yang, Z., Li, W., Dai, X., Cheng, J., Zhang, J., Ma, L., and Fu, X. (2022). A Comparative Analysis of Certainty Factor-Based Machine Learning Methods for Collapse and Landslide Susceptibility Mapping in Wenchuan County, China. Remote Sens., 14.10.3390/rs14143259 ↗
12. Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization10.1016/j.gsf.2021.101211 ↗
13. Landslide susceptibility mapping using Naïve Bayes and Bayesian network models in Umyeonsan, Korea10.1080/10106049.2019.1585482 ↗
14. Landslide Susceptibility Evaluation Based on Optimized Random Forest Model
15. Landslide Susceptibility Evaluation Based on CF-Integrated SSA Optimizing SVM and RF Models
16. Landslide Disaster Susceptibility Evaluation Method with Entropy Index Integrated into Support Vector Machine—Taking Shaanxi Province as an Example
17. Risk Assessment of Earthquake-Induced Landslides in Jiuzhaigou Based on Logistic Regression Model
18. Study on the Geological Disaster Susceptibility of National Tropical Rainforest Parks Based on CF, CF-LR and CF-AHP Models: A Case Study of Baoting, Hainan
19. Quantitative analysis method of diabetes blood Raman spectroscopy based on XGBoost
20. He, W., Chen, G., Zhao, J., Lin, Y., Qin, B., Yao, W., and Cao, Q. (2023). Landslide Susceptibility Evaluation of Machine Learning Based on Information Volume and Frequency Ratio: A Case Study of Weixin County, China. Sensors, 23.10.3390/s23052549 ↗
21. Geological hazard susceptibility assessment based on a random forest weighted information model: A case study of Shidian County, Yunnan Province
22. Research on Landslide Disaster Susceptibility Evaluation Models Based on I, SVM, and I-SVM
23. Landslide Susceptibility Evaluation in the Loess Plateau Based on Information Quantity and Convolutional Neural Network
24. Landslides susceptibility mapping based on geographical information system, GuiZhou, south-west China10.1007/s00254-008-1488-5 ↗
25. A subjective and objective integrated weighting method for landslide susceptibility mapping based on GIS10.1007/s12665-011-1148-z ↗
26. Research on the weight correction method in the evaluation of landslide susceptibility of artificial cut slopes—Taking Shadi Town, Ganzhou City as an example
27. Chelgani, S.C., Fatahi, R., Pournazari, A., and Nasiri, H. (2025). Modeling energy consumption indexes of an industrial cement ball mill for sustainable production. Sci. Rep., 15.10.1038/s41598-025-03232-z ↗
28. Coronary Heart Disease Prediction and Its Feature Analysis Model Combining XGBoost and SHAP
29. Temporal and Spatial Distribution Characteristics and Trends of Geological Hazards in Guizhou
30. Population Growth and Ecological Environment in Guizhou
31. Developmental Characteristics and Genesis Analysis of Collapse (Dangerous Rock Mass) Geological Hazards in Wudang District, Guiyang City
32. Altitude Characteristics of Grassland Community Diversity and Soil Physical and Chemical Property Characteristics in Karst Mountains
33. Snoek, J., Larochelle, H., and Adams, R.P. (2011, January 12–15). Practical Bayesian optimization of machine learning algorithms. Proceedings of the 25th International Conference on Neural Information Processing Systems, Granada, Spain.
34. Chen, B. (2023). Research on Fine Risk Assessment Method of Landslide Disasters Based on the Coupling of Information Quantity Model and Machine Learning. [Master’s thesis, East China University of Technology].
35. Evaluation of landslide hazard susceptibility based on GIS and information volume—Taking Wanzhou district in the Three Gorges reservoir area as an example
36. Shao, C. (2021). Risk Assessment of Shallow Soil Landslide Geological Disasters. [Master’s thesis, Guizhou University].
37. Evaluation of landslide susceptibility by multiple adaptive regression spline method
38. A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping10.1016/j.catena.2018.04.003 ↗
39. Pan, W., and Gao, W. (2024, January 24–26). Geological Hazard Susceptibility Prediction Based on Decision Tree Algorithm. Proceedings of the 2024 IEEE 6th Advanced Information Management, Communications, Electronic, and Automation Control Conference (IMCEC), Chongqing, China.10.1109/IMCEC59810.2024.10575466 ↗
40. Zhao, Z., Liu, Z.Y., and Xu, C. (2021). Slope Unit-Based Landslide Susceptibility Mapping Using Certainty Factor, Support Vector Machine, Random Forest, CF-SVM and CF-RF Models. Front. Earth Sci., 9.10.3389/feart.2021.589630 ↗
41. Support-vector networks10.1023/A:1022627411411 ↗
42. Comparisons of heuristic, general statistical and machine learning models for landslide susceptibility prediction and mapping10.1016/j.catena.2020.104580 ↗
43. Assessing and mapping landslide susceptibility using different machine learning methods10.1080/10106049.2020.1837258 ↗
44. Prediction Modeling of Landslide Susceptibility Based on Machine Learning and Identification of Its Main Controlling Factors
45. Does machine learning adequately predict earthquake-induced landslides?10.1016/j.soildyn.2023.107994 ↗
46. Comparative assessment of machine learning models for landslide susceptibility mapping: A focus on validation and accuracy10.1007/s11069-025-07197-0 ↗
47. Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China
48. Extreme Gradient Boosting as a Method for Quantitative Structure-Activity Relationships10.1021/acs.jcim.6b00591 ↗
49. Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township
50. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
51. A machine learning analysis method for landslide susceptibility based on river basin division: A case study of Fengjie County, Chongqing Municipality
52. Lihao, D., Yanhui, L., Junbao, H., and Haining, L. (Hydrogeol. Eng. Geol., 2024). A regional landslide disaster early warning model for Fujian Province based on a convolutional neural network, Hydrogeol. Eng. Geol., in press.
53. Landslide Disaster Susceptibility Evaluation in the Geomorphic Transition Zone of Western Sichuan Based on GIS
54. Lundberg, S.M., and Lee, S.I. (2017, January 4–9). A unified approach to interpreting model predictions. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
55. Investigation of feature contribution to shield tunneling-induced settlement using Shapley Additive Explanations method10.1016/j.jrmge.2022.01.002 ↗
56. Landslide susceptibility assessment based on a hybrid machine learning model
57. The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central Japan10.1016/j.geomorph.2004.06.010 ↗
58. Identification of collapse and landslide disasters and analysis of main controlling factors based on fine DEM—Taking the Jiacha—Langxian section of the Yarlung Zangbo River suture zone as an example
59. Hazard assessment of collapse and landslide geological disasters under different rainfall conditions
60. Landslide susceptibility zoning in Wushan County based on GIS and random forest
61. Machine learning for predicting landslide risk of Rohingya refugee camp infrastructure