Evaluation of Landslide Susceptibility Based on Layer Adaptive Weighted Convolutional Neural Network Model along Sichuan-Tibet Traffic Corridor
-
摘要: 开展铁路沿线滑坡易发性评价对川藏交通廊道工程建设及运维过程中的风险管理具有重要意义.提出一种层数自适应、通道加权的卷积神经网络(layer adaptive weighted convolutional neural network，LAW-CNN)，对川藏交通廊道沿线滑坡易发性进行评价.依据野外调查和影响因素分析筛选出影响滑坡发生的影响因子，绘制滑坡编目，构造用于易发性评价的实验数据集；针对卷积神经网络的权重初值、网络层数等超参数难以优化设置的问题，提出基于影响因子信息熵的通道加权方法和网络层数优选策略，通过多通道加权和层数自适应分类卷积的方式提出滑坡易发性制图的LAW-CNN架构；搜索最优LAW-CNN网络结构并训练网络参数，获取研究区滑坡发生概率并进行易发性分级评价.所提的LAW-CNN模型可以不同权重和不同深度挖掘影响因子的深层特征，实验结果表明，模型曲线下面积(area under curve，AUC)值为0.852 8，极高易发区滑坡点密度为1.251 9，均优于SVM(support vector machine)和CNN模型；川藏交通廊道沿线滑坡极高和高易发区主要集中在大江大河两侧以及横断山区.LAW-CNN模型可较好评价川藏交通廊道滑坡易发性，能够为川藏交通廊道的建设和灾害防治提供科学的依据.Abstract: It is of great significance for disaster risk management in the process of railway engineering construction, operation and maintenance to carry out precise landslide susceptibility assessment along the Sichuan-Tibet traffic corridor. In this paper, a layer adaptive weighted convolutional neural network (LAW-CNN) is proposed to evaluate the landslide susceptibility along the Sichuan-Tibet traffic corridor. According to the field investigation and influencing factor analysis, the influencing factors are selected, the landslide catalogue and the spatial database is constructed.To optimize the initial weight and the layer number of the CNN network, the channel weighted method and the network layer optimization strategy based on the influence factor information entropy are proposed, and the LAW-CNN architecture is constructed by multi-channel weighted convolution and multi-layer classification convolution. The optimal LAW-CNN structure is searched and the network parameters are trained to obtain the landslide occurrence probability in the study area, followed by a susceptibility classification evaluation.The proposed LAW-CNN model can fully represent the deep characteristics of the factor layers with different weights and depths.The experimental results show that the area under curve value of the proposed model is 0.852 8 and the landslide density in the very high susceptibility area is 1.251 9, which are better than the SVM and CNN models.The very high and high susceptibility areas are mainly concentrated on both sides of large rivers and the Hengduan Mountain Range.The LAW-CNN model can precisely assess landslide susceptibility, and then provide a scientific basis for the construction of the Sichuan-Tibet traffic corridor and disaster prevention.
-
图 2 川藏交通廊道沿线滑坡影响因子层
a.高程；b.坡度；c.坡向；d.曲率；e.平面曲率；f.剖面曲率；g.地面起伏度；h.地表粗糙度；i.TWI；j.NDVI；k.降雨量；l.岩性；m.距道路的距离；n.距河流的距离；o.距断层的距离
Fig. 2. Layers of landslide influencing factors along the Sichuan-Tibet traffic corridor
图 9 川藏交通廊道各段滑坡易发性统计图
Fig. 9. Statistics of landslide susceptibility in different sections of the Sichuan-Tibet traffic corridor
表 1 数据来源
Table 1. Data source
数据 来源 数据 来源 Landsat8 OLI影像 http://www.gscloud.cn 坡度 30 m SRTM DEM 30m SRTM DEM http://dwtkns.com/srtm30m/ 坡向 30 m SRTM DEM 岩性 http://geocloud.cgs.gov.cn 曲率 30 m SRTM DEM 道路 https://www.webmap.cn 平面曲率 30 m SRTM DEM 断层 http://geocloud.cgs.gov.cn 剖面曲率 30 m SRTM DEM 河流 https://www.webmap.cn 地表粗糙度 30 m SRTM DEM 降雨量 https://gpm.nasa.gov/ 地面起伏度 30 m SRTM DEM NDVI Landsat8 OLI影像 TWI 30 m SRTM DEM 
下载: 导出CSV
表 2 皮尔逊相关系数
Table 2. Pearson correlation coefficient
影响因子 高程 坡度 坡向 曲率 平面曲率 剖面曲率 距断层的距离 距河流的距离 距道路的距离 岩性 地表粗糙度 地面起伏度 NDVI TWI 降雨量 高程 1 0.109 8 0.013 3 0.015 1 -0.101 7 0.080 9 -0.105 1 0.186 2 0.297 3 0.193 5 0.020 5 0.066 6 -0.354 2 -0.118 6 -0.624 3 坡度 1 0.002 9 0.011 5 -0.481 5 0.167 6 -0.070 5 -0.109 8 0.062 6 0.116 9 0.788 2 0.903 4 0.026 3 -0.391 2 -0.140 9 坡向 1 0.004 2 0.005 8 -0.014 8 0.002 9 0.011 6 -0.002 1 -0.040 3 -0.000 5 -0.001 9 -0.110 6 -0.011 6 0.021 0 曲率 1 -0.003 5 -0.029 3 -0.004 1 0.009 2 -0.001 7 -0.001 5 0.063 4 0.044 0 -0.001 6 -0.333 7 0.002 9 平面曲率 1 0.073 3 0.073 9 0.084 5 -0.031 7 -0.057 3 -0.296 3 -0.391 0 -0.081 5 0.247 0 0.125 9 剖面曲率 1 -0.010 1 -0.000 8 0.070 0 0.069 8 0.103 3 0.185 7 0.007 5 -0.058 8 -0.069 9 距断层的距离 1 -0.060 8 -0.028 5 0.184 9 -0.037 2 -0.056 9 0.069 3 0.041 0 0.222 1 距河流的距离 1 0.166 0 0.028 4 -0.054 2 -0.082 2 -0.048 9 -0.008 8 0.027 5 距道路的距离 1 0.039 6 0.040 0 0.056 9 -0.142 5 -0.043 4 -0.049 7 岩性 1 0.073 4 0.103 0 -0.017 1 -0.036 6 -0.117 5 地表粗糙度 1 0.927 1 0.015 5 -0.275 9 -0.043 8 地面起伏度 1 0.024 4 -0.342 8 -0.092 7 NDVI 1 0.000 8 0.117 8 TWI 1 0.050 8 降雨量 1
下载: 导出CSV
表 3 影响因子的IGR值及权值
Table 3. Information gain ratios and weights
影响因子 信息熵 IGR W 高程 / 0.014 4 / 坡度 12.619 0 0.009 1 0.021 6 坡向 14.229 6 0.021 0 0.049 8 曲率 8.353 9 0.001 5 0.003 6 平面曲率 17.000 8 0.058 6 0.138 9 剖面曲率 17.002 0 0.058 7 0.139 2 距断层的距离 3.983 6 0.024 5 0.058 1 距河流的距离 7.129 6 0.032 6 0.077 3 距道路的距离 5.670 1 0.017 5 0.041 5 岩性 2.882 3 0.007 5 0.017 8 地表粗糙度 / 0.009 1 / 地面起伏度 / 0.005 4 / NDVI 16.735 4 0.058 7 0.139 2 TWI 15.233 9 0.033 6 0.079 7 降雨量 10.110 1 0.098 5 0.233 5
下载: 导出CSV
表 4 不同聚类个数下的AIC值
Table 4. AIC values under different cluster numbers
聚类个数 2 3 4 AIC值 21.794 6 14.538 8 16.859 1
下载: 导出CSV
表 5 统计分析
Table 5. Statistical analysis
易发性等级 SVM CNN LAW-CNN 分级栅格数(个) 分级占比(%) 分级栅格数(个) 分级占比(%) 分级栅格数(个) 分级占比(%) 极低易发区 47 987 600 17.40 76 258 529 27.66 93 129 820 33.78 低易发区 59 369 589 21.53 56 739 083 20.58 52 724 600 19.12 中等易发区 63 155 306 22.90 51 278 826 18.60 47 748 787 17.32 高易发区 59 097 511 21.43 49 266 609 17.87 46 530 453 16.88 极高易发区 46 123 198 16.73 42 190 157 15.30 35 589 544 12.91
下载: 导出CSV
-
[1] Akaike, H., 1978. A Bayesian Analysis of the Minimum AIC Procedure. Annals of the Institute of Statistical Mathematics, 30(1): 9-14. https://doi.org/10.1007/bf02480194 [2] 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 Naïve Bayes Tree for Landslide Susceptibility Modeling. Science of the Total Environment, 644: 1006-1018. https://doi.org/10.1016/j.scitotenv.2018.06.389 [3] Cui, P., Zou, Q., 2021. Evolution Law and Engineering Risk of Mountain Hazards in Sichuan-Tibet Traffic Corridor. Science Press, Beijing, 432(in Chinese). [4] Dou, J., Yunus, A. P., Merghadi, A., et al., 2020. Different Sampling Strategies for Predicting Landslide Susceptibilities are Deemed Less Consequential with Deep Learning. Science of the Total Environment, 720: 137320. https://doi.org/10.1016/j.scitotenv.2020.137320 [5] Ermini, L., Catani, F., Casagli, N., 2005. Artificial Neural Networks Applied to Landslide Susceptibility Assessment. Geomorphology, 66(1-4): 327-343. https://doi.org/10.1016/j.geomorph.2004.09.025 [6] Guo, C. B., Wu, R. A., Jiang L. W., et al., 2021. Typical Geohazards and Engineering Geological Problems along the Ya'an-Linzhi Section of the Sichuan-Tibet Railway, China. Geoscience, 35(1): 1-17(in Chinese with English abstract). [7] Guo, C. B., Zhang, Y. S., Jiang, L. W., et al., 2017. Discussion on the Environmental and Engineering Geological Problems along the Sichuan-Tibet Railway and Its Adjacent Area. Geoscience, 31(5): 877-889(in Chinese with English abstract). [8] Guo, Z. Z., Yin, K. L., Fu, S., et al., 2019. Evaluation of Landslide Susceptibility Based on GIS and WOE-BP Model. Earth Science, 44(12): 4299-4312(in Chinese with English abstract). [9] Hanley, J. A., McNeil, B. J., 1982. The Meaning and Use of the Area under a Receiver Operating Characteristic (ROC) Curve. Radiology, 143(1): 29-36. https://doi.org/10.1148/radiology.143.1.7063747 [10] Hu, R. L., Fan, L. F., Wang, S. S., et al., 2013. Theory and Method for Landslide Risk Assessment—Current Status and Future Development. Journal of Engineering Geology, 21(1): 76-84(in Chinese with English abstract). [11] Hu, X. C., Zhu, C. Y., Chen, Y., 2021. Research and Analysis of Deep Convolution Neural Network Model. Information Technology and Informatization, (4): 107-110(in Chinese with English abstract). [12] Krizhevsky, A., Sutskever, I., Hinton, G. E., 2017. ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60(6): 84-90. https://doi.org/10.1145/3065386 [13] Lan, H. X., Wu, F. Q., Zhou, C. H., et al, 2002. Analysis on Susceptibility of GIS Based Landslide Triggering Factors in Yunnan Xiaojiang Watershed. Chinese Journal of Rock Mechanics and Engineering, 21(10): 1500-1506(in Chinese with English abstract). [14] Li, L. P., Lan, H. X., Guo, C. B., et al., 2017. A Modified Frequency Ratio Method for Landslide Susceptibility Assessment. Landslides, 14(2): 727-741. https://doi.org/10.1007/s10346-016-0771-x [15] Li, L. P., Lan, H. X., Guo, C. B., et al., 2017. Geohazard Susceptibility Assessment along the Sichuan-Tibet Railway and Its Adjacent Area Using an Improved Frequency Ratio Method. Geoscience, 31(5): 911-929(in Chinese with English abstract). [16] Li, T. F., Zhao, Z. B., Sun, C., et al., 2020. Adaptive Channel Weighted CNN with Multisensor Fusion for Condition Monitoring of Helicopter Transmission System. IEEE Sensors Journal, 20(15): 8364-8373. https://doi.org/10.1109/jsen.2020.2980596 [17] Li, X. Z., Cui, Y., Zhang, X. G., et al., 2019. Types, Characteristics and Spatial Distribution Law of Landslides and Collapses along Sichuan-Tibet Railway. Journal of Engineering Geology, 27(Suppl. 1): 110-120(in Chinese with English abstract). [18] Lü, H. M., Shen, J. S., Arulrajah, A., 2018. Assessment of Geohazards and Preventative Countermeasures Using AHP Incorporated with GIS in Lanzhou, China. Sustainability, 10(2): 304. . https://doi.org/10.3390/su10020304 [19] Peng, J. B., Cui, P., Zhuang, J. Q., 2020. Challenges to Engineering Geology of Sichuan-Tibet Railway. Chinese Journal of Rock Mechanics and Engineering, 39(12): 2377-2389(in Chinese with English abstract). [20] Pham, B. T., Prakash, I., Dou, J., et al., 2020. A Novel Hybrid Approach of Landslide Susceptibility Modelling Using Rotation Forest Ensemble and Different Base Classifiers. Geocarto International, 35(12): 1267-1292. https://doi.org/10.1080/10106049.2018.1559885. [21] Pourghasemi, H. R., Yansari, Z. T., Panagos, P., et al., 2018. Analysis and Evaluation of Landslide Susceptibility: A Review on Articles Published during 2005-2016 (Periods of 2005-2012 and 2013-2016). Arabian Journal of Geosciences, 11(9). https://doi.org/10.1007/s12517-018-3531-5 [22] 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 [23] Sameen, M. I., Pradhan, B., Lee, S., 2020. Application of Convolutional Neural Networks Featuring Bayesian Optimization for Landslide Susceptibility Assessment. Catena, 186: 104249. https://doi.org/10.1016/j.catena.2019.104249 [24] Sun, D. L., Wen, H. J., Wang, D. Z., et al., 2020. A Random Forest Model of Landslide Susceptibility Mapping Based on Hyperparameter Optimization Using Bayes Algorithm. Geomorphology, 362: 107201. https://doi.org/10.1016/j.geomorph.2020.107201 [25] 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: 105972. https://doi.org/10.1016/j.enggeo.2020.105972 [26] Szegedy, C., Liu, W., Jia, Y. Q., et al., 2015. Going Deeper with Convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Boston, MA, 1-9. https://doi.org/10.1109/cvpr.2015.7298594 [27] Tan, L., Chen, G., Wang, S. Y., et al., 2014. Landslide Susceptibility Mapping Based on Logistic Regression and Support Vector Machine. Journal of Engineering Geology, 22(1): 56-63(in Chinese with English abstract). [28] Tang, X. N., 2019. Evaluation of Landslide Susceptibility in Lüliang City Based on Convolutional Neural Network and Comprehensive Index Model (Dissertation). Taiyuan University of Technology, Taiyuan(in Chinese with English abstract). [29] Thi Ngo, P. T., Panahi, M., Khosravi, K., et al., 2021. Evaluation of Deep Learning Algorithms for National Scale Landslide Susceptibility Mapping of Iran. Geoscience Frontiers, 12(2): 505-519. https://doi.org/10.1016/j.gsf.2020.06.013 [30] Tien Bui, D., Ho, T. C., Pradhan, B., et al., 2016. GIS-Based Modeling of Rainfall-Induced Landslides Using Data Mining-Based Functional Trees Classifier with AdaBoost, Bagging, and MultiBoost Ensemble Frameworks. Environmental Earth Sciences, 75(14): 1-22. https://doi.org/10.1007/s12665-016-5919-4 [31] Wang, H. J., Zhang, L. M., Luo, H. Y., et al., 2021. AI-Powered Landslide Susceptibility Assessment in Hong Kong. Engineering Geology, 288: 106103. https://doi.org/10.1016/j.enggeo.2021.106103 [32] Wang, X. H., 2020. Landslides Susceptibility Evaluation in Loess Mountain: A Case Study of Shanxi Linxian-Shaanxi Qingjian Area (Dissertation). Xi'an University of Science and Technology, Xi'an(in Chinese with English abstract). [33] Wang, Y., Fang, Z. C., Hong, H. Y., 2019. Comparison of Convolutional Neural Networks for Landslide Susceptibility Mapping in Yanshan County, China. Science of the Total Environment, 666: 975-993. https://doi.org/10.1016/j.scitotenv.2019.02.263 [34] Wang, Y., Fang, Z. C., Wang, M., et al., 2020. Comparative Study of Landslide Susceptibility Mapping with Different Recurrent Neural Networks. Computers & Geosciences, 138: 104445. https://doi.org/10.1016/j.cageo.2020.104445 [35] Yan, H., 2018. Research on Image Classification Algorithms Based on Convolutional Neural Network (Dissertation). Northwest University, Xi'an(in Chinese with English abstract). [36] Yang, X., Liu, R., Yang, M., et al., 2021. Incorporating Landslide Spatial Information and Correlated Features among Conditioning Factors for Landslide Susceptibility Mapping. Remote Sensing, 13(11): 2166. https://doi.org/10.3390/rs13112166 [37] Ye, Z., Yu, J. B., 2021. Feature Extraction of Gearbox Vibration Signals Based on Multi-Channels Weighted Convolutional Neural Network. Journal of Mechanical Engineering, 57(1): 110-120(in Chinese with English abstract). doi: 10.3901/JME.2021.01.110 [38] Yi, Y. N., Zhang, Z. J., Zhang, W. C., et al., 2020. Landslide Susceptibility Mapping Using Multiscale Sampling Strategy and Convolutional Neural Network: A Case Study in Jiuzhaigou Region. Catena, 195: 104851. https://doi.org/10.1016/j.catena.2020.104851 [39] Yu, L. B., Cao, Y., Zhou, C., et al., 2019. Landslide Susceptibility Mapping Combining Information Gain Ratio and Support Vector Machines: A Case Study from Wushan Segment in the Three Gorges Reservoir Area, China. Applied Sciences, 9(22): 4756. https://doi.org/10.3390/app9224756 [40] Yu, X. Y., 2016. Study on the Landslide Susceptibility Evaluation Method Based on Multi-Source Data and Multi-Scale Analysis (Dissertation). China University of Geosciences, Wuhan(in Chinese with English abstract). [41] Zêzere, J. L., Pereira, S., Melo, R., et al., 2017. Mapping Landslide Susceptibility Using Data-Driven Methods. Science of the Total Environment, 589: 250-267. https://doi.org/10.1016/j.scitotenv.2017.02.188 [42] Zhang, C. L., Li, Z. H., Yu, C., et al., 2021. Landslide Detection of the Jinsha River Region Using GACOS Assisted InSAR Stacking. Geomatics and Information Science of Wuhan University, 46(11): 1649-1657(in Chinese with English abstract). [43] Zhang, W., Bai, S. B., Wang, J., 2010. Regional Landslide Susceptibility Assessments Based Expert Experience: A Case Study of Gaopingpu Reservoir Area, Pingwu County, Sichuan Province. Journal of Geological Hazards and Environment Preservation, 21(4): 20-23, 37(in Chinese with English abstract). [44] Zhang, Y. L., Dang, Y., He, P. A., 2005. Quantitative Analysis of the Relationship of Biology Species Using Pearson Correlation Coefficient. Computer Engineering and Applications, 41 (33): 79-82, 99(in Chinese with English abstract). [45] Zhang, Y. X., Lan, H. X., Li, L. P., et al., 2020. Optimizing the Frequency Ratio Method for Landslide Susceptibility Assessment: A Case Study of the Caiyuan Basin in the Southeast Mountainous Area of China. Journal of Mountain Science, 17(2): 340-357. https://doi.org/10.1007/s11629-019-5702-6 [46] Zhou, C., Yin, K. L., Cao, Y., et al., 2020. Landslide Susceptibility Assessment by Applying the Coupling Method of Radial Basis Neural Network and Adaboost: A Case Study from the Three Gorges Reservoir Area. Earth Science, 45(6): 1865-1876(in Chinese with English abstract). [47] 崔鹏, 邹强, 2021. 川藏交通廊道山地灾害演化规律与工程风险. 北京: 科学出版社, 432. [48] 郭长宝, 吴瑞安, 蒋良文, 等, 2021. 川藏交通廊道雅安-林芝段典型地质灾害与工程地质问题. 现代地质, 35(1): 1-17. [49] 郭长宝, 张永双, 蒋良文, 等, 2017. 川藏交通廊道沿线及邻区环境工程地质问题概论. 现代地质, 31(5): 877-889. doi: 10.3969/j.issn.1000-8527.2017.05.001 [50] 郭子正, 殷坤龙, 付圣, 等, 2019. 基于GIS与WOE-BP模型的滑坡易发性评价. 地球科学, 44(12): 4299-4312. doi: 10.3799/dqkx.2018.555 [51] 胡瑞林, 范林峰, 王珊珊, 等, 2013. 滑坡风险评价的理论与方法研究. 工程地质学报, 21(1): 76-84. doi: 10.3969/j.issn.1004-9665.2013.01.009 [52] 胡小春, 朱成宇, 陈燕, 2021. 深度卷积神经网络模型的研究分析. 信息技术与信息化, (4): 107-110. doi: 10.3969/j.issn.1672-9528.2021.04.032 [53] 兰恒星, 伍法权, 周成虎, 等, 2002. 基于GIS的云南小江流域滑坡因子敏感性分析. 岩石力学与工程学报, 21(10): 1500-1506. doi: 10.3321/j.issn:1000-6915.2002.10.014 [54] 李郎平, 兰恒星, 郭长宝, 等, 2017. 基于改进频率比法的川藏交通廊道沿线及邻区地质灾害易发性分区评价. 现代地质, 31(5): 911-929. doi: 10.3969/j.issn.1000-8527.2017.05.004 [55] 李秀珍, 崔云, 张小刚, 等, 2019. 川藏交通廊道全线崩滑灾害类型、特征及其空间分布发育规律. 工程地质学报, 27(增刊1): 110-120. [56] 彭建兵, 崔鹏, 庄建琦, 2020. 川藏交通廊道对工程地质提出的挑战. 岩石力学与工程学报, 39(12): 2377-2389. [57] 谭龙, 陈冠, 王思源, 等, 2014. 逻辑回归与支持向量机模型在滑坡敏感性评价中的应用. 工程地质学报, 22(1): 56-63. doi: 10.3969/j.issn.1004-9665.2014.01.008 [58] 唐晓娜, 2019. 基于卷积神经网络和综合指数模型的吕梁市滑坡灾害易发性评价(硕士学位论文). 太原: 太原理工大学. [59] 王小浩, 2020. 黄土山区滑坡敏感性评价研究(硕士学位论文). 西安: 西安科技大学. [60] 严寒, 2018. 基于卷积神经网络的图像分类算法研究(硕士学位论文). 西安: 西北大学. [61] 叶壮, 余建波, 2021. 基于多通道加权卷积神经网络的齿轮箱振动信号特征提取. 机械工程学报, 57(1): 110-120. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202101012.htm [62] 于宪煜, 2016. 基于多源数据和多尺度分析的滑坡易发性评价方法研究(博士学位论文). 武汉: 中国地质大学. [63] 张成龙, 李振洪, 余琛, 等, 2021. 利用GACOS辅助下InSAR Stacking对金沙江流域进行滑坡监测. 武汉大学学报(信息科学版), 46(11): 1649-1657. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202111006.htm [64] 张文, 白世彪, 王建, 2010. 基于专家经验值的滑坡易发性评价——以四川平武高坪铺库区为例. 地质灾害与环境保护, 21(4): 20-23, 37. doi: 10.3969/j.issn.1006-4362.2010.04.003 [65] 张宇镭, 党琰, 贺平安, 2005. 利用Pearson相关系数定量分析生物亲缘关系. 计算机工程与应用, 41(33): 79-82, 99. doi: 10.3321/j.issn:1002-8331.2005.33.026 [66] 周超, 殷坤龙, 曹颖, 等, 2020. 基于集成学习与径向基神经网络耦合模型的三峡库区滑坡易发性评价. 地球科学, 45(6): 1865-1876. doi: 10.3799/dqkx.2020.071 -
点击查看大图
图(10) / 表(5)
计量
- 文章访问数: 460
- HTML全文浏览量: 277
- PDF下载量: 85
- 被引次数: 0
