Insights from Optimized Non-Landslide Sampling and SHAP Explainability for Landslide Susceptibility Prediction
Source abstract
Abstract
The quality of sampling data critically influences landslide susceptibility prediction accuracy. Current studies commonly use a 1:1 ratio of landslide to non-landslide samples, failing to reflect natural geographical variability. This study develops a region-specific framework by integrating SHAP (SHapley Additive exPlanation) analysis with twelve landslide conditioning factors (LCFs) and three progressive sampling strategies, aiming to create adaptive non-landslide point selection criteria tailored to unique environmental and geological characteristics. The strategies include (1) multi-ratio random sampling (1:1 to 1:200), (2) susceptibility-based sampling adjustments derived from pre-susceptibility analysis, and (3) LCF-based correction using the NDVI threshold identified through SHAP analysis. Results show that LCF-based correction achieved the highest performance, while a 1:5 ratio proved optimal in random sampling, aligning with regional characteristics. This framework demonstrates the importance of region-specific sampling strategies in improving landslide susceptibility prediction.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Landslides and related hazards · Dam Engineering and Safety · Geotechnical Engineering and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Mountain Hazards and Engineering Resilience, Chengdu 610299, China
Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610299, China
University of Chinese Academy of Sciences, Beijing 101408, China
Funding
Science and Technology Research Program of the Institute of Mountain Hazards and Environment, Chinese Academy of Sciences
References (60)
Show source-provided references
1. Landslide Inventory Maps: New Tools for an Old Problem10.1016/j.earscirev.2012.02.001 ↗
2. Global Fatal Landslide Occurrence from 2004 to 201610.5194/nhess-18-2161-2018 ↗
3. Landslide Types and Processes
4. 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 ↗
5. The San Mateo County California GIS Project for Predicting the Consequences of Hazardous Geologic Processes
6. Recommendations for the Quantitative Analysis of Landslide Risk
7. A Prediction Model of Landslips10.1016/0341-8162(76)90011-4 ↗
8. Landslide Hazard Assessment: Summary Review and New Perspectives10.1007/s100640050066 ↗
9. Sim, A., Ong, D., and Bachat, J. (2016, January 30). Geomorphological Approach for Assessment of Slope Stability and Landslide Hazard Mapping. Proceedings of the 19th Southeast Asian Geotechnical Conference & 2nd AGSSEA Conference (19SEAGC & 2AGSSEA), Kuala Lumpur, Malaysia.
10. Evaluation of Different Landslide Susceptibility Analysis Methods: A Case Study of Bagmati Rural Municipality10.3126/joetp.v3i1.49607 ↗
11. Skempton, A.W., and Delory, F.A. (1984). Stability of Natural Slopes in London Clay. Selected Papers on Soil Mechanics, Thomas Telford Publishing.10.1680/sposm.02050.0011 ↗
12. Constructing a Complete Landslide Inventory Dataset for the 2018 Monsoon Disaster in Kerala, India, for Land Use Change Analysis10.5194/essd-12-2899-2020 ↗
13. GIS Techniques and Statistical Models in Evaluating Landslide Hazard10.1002/esp.3290160505 ↗
14. Modelling Landslide Susceptibility Prediction: A Review and Construction of Semi-Supervised Imbalanced Theory10.1016/j.earscirev.2024.104700 ↗
15. A Review of Statistically-Based Landslide Susceptibility Models10.1016/j.earscirev.2018.03.001 ↗
16. Tree Retraining in the Decision Tree Learning Algorithm10.1088/1757-899X/1047/1/012082 ↗
17. Decision Tree Based Ensemble Machine Learning Approaches for Landslide Susceptibility Mapping10.1080/10106049.2021.1892210 ↗
18. Machine Learning Methods for Landslide Susceptibility Studies: A Comparative Overview of Algorithm Performance10.1016/j.earscirev.2020.103225 ↗
19. Machine Learning for Landslides Prevention: A Survey10.1007/s00521-020-05529-8 ↗
20. Prediction of the Landslide Susceptibility: Which Algorithm, Which Precision?10.1016/j.catena.2017.11.022 ↗
21. Investigating the Effects of Different Landslide Positioning Techniques, Landslide Partitioning Approaches, and Presence-Absence Balances on Landslide Susceptibility Mapping10.1016/j.catena.2019.104364 ↗
22. Comparison of the Presence-Only Method and Presence-Absence Method in Landslide Susceptibility Mapping10.1016/j.catena.2018.07.012 ↗
23. Regional Landslide Susceptibility Assessment Based on Improved Semi-Supervised Clustering and Deep Learning10.1007/s11440-023-01950-0 ↗
24. Three Oversampling Methods Applied in a Comparative Landslide Spatial Research in Penang Island, Malaysia10.1007/s42452-020-03307-8 ↗
25. A Comprehensive Approach to the Observation and Prevention of Debris Flows in China10.1007/BF00595676 ↗
26. Comparison of Bivariate and Multivariate Statistical Approaches in Landslide Susceptibility Mapping at a Regional Scale10.1016/j.geomorph.2012.03.036 ↗
27. New Zealand’s National Landslide Database10.1007/s10346-017-0843-6 ↗
28. Review on Landslide Susceptibility Mapping Using Support Vector Machines10.1016/j.catena.2018.03.003 ↗
29. Multicollinearity in Regression Analysis: Comment10.2307/1926450 ↗
30. Landslide Susceptibility Mapping Using Machine Learning Algorithms and Comparison of Their Performance at Abha Basin, Asir Region, Saudi Arabia10.1016/j.gsf.2020.05.010 ↗
31. Çellek, S. (2020). Effect of the Slope Angle and Its Classification on Landslide. Nat. Hazards Earth Syst. Sci., preprint.10.5194/nhess-2020-87 ↗
32. Assessment of Landslide Susceptibility on the Natural Terrain of Lantau Island, Hong Kong10.1007/s002540000163 ↗
33. Landslide Susceptibility Mapping Using Frequency Ratio, Logistic Regression, Artificial Neural Networks and Their Comparison: A Case Study from Kat Landslides (Tokat—Turkey)10.1016/j.cageo.2008.08.007 ↗
34. On the Calculation of the Topographic Wetness Index: Evaluation of Different Methods Based on Field Observations10.5194/hess-10-101-2006 ↗
35. Optimizing Landslide Susceptibility Mapping Using Machine Learning and Geospatial Techniques10.1016/j.ecoinf.2024.102583 ↗
36. GIS-Based Evaluation of Landslide Susceptibility Using Hybrid Computational Intelligence Models10.1016/j.catena.2020.104777 ↗
37. Status of Remote Sensing Algorithms for Estimation of Land Surface State Parameters10.1016/0034-4257(94)00071-T ↗
38. Optimizing Landslide Susceptibility Mapping in the Kongtong District, NW China: Comparing the Subdivision Criteria of Factors10.1080/10106049.2018.1499816 ↗
39. Landslide Susceptibility near Highways Is Increased by 1 Order of Magnitude in the Andes of Southern Ecuador, Loja Province10.5194/nhess-15-45-2015 ↗
40. Identifying the Role of Structural and Lithological Control of Landslides Using TOBIA and Weight of Evidence: Case Studies from Romania10.1007/s10346-021-01749-8 ↗
41. The Varnes Classification of Landslide Types, an Update10.1007/s10346-013-0436-y ↗
42. Comparison of GIS-Based Landslide Susceptibility Models Using Frequency Ratio, Logistic Regression, and Artificial Neural Network in a Tertiary Region of Ambon, Indonesia10.1016/j.geomorph.2018.06.006 ↗
43. Analysis and Evaluation of Landslide Susceptibility: A Review on Articles Published during 2005–2016 (Periods of 2005–2012 and 2013–2016)10.1007/s12517-018-3531-5 ↗
44. Lundberg, S.M., and Lee, S.-I. (2017, January 4–9). A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA.
45. Insights into Geospatial Heterogeneity of Landslide Susceptibility Based on the SHAP-XGBoost Model10.1016/j.jenvman.2023.117357 ↗
46. What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values10.3390/jtaer16030029 ↗
47. Yang, B., Lu, H., and Ran, Y. (2024). Advancing Non-Alcoholic Fatty Liver Disease Prediction: A Comprehensive Machine Learning Approach Integrating SHAP Interpretability and Multi-Cohort Validation. Front. Endocrinol., 15.10.3389/fendo.2024.1450317 ↗
48. Evaluating the Predictive Performance of Habitat Models Developed Using Logistic Regression10.1016/S0304-3800(00)00322-7 ↗
49. Aguirre-Gutiérrez, J., Carvalheiro, L.G., Polce, C., van Loon, E.E., Raes, N., Reemer, M., and Biesmeijer, J.C. (2013). Fit-for-Purpose: Species Distribution Model Performance Depends on Evaluation Criteria—Dutch Hoverflies as a Case Study. PLoS ONE, 8.10.1371/journal.pone.0063708 ↗
50. Species Distribution Models and Ecological Theory: A Critical Assessment and Some Possible New Approaches10.1016/j.ecolmodel.2006.07.005 ↗
51. Novel Methods Improve Prediction of Species’ Distributions from Occurrence Data10.1111/j.2006.0906-7590.04596.x ↗
52. Landslide Hazard Evaluation: A Review of Current Techniques and Their Application in a Multi-Scale Study, Central Italy10.1016/S0169-555X(99)00078-1 ↗
53. Landslide Susceptibility Mapping in the Damrei Romel Area, Cambodia Using Frequency Ratio and Logistic Regression Models10.1007/s00254-006-0256-7 ↗
54. Gómez-Ramírez, J., Ávila-Villanueva, M., and Fernández-Blázquez, M.Á. (2020). Selecting the Most Important Self-Assessed Features for Predicting Conversion to Mild Cognitive Impairment with Random Forest and Permutation-Based Methods. Sci. Rep., 10.10.1038/s41598-020-77296-4 ↗
55. The Use of the Area under the ROC Curve in the Evaluation of Machine Learning Algorithms10.1016/S0031-3203(96)00142-2 ↗
56. A Random Forest Model to Predict Heatstroke Occurrence for Heatwave in China10.1016/j.scitotenv.2018.09.369 ↗
57. Modeling Shallow Landslides and Root Reinforcement: A Review10.1016/j.ecoleng.2022.106671 ↗
58. Murgia, I., Giadrossich, F., Niccolini, M., Preti, F., Giambastiani, Y., Capra, G.F., and Cohen, D. (2021, January 19–30). Using SlideforMAP and SOSlope to Identify Susceptible Areas to Shallow Landslides in the Foreste Casentinesi National Park (Tuscany, Italy). Proceedings of the EGU General Assembly 2021, Online.10.5194/egusphere-egu21-14454 ↗
59. Marzini, L., D’Addario, E., Papasidero, M.P., Chianucci, F., and Disperati, L. (2023). Influence of Root Reinforcement on Shallow Landslide Distribution: A Case Study in Garfagnana (Northern Tuscany, Italy). Geosciences, 13.10.3390/geosciences13110326 ↗
60. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13–17). “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939778 ↗