考虑自然地域分异的云南省滑坡易发性制图及其可解释性分析

doi:10.3799/dqkx.2026.120

考虑自然地域分异的云南省滑坡易发性制图及其可解释性分析

doi: 10.3799/dqkx.2026.120

吴文欢^1,2,
杨雅捷³,
于龙⁴,
张强²,
文海家⁵,
田洁⁶,
尹红悦⁶,
潘明辰⁶

1. 核工业北京地质研究院铀资源探采与核遥感全国重点实验室, 北京 100029;
2. 北京师范大学地理科学学部, 北京 100875;
3. 云南师范大学地理学部, 云南昆明 650500;
4. 曲靖师范学院地理与旅游学院, 云南曲靖 655011;
5. 重庆大学土木工程学院, 重庆 400045;
6. 重庆师范大学地理信息系统应用研究重庆市高校重点实验室, 重庆 401331

基金项目:

中核集团稳定支持项目(No.WDZC-2023-002)

详细信息

作者简介:
吴文欢（1989-），男，博士，主要从事高光谱遥感与多源遥感技术集成应用等方面的研究及教学工作.ORCID：0000-0003-1718-390X； E-mail： whwu@briug.cn

中图分类号: P642.22
计量
- 文章访问数: 42
- HTML全文浏览量: 0
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2025-12-20
- 网络出版日期: 2026-05-13

Mapping Landslide Susceptibility in Yunnan Province Considering Natural Regional Differentiation and Its Interpretability Analysis

1. National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing, Beijing Research Institute of Uranium Geology, Beijing 100029, China;
2. Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China;
3. Faculty of Geography, Yunnan Normal University, Kunming 650500, China;
4. School of Geography and Tourism, Qujing Normal University, Qujing 655011, China;
5. School of Civil Engineering, Chongqing University, Chongqing 400045, China;
6. GIS Application Research Key Laboratory of Chongqing Education Commission, Chongqing Normal University, Chongqing 401331, China

摘要

摘要: 云南省滑坡灾害风险突出，但现有滑坡易发性制图（LSM）研究多局限于局地尺度，缺乏在统一标准和地域分异视角下的省域系统评估与可解释分析。基于云南省综合自然区划多级分区体系，本文将研究区细化为5个自然地带、8个自然地区及22个自然区，选取20个评价因子，构建自然区尺度的LightGBM-SHAP滑坡易发性模型，并结合SHAP方法解析滑坡影响因子贡献的空间差异特征。结果表明，各自然区模型均具有较强预测能力（测试集AUC均大于0.80）。省域尺度上，滑坡易发性呈现“西南部及山地边缘高、东北部及盆地低”的空间格局； SHAP分析显示，高程、植被覆盖率、年均降雨量、地震点核密度和POI核密度为普遍性影响因子，而土地利用、距河流/道路距离、采矿点核密度和坡度等因子具有显著区域差异性。研究表明，考虑自然地域分异的多分区建模与可解释性分析可有效提升滑坡易发性评价的科学性与应用价值。
- 滑坡易发性 /
- 省域尺度评估 /
- LightGBM-SHAP /
- 地域分异视角 /
- 综合自然区划
Abstract: Yunnan Province faces prominent landslide hazards, yet existing landslide susceptibility mapping (LSM) studies are predominantly limited to local scales, lacking provincial-scale systematic assessment and interpretable analysis under unified standards and regional differentiation perspectives. Based on the multi-level hierarchical zoning system of comprehensive physical geography in Yunnan Province, this study subdivided the research area into 5 natural zones, 8 natural regions, and 22 natural subregions. Twenty evaluation factors were selected to construct natural subregion-scale LightGBM-SHAP landslide susceptibility models, combined with SHAP method to analyze spatial differentiation characteristics of landslide influencing factor contributions. The results indicate that all natural subregion models demonstrate strong predictive capability (AUC > 0.80 for test sets). At the provincial scale, landslide susceptibility presents a spatial pattern of "high in southwestern mountainous margins and low in northeastern basins." SHAP analysis reveals that elevation, normalized difference vegetation index (NDVI), annual average rainfall, seismic point kernel density, and POI kernel density serve as universal influencing factors, while land use, distance from rivers/roads, mining point kernel density, and slope exhibit significant regional heterogeneity. This study demonstrates that multi-partition modeling incorporating natural regional differentiation combined with interpretability analysis can effectively enhance the scientific validity and practical applicability of landslide susceptibility assessment.
- landslide susceptibility /
- provincial-scale assessment /
- LightGBM-SHAP /
- regional differentiation perspective /
- comprehensive natural zoning

HTML全文

参考文献(45)

Aleotti, P., Chowdhury, R., 1999. Landslide hazard assessment: summary review and new perspectives. Bulletin of Engineering Geology and the Environment, 58(1):21-44. https://doi.org/10.1007/s100640050066.
Al-Najjar, H., Pradhan, B., Beydoun, G.,et al., 2023. A novel method using explainable artificial intelligence (xai)-based shapley additive explanations for spatial landslide prediction using time-series sar dataset. Gondwana Research, 123:107-124. https://doi.org/10.1016/j.gr.2022.08.004.
Baptista, M. L., Goebel, K., & Henriques, E., 2022. Relation between prognostics predictor evaluation metrics andlocal interpretability shap values. Artificial Intelligence, 306. https://doi.org/10.1016/j.artint.2022.103667.
Broeckx, J., Vanmaercke, M., Duchateau, R., et al., 2018. A data-based landslide susceptibility map of africa. Earth-Science Reviews, 185: 102-121. https://doi.org/10.1016/j.earscirev.2018.05.002.
Cao, S., Guo, C., Yang, W., et al., 2025. Development characteristics and evolutionary mechanisms of large high-elevation landslides in the Deqin section of the upper Lancang River. Earth Science, 1-29 (in Chinese with English abstract).
Cascini, L. 2008. Applicability of landslide susceptibility and hazard zoning at different scales. Engineering Geology, 102(3-4): 164-177. https://doi.org/10.1016/j.enggeo.2008.03.016.
Cemiloglu, A., Zhu, L. C., Mohammednour, A. B., et al., 2023. Landslide susceptibility assessment for maragheh county, iran, using the logistic regression algorithm. Land, 12(7). https://doi.org/10.3390/land12071397.
Chen, W., Zhang, S., Li, R. W., et al., 2018. Performance evaluation of the gis-based data mining techniques of best-first decision tree, random forest, and naive bayes tree for landslide susceptibility modeling. Science of the Total Environment, 644: 1006-1018. https://doi.org/10.1016/j.scitotenv.2018.06.389.
Chen, X. L., Liu, C. G., Chang, Z. F., et al., 2016. The relationship between the slope angle and the landslide size derived from limit equilibrium simulations. Geomorphology, 253: 547-550. https://doi.org/10.1016/j.geomorph.2015.01.036.
Dragicevic, S., Lai, T., Balram, S, et al., 2015. Gis-based multicriteria evaluation with multiscale analysis to characterize urban landslide susceptibility in data-scarce environments. Habitat International, 45: 114-125. https://doi.org/10.1016/j.habitatint.2014.06.031.
Fell, R., Cororninas, J., Bonnard, C., et al., 2008. Guidelines for landslide susceptibility, hazard and risk-zoning for land use planning. Engineering Geology, 102(3-4): 85-98. https://doi.org/10.1016/j.enggeo.2008.03.022.
Feng, W., Zhao, J., Yi, X., et al., 2025. Characteristics and driving factors of rainfall-induced clustered landslides triggered by the “June 16” extreme rainfall event in the Fujian-Guangdong-Jiangxi border region. Earth Science, 50(10): 4111-4124 (in Chinese with English abstract).
Günther, A., Van den Eeckhaut, M., Malet, J. P., et al., 2014. Climate-physiographically differentiated pan-european landslide susceptibility assessment using spatial multi-criteria evaluation and transnational landslide information. Geomorphology, 224: 69-85. https://doi.org/10.1016/j.geomorph.2014.07.011.
He, F., Tan, S. C., Liu, H. J., 2022. Mechanism of rainfall induced landslides in yunnan province using multi-scale spatiotemporal analysis and remote sensing interpretation. Microprocessors and Microsystems, 90. https://doi.org/10.1016/j.micpro.2022.104502.
Huang, F. M., Cao, Z. S., Guo, J. F., et al., 2020. Comparisons of heuristic, general statistical and machine learning models for landslide susceptibility prediction and mapping. Catena, 191. https://doi.org/10.1016/j.catena.2020.104580.
Lan, H. X., Zhou, C. H., Wang, L. J., et al., 2004. Landslide hazard spatial analysis and prediction using gis in the xiaojiang watershed, yunnan, china. Engineering Geology, 76(1): 109-128. https://doi.org/https://doi.org/10.1016/j.enggeo.2004.06.009.
Lee, M. L., Ng, K. Y., Huang, Y. F., et al., 2014. Rainfall-induced landslides in hulu kelang area, malaysia. Natural Hazards, 70(1): 353-375. https://doi.org/10.1007/s11069-013-0814-8.
Li, W. Y., Liu, C., Hong, Y., et al., 2016. A public cloud-based china's landslide inventory database (cslid): development, zone, and spatiotemporal analysis for significant historical events, 1949-2011. Journal of Mountain Science, 13(7): 1275-1285. https://doi.org/10.1007/s11629-015-3659-7.
Li, Z., 2022. Extracting spatial effects from machine learning model using local interpretation method: an example of shap and xgboost. Computers, Environment and Urban Systems, 96: 101845. https://doi.org/https://doi.org/10.1016/j.compenvurbsys.2022.101845.
Lin, G. F., Chang, M. J., Huang, Y. C., et al., 2017. Assessment of susceptibility to rainfall-induced landslides using improved self-organizing linear output map, support vector machine, and logistic regression. Engineering Geology, 224: 62-74. https://doi.org/10.1016/j.enggeo.2017.05.009.
Liu, B., Guo, H. X., Li, J. L., et al., 2024. Application and interpretability of ensemble learning for landslide susceptibility mapping along the three gorges reservoir area, china. Natural Hazards, 120(5): 4601-4632. https://doi.org/10.1007/s11069-023-06374-3.
Liu, S. L., Wang, L. Q., Zhang, W. A., et al., 2023. A comprehensive review of machine learning-based methods in landslide susceptibility mapping. Geological Journal, 58(6): 2283-2301. https://doi.org/10.1002/gj.4666.
Medina, V., Hürlimann, M., Guo, Z. Z., et al., 2021. Fast physically-based model for rainfall-induced landslide susceptibility assessment at regional scale. Catena, 201. https://doi.org/10.1016/j.catena.2021.105213.
Reichenbach, P., Rossi, M., Malamud, B. D., et al., 2018. A review of statistically-based landslide susceptibility models. Earth-Science Reviews, 180: 60-91. https://doi.org/10.1016/j.earscirev.2018.03.001.
Riaz, M. T., Basharat, M., Hameed, N., et al., 2018. A data-driven approach to landslide-susceptibility mapping in mountainous terrain: case study from the northwest himalayas, pakistan. Natural Hazards Review, 19(4). https://doi.org/10.1061/(ASCE)NH.1527-6996.0000302.
Sun, D. L., Chen, D. L., Zhang, J. L., et al., 2023. Landslide susceptibility mapping based on interpretable machine learning from the perspective of geomorphological differentiation. Land, 12(5). https://doi.org/10.3390/land12051018.
Sun, D. L., Gu, Q. Y., Wen, H. J., et al., 2023. Assessment of landslide susceptibility along mountain highways based on different machine learning algorithms and mapping units by hybrid factors screening and sample optimization. Gondwana Research, 123: 89-106. https://doi.org/10.1016/j.gr.2022.07.013.
Sun, D. L., Xu, J. H., Wen, H. J., et al., 2021. Assessment of landslide susceptibility mapping based on bayesian hyperparameter optimization: a comparison between logistic regression and random forest. Engineering Geology, 281. https://doi.org/10.1016/j.enggeo.2020.105972.
Sun, X. L., Liu, M. X., Sima, Z. Q., 2020. A novel cryptocurrency price trend forecasting model based on lightgbm. Finance Research Letters, 32. https://doi.org/10.1016/j.frl.2018.12.032.
Wang, H. J., Liang, Q. X., Hancock, J. T., et al., 2024. Feature selection strategies: a comparative analysis of shap-value and importance-based methods. Journal of Big Data, 11(1). https://doi.org/10.1186/s40537-024-00905-w.
Wang, X. L., Zhang, L. Q., Wang, S. J., et al., 2014. Regional landslide susceptibility zoning with considering the aggregation of landslide points and the weights of factors. Landslides, 11(3): 399-409. https://doi.org/10.1007/s10346-013-0392-6.
Xing, Y., Yue, J. P., Guo, Z. Z., et al., 2021. Large-scale landslide susceptibility mapping using an integrated machine learning model:a case study in the lvliang mountains of china. Frontiers in Earth Science, 9. https://doi.org/10.3389/feart.2021.722491.
Ye, H., Bai, D., Tan, S. C., et al., 2024. Vulnerability assessment of landslides along the yunnan section of the northern tropic of cancer based on fuzzy evidence weight model. Natural Hazards, 120(14): 12705-12727. https://doi.org/10.1007/s11069-024-06696-w.
Youssef, K., Shao, K., Moon, S., et al., 2023. Landslide susceptibility modeling by interpretable neural network. Communications Earth & Environment, 4(1). https://doi.org/10.1038/s43247-023-00806-5.
Zhang, J. Y., Ma, X. L., Zhang, J. L., et al., 2023. Insights into geospatial heterogeneity of landslide susceptibility based on the shap-xgboost model. Journal of Environmental Management, 332. https://doi.org/10.1016/j.jenvman.2023.117357.
Zhang, S., Li, C., Peng, J., et al., 2023. Fatal landslides in china from 1940 to 2020: occurrences and vulnerabilities. Landslides, 20(6),: 1243-1264. https://doi.org/10.1007/s10346-023-02034-6.
Zhang, W. A., Gu, X., Tang, L. B., et al., 2022. Application of machine learning, deep learning and optimization algorithms in geoengineering and geoscience: comprehensive review and future challenge. Gondwana Research, 109: 1-17. https://doi.org/10.1016/j.gr.2022.03.015.
Zhao, X., Zhao, Z. F., Huang, F. M., et al., 2023. Application of environmental variables in statistically-based landslide susceptibility mapping:a review. Frontiers in Earth Science, 11. https://doi.org/10.3389/feart.2023.1147427.
Zhou, X. Z., Wen, H. J., Li, Z. W., et al., 2022. An interpretable model for the susceptibility of rainfall-induced shallow landslides based on shap and xgboost. Geocarto International, 37(26): 13419-13450. https://doi.org/10.1080/10106049.2022.2076928.
Zheng, Y. K., Chen, J. G., Wang, C. B., 2020. Application of Certainty Factor and Random Forest Models for Landslide Susceptibility Assessment in Mangshi, Yunnan, China. Bulletin of Geological Science and Technology, 39(6): 131-144 (in Chinese with English abstract).
附中文参考文献
曹世超, 郭长宝, 杨为民, 等, 2025. 澜沧江上游德钦段大型高位滑坡发育特征与形成演化机制研究. 地球科学, 1-29.
冯文凯, 赵家琛, 易小宇, 等, 2025. 闽粤赣边区“6·16”强降雨诱发群发滑坡特征与驱动因素. 地球科学, 50(10): 4111-4124.
杨一光, 1991. 云南省综合自然区划.北京: 高等教育出版社, 253
郑迎凯, 陈建国, 王成彬, 等, 2020. 确定性系数与随机森林模型在云南芒市滑坡易发性评价中的应用. 地质科技通报, 39(6): 131-144.

施引文献

资源附件(0)

访问统计

点击查看大图

计量

文章访问数: 42
HTML全文浏览量: 0
PDF下载量: 2
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

考虑自然地域分异的云南省滑坡易发性制图及其可解释性分析

doi: 10.3799/dqkx.2026.120

作者简介:
吴文欢（1989-），男，博士，主要从事高光谱遥感与多源遥感技术集成应用等方面的研究及教学工作.ORCID：0000-0003-1718-390X； E-mail： whwu@briug.cn

计量

Mapping Landslide Susceptibility in Yunnan Province Considering Natural Regional Differentiation and Its Interpretability Analysis

计量

目录

留言板

考虑自然地域分异的云南省滑坡易发性制图及其可解释性分析

doi: 10.3799/dqkx.2026.120

作者简介: 吴文欢（1989-），男，博士，主要从事高光谱遥感与多源遥感技术集成应用等方面的研究及教学工作.ORCID：0000-0003-1718-390X； E-mail： whwu@briug.cn

计量

出版历程

Mapping Landslide Susceptibility in Yunnan Province Considering Natural Regional Differentiation and Its Interpretability Analysis

计量

出版历程

目录

作者简介:
吴文欢（1989-），男，博士，主要从事高光谱遥感与多源遥感技术集成应用等方面的研究及教学工作.ORCID：0000-0003-1718-390X； E-mail： whwu@briug.cn