[1]张洪吉,赵铮,陈建华,等.面向滑坡危险性评价的深度一维卷积神经网络方法——以四川省芦山县为例[J].自然灾害学报,2021,30(03):191-198.[doi:10.13577/j.jnd.2021.0321]
 ZHANG Hongji,ZHAO Zheng,CHEN Jianhua,et al.A deep one-dimensional convolutional neural network method for landslide risk assessment: A case study in Lushan, Sichuan, China[J].,2021,30(03):191-198.[doi:10.13577/j.jnd.2021.0321]
点击复制

面向滑坡危险性评价的深度一维卷积神经网络方法——以四川省芦山县为例
分享到:

《自然灾害学报》[ISSN:/CN:23-1324/X]

卷:
30
期数:
2021年03期
页码:
191-198
栏目:
出版日期:
2021-06-28

文章信息/Info

Title:
A deep one-dimensional convolutional neural network method for landslide risk assessment: A case study in Lushan, Sichuan, China
作者:
张洪吉1 赵铮2 陈建华2 甘先霞2 谢华伟2 谭小琴1
1. 四川省自然资源科学研究院, 四川 成都 610015;
2. 成都理工大学 地球物理学院, 四川 成都 610059
Author(s):
ZHANG Hongji1 ZHAO Zheng2 CHEN Jianhua2 GAN Xianxia2 XIE Huawei2 TAN Xiaoqin1
1. Institute of Natural Resource Sciences of Sichuan Province, Chengdu 610015, China;
2. College of Geophysics, Chengdu University of Technology, Chengdu 610059, China
关键词:
滑坡灾害卷积神经网络支持向量机滑坡危险性评价机器学习
Keywords:
landslide disasterconvolutional neural networksupport vector machinelandslide risk assessmentmachine learning
分类号:
TU4;X4;X9
DOI:
10.13577/j.jnd.2021.0321
摘要:
滑坡灾害威胁着人类生命财产安全。因此,准确地评价滑坡危险性对于灾害分析至关重要。目前常见的机器学习方法不能提取更深层次的数据特征,难以获得高质量的滑坡危险性评价图。因此,论文提出一种面向滑坡危险性评价的深度一维卷积神经网络方法,以期利用卷积神经网络强大的表征学习能力获得更高精度的评价结果。以滑坡灾害多发的四川省芦山县为例,选择2016年346个历史滑坡数据用于模型的训练和验证。为了验证模型的有效性和精度,实验将支持向量机模型、信息量模型与一维卷积神经网络模型进行对比分析,并将其应用于芦山县全区滑坡危险性评价。结果上,一维卷积神经网络和支持向量机的总体精度分别为0.9015和0.842,而一维卷积神经网络、支持向量机、信息量模型的AUC值分别为0.888、0.876、0.818。结果表明:一维卷积神经网络模型精度较高,在数据拟合度和评价效果上优于支持向量机模型、信息量模型,可以有效地应用于滑坡危险性评价。
Abstract:
Landslide disasters threaten the safety of human life and properties. It is important to accurately assess the risk of regional landslides. At present, common machine learning methods cannot extract deeper data features and obtain higher precision landslide hazard assessment maps. Therefore, this paper proposes a deep one-dimensional convolutional neural network method for landslide risk assessment, in order to extract deeper features and obtain higher precision evaluation results by based on its powerful learning ability. Taking Lushan, Sichuan, China as an example, 346 historical landslide pionts of Lushan in 2016 were selected for model training and verification. In order to verify the validity and precision of the model, the support vector machine, the information value method and the proposed convolutional neural network model were compared in the experiments. The overall accuracies of the convolutional neural network and the support vector machine are 0.9015 and 0.842. The AUC values of the one-dimensional convolutional neural network, support vector machine, and information value model are 0.888, 0.876, and 0.818, respectively, The results show that the proposed convolutional neural network model has a higher accuracy and is superior to the support vector machine and the information value method in data fitting ability and evaluation effect, and can be effectively applied to the regional landslide risk evaluation.

参考文献/References:

[1] Dou J, Yunus A P, Bui D T, et al. Improved landslide assessment using support vector machine with bagging, boosting, and stacking ensemble machine learning framework in a mountainous watershed, Japan[J]. Landslides, 2020, 17(3):641-658.
[2] 黄发明, 殷坤龙, 蒋水华, 等. 基于聚类分析和支持向量机的滑坡易发性评价[J]. 岩石力学与工程学报, 2018, 37(1):156-167. HUANG Faming, YIN Kunlong, JIANG Shuihua, et al. Landslide susceptibility assessment based on clustering analysis and support vector machine[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(1):156-167. (in Chinese)
[3] 王丽丽, 苏程, 冯存均, 等. 数据驱动自适应更新的斜坡地质灾害易发性评价系统[J]. 岩石力学与工程学报, 2016, 35(增1):3076-3083. WANG Lili, SU Cheng, FENG Cunjun, et al. A data driven self-adaptive update landslide susceptibility assessment system[J]. Chinese Journal of Rock Mechanics and Engineering, 2016, 35(S1):3076-3083. (in Chinese)
[4] 马志江, 陈汉林, 杨树锋. 基于支持向量机理论的滑坡灾害预测-以浙江庆元地区为例[J]. 浙江大学学报(理学版), 2003, 30(5):592. MA Zhijiang, CHEN Hanlin, YANG Shufeng. Prediction of landslide hazard based on support vector machine theory[J].Journal of Zhejiang University(Sciences Edition), 2003, 30(5):592. (in Chinese)
[5] 朱良峰, 吴信才, 殷坤龙, 等. 基于信息量模型的中国滑坡灾害风险区划研究[J]. 地球科学与环境学报, 2004, 26(3):52-56. ZHU Liangfeng, WU Xincai, YIN Kunlong, et al. Risk zonation of landslide in China based on information content model[J]. Journal of Earth Science and Enivronmental, 2004, 26(3):52-56. (in Chinese)
[6] 李文彦, 王喜乐. 频率比与信息量模型在黄土沟壑区滑坡易发性评价中的应用与比较[J]. 自然灾害学报, 2020, 29(4):213-220. LI Wenyan, WANG Xile. Application and comparison of frequency ratio and information value model for evaluating landslide susceptibility of loess gully region[J].Journal of Natural Disasters, 2020, 29(4):213-220. (in Chinese)
[7] 张向营, 张春山, 孟华君, 等. 基于Random Forest和AHP的贵德县北部山区滑坡危险性评价[J]. 水文地质工程地质, 2018, 45(4):142-149. ZHANG Xiangying, ZHANG Chunshan, MENG Huajun, et al. Landslide hazard evaluation in the northern mountainous area of Guide County based on Random Forest and AHP[J]. Hydrogeology & Engineering Geology, 2018, 45(4):142-149. (in Chinese)
[8] Saito H, Nakayama D, Matsuyama H. Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence:The Akaishi Mountains, Japan[J]. Geomorphology, 2009, 109(3-4):108-121.
[9] 王芳, 殷坤龙, 桂蕾, 等. 不同日降雨工况下万州区滑坡灾害危险性分析[J]. 地质科技情报, 2018, 37(1):190-195,203. WANG Fang, YIN Kunlong, GUI Lei, et al. Landslide hazard analysis under different daily rainfall conditions in Wanzhou district[J]. Geological Science and Technology Information, 2018, 37(1):190-195,203. (in Chinese)
[10] 郭子正, 殷坤龙, 付圣, 等. 基于GIS与WOE-BP模型的滑坡易发性评价[J]. 地球科学, 2019, 44(12):4299-4312. GUO Zizheng, YIN Kunlong, FU Sheng, et al. Evaluation of landslide susceptibility based on GIS and WOE-BP model[J]. Earth Science, 2019, 44(12):4299-4312. (in Chinese)
[11] 邱海军, 曹明明, 刘闻, 等. 基于三种不同模型的区域滑坡灾害敏感性评价及结果检验研究[J]. 地理科学, 2014, 34(1):110-115. QIU Haijun, CAO Mingming, LIU Wen, et al. The Susceptibility Assessment of landslide and its calibration of the models based on three different models[J]. Scientia Geographica Sinica, 2014, 34(1):110-115. (in Chinese)
[12] 郭天颂, 张菊清, 韩煜, 等. 基于粒子群优化支持向量机的延长县滑坡易发性评价[J]. 地质科技情报, 2019, 38(3):236-243. GUO Tiansong, ZHANG Juqing, HAN Yu, et al. Evaluation of landslide susceptibility in Yanchang County based on particle swarm optimization-based support vector machine[J].Geological Science and Technology Information, 2019, 38(3):236-243. (in Chinese)
[13] Andrieu C, De Freitas N, Doucet A, et al. An introduction to MCMC for machine learning[J]. Machine Learning, 2003, 50:5-43.
[14] Mellouli D, Hamdani T M, Sanchezmedina J J, et al. Morphological convolutional neural network architecture for digit recognition[J]. IEEE Transactions on Neural Networks, 2019, 30(9):2876-2885.
[15] 张哲晗, 方薇, 杜丽丽, 等. 基于编码-解码卷积神经网络的遥感图像语义分割[J]. 光学学报, 2020, 40(3):31-001. ZHANG Zhehan, FANG Wei, DU Lili, et al. Semantic segmentation of remote sensing image based on encoder-decoder convolutional neural network[J]. Acta Optica Sinica, 2020, 40(3):31-001. (in Chinese)
[16] 叶发茂, 董萌, 罗威, 等. 基于卷积神经网络和重排序的农业遥感图像检索[J]. 农业工程学报, 2019, 35(15):138-145. YE Famao, DONG Meng, LUO Wei, et al. Agricultural remote sensing image retrieval based on convolutional neural network and reranking[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(15):138-145. (in Chinese)
[17] Yang X, Ye Y, Li X, et al. Hyperspectral image classification with deep learning models[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(99):5408-5423.
[18] Wang Y, Fang Z, Hong H. Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China[J]. Science of the Total Environment, 2019, 666(20):975-993.
[19] 张倩荧, 王俊英, 雷冬冬.