Evolution Patterns of Landslide Susceptibility in Three Gorges Reservoir Areas
-
摘要: 为探究库区滑坡易发性演化规律，以三峡库区万州区多时序滑坡为研究对象，利用频率比法分析滑坡空间分布时变规律，通过机器学习算法建立多时序下的滑坡易发性模型并分析模型时效性及易发性演化规律，采用标准差椭圆刻画不同时序下高易发区的分布趋势.结果表明：各孕灾因子对滑坡的贡献度随时间变化；易发性模型的建模精度随滑坡编录数据时间跨度的增加而降低；按照时间顺序采样的滑坡易发性模型建模精度高、预测精度低，且预测性能随时间推移而降低；不同时序下高易发区的标准差椭圆分布存在显著差异且与人类工程活动相关.研究揭示了滑坡易发性的时变性和演化规律，未来应从滑坡发育的时间视角出发，探索具有时效性的易发性评价方法.Abstract: To understand the evolution of landslide susceptibility in reservoir areas, in this research it focuses on multi-temporal landslides in the Wanzhou district of the Three Gorges Reservoir area. The spatial distribution of landslides and their temporal variations were analyzed using the frequency ratio method. Machine learning algorithms are employed to construct landslide susceptibility models for different time sequences, investigating the models' temporal effectiveness and the evolution of susceptibility. The distribution trends of areas with high susceptibility in various time sequences are depicted using standard deviation ellipses. Results show that the impact of different predisposing factors on landslides changes over time. As the time span of landslide inventory data increases, the accuracy of the susceptibility models decreases. Models based on chronologically ordered data have high modeling accuracy but low predictive precision, and their predictive performance diminishes over time. The standard deviation ellipses for high-susceptibility areas differ significantly across time sequences and correlate with human engineering activities. The study highlights the temporal variability and evolving patterns of landslide susceptibility, underscoring the need for future landslide susceptibility assessments to consider the temporal aspect of landslide development.
-
图 7 不同时序下高易发区的标准差椭圆（SDE）分布
Fig. 7. Distribution of standard deviational ellipse (SDE) in different time series
表 1 不同时间集采样下随机森林模型的建模、预测精度
Table 1. Performance of RF models in different temporal sampling strategies
建模数据 建模精度 预测精度 $ {T}_{2} $ $ {T}_{3} $ $ {T}_{4} $ $ {T}_{5} $ $ {T}_{1} $ 0.937 0.766 0.652 0.639 0.548 $ {T}_{1}~{T}_{2} $ 0.892 0.632 0.671 0.582 $ {T}_{1}~{T}_{3} $ 0.845 0.675 0.569 $ {T}_{1}~{T}_{4} $ 0.810 0.605 
下载: 导出CSV
表 2 不同时间集采样下极限梯度决策提升树模型的建模、预测精度
Table 2. Performance of XGBoost models in different temporal sampling strategies
建模数据 建模精度 预测精度 $ {T}_{2} $ $ {T}_{3} $ $ {T}_{4} $ $ {T}_{5} $ $ {T}_{1} $ 0.946 0.744 0.630 0.581 0.566 $ {T}_{1}~{T}_{2} $ 0.897 0.611 0.656 0.615 $ {T}_{1}~{T}_{3} $ 0.867 0.653 0.563 $ {T}_{1}~{T}_{4} $ 0.812 0.622
下载: 导出CSV
-
Bradley, A. P., 1997. The Use of the Area under the ROC Curve in the Evaluation of Machine Learning Algorithms. Pattern Recognition, 30(7): 1145-1159. https://doi.org/10.1016/S0031-3203(96)00142-2 Breiman, L., 2001. Random Forests. Machine Learning, 45(1): 5–32. https://doi.org/10.1023/A: 1010933404324 doi: 10.1023/A:1010933404324 Chen, J., Li, X., Yang, Z. F., 2005. On the Distribution and Mechanism of Landslides in the Three Gorges Reservoir Area. Journal of Engineering Geology, 13(3): 305-309(in Chinese with English abstract). Chen, T. Q., Guestrin, C., Chen, T. Q., et al., 2016. XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. August 13 - 17, 2016, San Francisco, California, USA. ACM: 785-794. https://doi.org/10.1145/2939672.2939785 Chen, W., Pourghasemi, H. R., Panahi, M., et al., 2017. Spatial Prediction of Landslide Susceptibility Using an Adaptive Neuro-Fuzzy Inference System Combined with Frequency Ratio, Generalized Additive Model, and Support Vector Machine Techniques. Geomorphology, 297: 69-85. https://doi.org/10.1016/j.geomorph.2017.09.007 Cheng, J. Y., Dai, X. A., Wang, Z. K., et al., 2022. Landslide Susceptibility Assessment Model Construction Using Typical Machine Learning for the Three Gorges Reservoir Area in China. Remote Sensing, 14(9): 2257. https://doi.org/10.3390/rs14092257 Choi, J., Oh, H. J., Lee, H. J., et al., 2012. Combining Landslide Susceptibility Maps Obtained from Frequency Ratio, Logistic Regression, and Artificial Neural Network Models Using ASTER Images and GIS. Engineering Geology, 124: 12-23. https://doi.org/10.1016/j.enggeo.2011.09.011 Deng, M., Cai, J. N., Yang, W. T., et al., 2020. Spatio-Temporal Analysis Methods for Multi-Modal Geographic Big Data. Journal of Geo-Information Science, 22(1): 41-56(in Chinese with English abstract). Hu, Q., Zhou, Y., Wang, S. X., et al., 2020. Machine Learning and Fractal Theory Models for Landslide Susceptibility Mapping: Case Study from the Jinsha River Basin. Geomorphology, 351: 106975. https://doi.org/10.1016/j.geomorph.2019.106975 Huang, F. M., Chen, B., Mao, D. X., et al., 2023. Landslide Susceptibility Prediction Modeling and Interpretability Based on Self-Screening Deep Learning Model. Earth Science, 48(5): 1696-1710(in Chinese with English abstract). Huang, F. M., Yin, K. L., Huang, J. S., et al., 2017. Landslide Susceptibility Mapping Based on Self-Organizing-Map Network and Extreme Learning Machine. Engineering Geology, 223: 11-22. https://doi.org/10.1016/j.enggeo.2017.04.013 Jones, J. N., Boulton, S. J., Bennett, G. L., et al., 2021. Temporal Variations in Landslide Distributions Following Extreme Events: Implications for Landslide Susceptibility Modeling. Journal of Geophysical Research: Earth Surface, 126(7): e2021JF006067. https://doi.org/10.1029/2021JF006067 Khanna, K., Martha, T. R., Roy, P., et al., 2021. Effect of Time and Space Partitioning Strategies of Samples on Regional Landslide Susceptibility Modelling. Landslides, 18(6): 2281-2294. https://doi.org/10.1007/s10346-021-01627-3 Lefever, D. W., 1926. Measuring Geographic Concentration by Means of the Standard Deviational Ellipse. American Journal of Sociology, 32(1): 88-94. https://doi.org/10.1086/214027 Li, K. F., Zhu, C., Wu, L., et al., 2013. Problems Caused by the Three Gorges Dam Construction in the Yangtze River Basin: A Review. Environmental Reviews, 21(3): 127-135. https://doi.org/10.1139/er-2012-0051 Lin, Q. G., Wang, Y., 2018. Spatial and Temporal Analysis of a Fatal Landslide Inventory in China from 1950 to 2016. Landslides, 15(12): 2357-2372. https://doi.org/10.1007/s10346-018-1037-6 Loche, M., Alvioli, M., Marchesini, I., et al., 2022. Landslide Susceptibility Maps of Italy: Lesson Learnt from Dealing with Multiple Landslide Types and the Uneven Spatial Distribution of the National Inventory. Earth-Science Reviews, 232: 104125. https://doi.org/10.1016/j.earscirev.2022.104125 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/10.1016/j.earscirev.2020.103225 Miao, F. S., Ruan, Q. Y., Wu, Y. P., et al., 2023a. Landslide Dynamic Susceptibility Mapping Base on Machine Learning and the PS-InSAR Coupling Model. Remote Sensing, 15(22): 5427. https://doi.org/10.3390/rs15225427 Miao, F. S., Zhao, F. C., Wu, Y. P., et al., 2023b. Landslide Susceptibility Mapping in Three Gorges Reservoir Area Based on GIS and Boosting Decision Tree Model. Stochastic Environmental Research and Risk Assessment, 37(6): 2283-2303. https://doi.org/10.1007/s00477-023-02394-4 Ozturk, U., Pittore, M., Behling, R., et al., 2021. How Robust are Landslide Susceptibility Estimates? Landslides, 18(2): 681-695. https://doi.org/10.1007/s10346-020-01485-5 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 Samia, J., Temme, A., Bregt, A., et al., 2017. Do Landslides Follow Landslides? Insights in Path Dependency from a Multi-Temporal Landslide Inventory. Landslides, 14(2): 547-558. https://doi.org/10.1007/s10346-016-0739-x Tien Bui, D., Pradhan, B., Lofman, O., et al., 2012. Landslide Susceptibility Mapping at Hoa Binh Province (Vietnam) Using an Adaptive Neuro-Fuzzy Inference System and GIS. Computers & Geosciences, 45: 199-211. https://doi.org/10.1016/j.cageo.2011.10.031 Torizin, J., Wang, L. C., Fuchs, M., et al., 2018. Statistical Landslide Susceptibility Assessment in a Dynamic Environment: A Case Study for Lanzhou City, Gansu Province, NW China. Journal of Mountain Science, 15(6): 1299-1318. https://doi.org/10.1007/s11629-017-4717-0 Vakhshoori, V., Zare, M., 2018. Is the ROC Curve a Reliable Tool to Compare the Validity of Landslide Susceptibility Maps? Geomatics, Natural Hazards and Risk, 9(1): 249-266. https://doi.org/10.1080/19475705.2018.1424043 Wang, J. J., Yin, K. L., Xiao, L. L., 2014. Landslide Susceptibility Assessment Based on GIS and Weighted Information Value: A Case Study of Wanzhou District, Three Gorges Reservoir. Chinese Journal of Rock Mechanics and Engineering, 33(4): 797-808(in Chinese with English abstract). Wang, Y. M., Feng, L. W., Li, S. J., et al., 2020. A Hybrid Model Considering Spatial Heterogeneity for Landslide Susceptibility Mapping in Zhejiang Province, China. CATENA, 188: 104425. https://doi.org/10.1016/j.catena.2019.104425 Wu, S. R., Shi, J. S., Zhang, Y. S., et al., 2006. Landslide Mechanisms: A Case Study of the Yangtze Three Gorges Reservoir Area. Geological Bulletin of China, 25(7): 874-879(in Chinese with English abstract). Xiao, T., 2020. Risk Assessment of Landslide Disaster in Wanzhou District and Bank Section of Three Gorges Reservoir Area(Dissertation). China University of Geosciences, Wuhan (in Chinese with English abstract). Xiao, T., Yu, L. B., Tian, W. M., et al., 2021. Reducing Local Correlations among Causal Factor Classifications as a Strategy to Improve Landslide Susceptibility Mapping. Frontiers in Earth Science, 9: 781674. https://doi.org/10.3389/feart.2021.781674 Yin, Y. P., 2004. Research Progress of Major Geological Disasters and Their Prevention in the Three Gorges Reservoir Area. Geotechnical Engineering Community, (8): 20-26(in Chinese). Yuan, W. H., Yin, D. W., Finlayson, B., et al., 2012. Assessing the Potential for Change in the Middle Yangtze River Channel Following Impoundment of the Three Gorges Dam. Geomorphology, 147: 27-34. https://doi.org/10.1016/j.geomorph.2011.06.039 Zeng, T. R., Wu, L. Y., Peduto, D., et al., 2023. Ensemble Learning Framework for Landslide Susceptibility Mapping: Different Basic Classifier and Ensemble Strategy. Geoscience Frontiers, 14(6): 101645. https://doi.org/10.1016/j.gsf.2023.101645 Zhang, H. J., Song, Y. X., Xu, S. L., et al., 2022. Combining a Class-Weighted Algorithm and Machine Learning Models in Landslide Susceptibility Mapping: A Case Study of Wanzhou Section of the Three Gorges Reservoir, China. Computers & Geosciences, 158: 104966. https://doi.org/10.1016/j.cageo.2021.104966 Zhao, Y. F., Wu, Q. R., Wei, P. P., et al., 2022. Explore the Mitigation Mechanism of Urban Thermal Environment by Integrating Geographic Detector and Standard Deviation Ellipse (SDE). Remote Sensing, 14(14): 3411. https://doi.org/10.3390/rs14143411 陈剑, 李晓, 杨志法, 2005. 三峡库区滑坡的时空分布特征与成因探讨. 工程地质学报, 13(3): 305-309. 邓敏, 蔡建南, 杨文涛, 等, 2020. 多模态地理大数据时空分析方法. 地球信息科学学报, 22(1): 41-56. 黄发明, 陈彬, 毛达雄, 等, 2023. 基于自筛选深度学习的滑坡易发性预测建模及其可解释性. 地球科学, 48(5): 1696-1710. 王佳佳, 殷坤龙, 肖莉丽, 2014. 基于GIS和信息量的滑坡灾害易发性评价: 以三峡库区万州区为例. 岩石力学与工程学报, 33(4): 797-808. 吴树仁, 石菊松, 张永双, 等, 2006. 滑坡宏观机理研究: 以长江三峡库区为例. 地质通报, 25(7): 874-879. 肖婷, 2020. 三峡库区万州区及重点库岸段滑坡灾害风险评价(博士学位论文). 武汉: 中国地质大学. 殷跃平, 2004. 三峡库区重大地质灾害及防治研究进展. 岩土工程界, (8): 20-26. -
点击查看大图
图(7) / 表(2)
计量
- 文章访问数: 24
- HTML全文浏览量: 8
- PDF下载量: 6
- 被引次数: 0
