Susceptibility Assessment of Landslides Based on Convolutional Neural Network Model: A Case Study from Xianrendong National Nature Reserve in Southern Liaoning Province
-
摘要: 为了解决滑坡易发性评价过程中存在的滑坡编录数据不足，主观或者随机地选取非滑坡栅格单元而导致模型准确率较低等问题，以辽南仙人洞国家级自然保护区为研究区，首先，从地形地貌、地质条件、水文气象条件和人类工程活动等方面选取了12个评价因子构建滑坡评价体系；其次，利用SMOTETomek综合采样方法解决滑坡与非滑坡样本类别的比例失衡问题，进而建立滑坡易发性评价模型的数据集；最后，针对研究区东西两侧（A区和B区）的非线性滑坡数据，通过构建卷积神经网络（Convolutional Neural Networks，CNN）模型进行滑坡易发性评价，并精准绘制了研究区滑坡易发性分布图.结果表明：CNN模型具有良好的适应性，绘制的滑坡易发性分区图显示出合理的空间分布，A区和B区的测试集AUC面积分别为91.2%和94.3%；70%的滑坡数据分布在较高及以上等级的易发区，68.7%的非滑坡数据分布在较低及以下等级的易发区；滑坡高易发区主要位于研究区东北部猫岭北沟山一带、冰峪沟风景区的北部山区和碧流河水库沿岸区.研究成果为辽南仙人洞国家级自然保护区的地质灾害防治规划、应急预案制定等提供了重要的科学依据.Abstract: In order to solve the problems of insufficient landslide catalog data in the process of landslide susceptibility evaluation, and low model accuracy due to subjective or random selection of non-landslide raster cells, 12 evaluation factors were selected from the aspects of topography and geomorphology, geological conditions, hydrometeorological conditions and human engineering activities to construct a landslide evaluation system for Xianrendong National Nature Reserve in southern Liaoning Province in this paper; Furthermore, the imbalance of sample categories between landslide and non-landslide was solved based on SMOTETomek comprehensive sampling method, and then a dataset of landslide susceptibility evaluation was established; Finally, for the nonlinear landslide data in the east and west sides of the study area (zones A and B), the convolutional neural networks (CNN) model was constructed to evaluate the landslide susceptibility, and the distribution map of landslide susceptibility in the study area was accurately drawn. The results show that the CNN model had good adaptability, and the zoning map of landslide susceptibility shows a reasonable spatial distribution. The AUC area of the test set in part A and part B of the study area was 91.2% and 94.3%, respectively.70% of landslides were distributed in higher and above grade prone areas, and 68.7% of non-landslides were distributed in lower and below grade prone areas. The high prone area of landslide is mainly located in the area of Maoling Beigou Mountain in the northeast of the study area, the northern mountainous area of the Bingyugou Scenic Area, and the coastal area of the Biliuhe Reservoir. The research results can provide an important scientific basis for the planning of geological disaster prevention and control, and the formulation of emergency plans in Xianrendong National Nature Reserve in southern Liaoning Province.
-
图 3 研究区滑坡易发性评价因子分布
Fig. 3. The distribution map of landslide susceptibility assessment factors in the study area
表 1 滑坡易发性评价因子多重共线性检验
Table 1. Multicollinearity test of landslide susceptibility assessment factors
滑坡因子 高程 坡向 坡度 地形起伏度 TWI 岩性 距断层距离 汛期降雨量 距河流距离 距道路距离 土地利用类型 NDVI VIF 2.59 1.02 1.66 2.35 1.38 1.21 1.41 1.42 1.14 1.27 1.29 1.54 TOL 0.39 0.98 0.60 0.43 0.72 0.83 0.71 0.70 0.88 0.79 0.78 0.65 
下载: 导出CSV
表 2 CNN参数设置
Table 2. The parameter setting of CNN
CNN模型参数 卷积核大小 最大池化 激活函数 优化器 学习率 训练次数 A区 3×1 2×1 修正线性单元函数 自适应梯度下降算法 0.003 80 B区 3×1 2×1 双曲正切函数 自适应梯度下降算法 0.003 50
下载: 导出CSV
-
Althuwaynee, O. F., Pradhan, B., Lee, S., 2016. A Novel Integrated Model for Assessing Landslide Susceptibility Mapping Using CHAID and AHP Pair-Wise Comparison. International Journal of Remote Sensing, 37(5): 1190-1209. https://doi.org/10.1080/01431161.2016.1148282 Aslam, B., Zafar, A., Khalil, U., 2021. Development of Integrated Deep Learning and Machine Learning Algorithm for the Assessment of Landslide Hazard Potential. Soft Computing, 25(21): 13493-13512. https://doi.org/10.1007/s00500-021-06105-5 Blahut, J., van Westen, C. J., Sterlacchini, S., 2010. Analysis of Landslide Inventories for Accurate Prediction of Debris-Flow Source Areas. Geomorphology, 119(1-2): 36-51. https://doi.org/10.1016/j.geomorph.2010.02.017 Chauhan, S., Sharma, M., Arora, M. K., et al., 2010. Landslide Susceptibility Zonation through Ratings Derived from Artificial Neural Network. International Journal of Applied Earth Observation and Geoinformation, 12(5): 340-350. https://doi.org/10.1016/j.jag.2010.04.006 Chen, W., Li, W. P., Hou, E. K., et al., 2014. Landslide Susceptibility Mapping Based on GIS and Information Value Model for the Chencang District of Baoji, China. Arabian Journal of Geosciences, 7(11): 4499-4511. https://doi.org/10.1007/s12517-014-1369-z Fang, Z. C., Wang, Y., Peng, L., et al., 2020. Integration of Convolutional Neural Network and Conventional Machine Learning Classifiers for Landslide Susceptibility Mapping. Computers & Geosciences, 139: 104470. https://doi.org/10.1016/j.cageo.2020.104470 Geertsema, M., Pojar, J. J., 2007. Influence of Landslides on Biophysical Diversity—A Perspective from British Columbia. Geomorphology, 89(1-2): 55-69. https://doi.org/10.1016/j.geomorph.2006.07.019 Girshick, R., 2015. Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 1440-1448. https://doi.org/10.1109/ICCV.2015.169 Habumugisha, J. M., Chen, N. S., Rahman, M., et al., 2022. Landslide Susceptibility Mapping with Deep Learning Algorithms. Sustainability, 14(3): 1734. https://doi.org/10.3390/su14031734 Hansen, A., Franks, C. A. M., Kirk, P. A., et al., 1995. Application of GIS to Hazard Assessment, with Particular Reference to Landslides in Hong Kong. Geographical Information Systems in Assessing Natural Hazards. Springer, Dordrecht, 273-298. https://doi.org/10.1007/978-94-015-8404-3_14 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., Chen, J. W., Tang, Z. P., et al., 2021. Uncertainties of Landslide Susceptibility Prediction due to Different Spatial Resolutions and Different Proportions of Training and Testing Datasets. Journal of Rock Mechanics and Engineering, 40(6): 1155-1169 (in Chinese with English abstract). Huang, F. M., Yin, K. L., Jiang, S. H., et al., 2018. Landslide Susceptibility Assessment Based on Clustering Analysis and Support Vector Machine. Journal of Rock Mechanics and Engineering, 37(1): 156-167 (in Chinese with English abstract). Huang, W. B., Ding, M. T., Wang, D., et al., 2022. Evaluation of Landslide Susceptibility Based on Layer Adaptive Weighted Convolutional Neural Network Model along Sichuan-Tibet Traffic Corridor. Earth Science, 47(6): 2015-2030 (in Chinese with English abstract). Ilmy, H. F., Darminto, M. R., Widodo, A., 2021. Application of Machine Learning on Google Earth Engine to Produce Landslide Susceptibility Mapping (Case Study: Pacitan). IOP Conference Series: Earth and Environmental Science, 731(1): 012028. https://doi.org/10.1088/1755-1315/731/1/012028 Li, W. B., Fan, X. M., Huang, F. M., 2021. Uncertainties of Landslide Susceptibility Modeling under Different Environmental Factor Connections and Prediction Models. Earth Science, 46(10): 3777-3795 (in Chinese with English abstract). Li, W. J., Fang, Z. C., Wang, Y., 2022. Stacking Ensemble of Deep Learning Methods for Landslide Susceptibility Mapping in the Three Gorges Reservoirarea, China. Stochastic Environmental Research and Risk Assessment, 36(8): 2207-2228. https://doi.org/10.1007/s00477-021-02032-x Liu, Y., 2022. Research on Pre Loan Risk Control Based on Stacking Integration Method under Unbalanced Samples (Dissertation). Central China Normal University, Wuhan (in Chinese with English abstract). Meten, M., Bhandary, N. P., Yatabe, R., 2015. GIS-Based Frequency Ratio and Logistic Regression Modelling for Landslide Susceptibility Mapping of Debre Sina Area in Central Ethiopia. Journal of Mountain Science, 12(6): 1355-1372. https://doi.org/10.1007/s11629-015-3464-3 Moni, M., Sethi, I. P. S., Sethi, S. P. S., 1991. Natural Calamities Relief Management Software. IETE Technical Review, 8(2): 64-71. https://doi.org/10.1080/02564602.1991.11438716 Nian, T. K., Feng, Z. K., Yu, P. C., et al., 2013. Strength Behavior of Slip-Zone Soils of Landslide Subject to the Change of Water Content. Natural Hazards, 68(2): 711-721. https://doi.org/10.1007/s11069-013-0647-5 Pardeshi, S. D., Autade, S. E., Pardeshi, S. S., 2013. Landslide Hazard Assessment: Recent Trends and Techniques. Springer Plus, 2(1): 523. https://doi.org/10.1186/2193-1801-2-523 Pei, Z. W., Nian, T. K., Wu, H., et al., 2021. Research Progress on Emergency Treatment Techniques for Landslide Geological Hazards. Journal of Disaster Prevention and Mitigation Engineering, 41(6): 1382-1394 (in Chinese with English abstract). Pham, V. D., Nguyen, Q. H., Nguyen, H. D., et al., 2020. Convolutional Neural Network-Optimized Moth Flame Algorithm for Shallow Landslide Susceptible Analysis. IEEE Access, 8: 32727-32736. https://doi.org/10.1109/ACCESS.2020.2973415 Wang, C. Y., 2008. Study on the Relationship between Aspect and Slope Stability (Dissertation). Kunming University of Science and Technology, Kunming (in Chinese with English abstract). Wang, W. D., He, Z. L., Han, Z., et al., 2020. Mapping the Susceptibility to Landslides Based on the Deep Belief Network: A Case Study in Sichuan Province, China. Natural Hazards, 103(3): 3239-3261. https://doi.org/10.1007/s11069-020-04128-z Wang, Y., Fang, Z. C., Niu, R. Q., et al., 2021. Landslide Susceptibility Analysis Based on Deep Learning. Journal of Geo-Information Science, 23(12): 2244-2260 (in Chinese with English abstract). Wu, C., 2019. Landslide Susceptibility Based on Extreme Rainfall-Induced Landslide Inventories and the Following Landslide Evolution. Water, 11(12): 2609. https://doi.org/10.3390/w11122609 Wu, X. L., Yang, J. Y., Niu, R. Q., 2020. A Landslide Susceptibility Assessment Method Using SMOTE and Convolutional Neural Network. Geomatics and Information Science of Wuhan University, 45(8): 1223-1232 (in Chinese with English abstract). Yan, C. L., Zheng, D. F., Nian, T. K., et al., 2021. Fuzzy Bayesian Network Model Based on ANP and Its Application to Coastal Zone Geohazard Risk Assessment. Journal of Engineering Geology, 29(6): 1862-1868 (in Chinese with English abstract). Zhang, C. X., Yang, Q. K., Li, R., 2005. Advancement in Topographic Wetness Index and Its Application. Progress In Geography, 24(6): 116-123 (in Chinese with English abstract). doi: 10.3969/j.issn.1007-6301.2005.06.014 Zhang, K. X., Wu, X. L., Niu, R. Q., et al., 2017. The Assessment of Landslide Susceptibility Mapping Using Random Forest and Decision Tree Methods in the Three Gorges Reservoir Area, China. Environmental Earth Sciences, 76(11): 405. https://doi.org/10.1007/s12665-017-6731-5 Zhao, P. X., Masoumi, Z., Kalantari, M., et al., 2022. A GIS-Based Landslide Susceptibility Mapping and Variable Importance Analysis Using Artificial Intelligent Training-Based Methods. Remote Sensing, 14(1): 211. https://doi.org/10.3390/rs14010211 Zhou, X. T., Huang, F. M., Wu, W. C., et al., 2022. Regional Landslide Susceptibility Prediction Based on Negative Sample Selected by Coupling Information Value Method. Advanced Engineering Sciences, 54(3): 25-35 (in Chinese with English abstract). 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. doi: 10.3799/dqkx.2022.247 黄发明, 陈佳武, 唐志鹏, 等, 2021. 不同空间分辨率和训练测试集比例下的滑坡易发性预测不确定性. 岩石力学与工程学报, 40(6): 1155-1169. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX202106008.htm 黄发明, 殷坤龙, 蒋水华, 等, 2018. 基于聚类分析和支持向量机的滑坡易发性评价. 岩石力学与工程学报, 37(1): 156-167. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201801016.htm 黄武彪, 丁明涛, 王栋, 等, 2022. 基于层数自适应加权卷积神经网络的川藏交通廊道沿线滑坡易发性评价. 地球科学, 47(6): 2015-2030. 李文彬, 范宣梅, 黄发明, 等, 2021. 不同环境因子联接和预测模型的滑坡易发性建模不确定性. 地球科学, 46(10): 3777-3795. doi: 10.3799/dqkx.2021.042 刘允, 2022. 基于不平衡样本下Stacking集成方法的贷前风控研究(硕士学位论文). 武汉: 华中师范大学. 裴振伟, 年廷凯, 吴昊, 等, 2021. 滑坡地质灾害应急处置技术研究进展. 防灾减灾工程学报, 41(6): 1382-1394. https://www.cnki.com.cn/Article/CJFDTOTAL-DZXK202106028.htm 王朝阳, 2008. 坡向与斜坡稳定性的关系研究(硕士学位论文). 昆明: 昆明理工大学. 王毅, 方志策, 牛瑞卿, 等, 2021. 基于深度学习的滑坡灾害易发性分析. 地球信息科学学报, 23(12): 2244-2260. doi: 10.12082/dqxxkx.2021.210057 武雪玲, 杨经宇, 牛瑞卿, 2020. 一种结合SMOTE和卷积神经网络的滑坡易发性评价方法. 武汉大学学报(信息科学版), 45(8): 1223-1232. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202008013.htm 闫成林, 郑德凤, 年廷凯, 等, 2021. 基于ANP的模糊贝叶斯网络模型及其在海岸带地质灾害风险评价中的应用. 工程地质学报, 29(6): 1862-1868. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ202106021.htm 张彩霞, 杨勤科, 李锐, 2005. 基于DEM的地形湿度指数及其应用研究进展. 地理科学进展, 24(6): 116-123. doi: 10.3969/j.issn.1007-6301.2005.06.014 周晓亭, 黄发明, 吴伟成, 等, 2022. 基于耦合信息量法选择负样本的区域滑坡易发性预测. 工程科学与技术, 54(3): 25-35. https://www.cnki.com.cn/Article/CJFDTOTAL-SCLH202203003.htm -
点击查看大图
图(6) / 表(2)
计量
- 文章访问数: 480
- HTML全文浏览量: 160
- PDF下载量: 62
- 被引次数: 0
