State recognition method of hydrodynamic pressure-driven landslides based on a generative adversarial network
-
摘要:
动水驱动型滑坡状态识别能更有效地辅助分析滑坡形变规律, 实现滑坡状态的准确识别对深入展开动水驱动型滑坡状态研究具有重要意义。针对目前动水驱动型滑坡突变状态研究较少, 难以获得相关特征, 从而导致状态识别性能不佳的问题, 提出了一种应用于动水驱动型滑坡状态识别的生成对抗网络学习方法。本方法通过构建滑坡状态监测数据矩阵, 依据少量数据样本设计合理的生成器网络完成对滑坡状态的数据扩增并设计判别器网络实现扩增数据的筛选, 通过对抗生成网络实现对滑坡状态的分类, 达到滑坡状态识别的目的。以三峡库区白水河滑坡为研究对象, 将降雨、库水位、深部位移和地表位移等多源监测数据进行了规范化处理, 设计生成器网络和对抗器网络完成了对滑坡状态数据的扩增, 设计滑坡状态识别生成对抗网络完成了对滑坡状态的分类和识别。结果表明, 生成对抗网络对滑坡状态识别具有较高的准确率。研究结果证实本方法能够对目标区域内的动水驱动型滑坡状态进行准确识别和分类, 可直接应用于工程实际。
Abstract:Identifying the states of hydrodynamic pressure-driven landslides can more effectively assist in the analysis of the landslide deformation law, and accurately identifying the landslide state is of great significance for the in-depth study of the hydrodynamic pressure-driven landslide state. Aiming at the problem that there are few abrupt states of hydrodynamic pressure-driven landslides, it is difficult to obtain relevant features, which leads to poor state recognition performance, and a generative adversarial network learning method for landslide state recognition is proposed.In this method, the landslide state monitoring data matrix is constructed, a reasonable generator network is designed based on a small number of data samples to complete the data amplification of the landslide states, and the discriminator network is designed to realize the screening of the amplified data, and the classifying landslide states being realized through the confrontation generation network to achieve the purpose of landslide status identification. Taking the Baishuihe landslide in the Three Gorges Reservoir area as the research object, multisource monitoring data such as rainfall, reservoir water level, deep displacement, and surface displacement are normalized. The states recognition generative adversarial network completes the classification and identification of the landslide state. The results show that the generative adversarial network has high accuracy for landslide state recognition. The research method in this paper can accurately identify and classify the landslide state in the target area.
-
-
[1] 谭建民, 韩会卿, 伏永朋. 库水位升降条件下滑坡的稳定性极小状态: 以三峡库区为例[J]. 工程勘察, 2012, 40(4): 42-46. https://www.cnki.com.cn/Article/CJFDTOTAL-GCKC201204011.htmTan J M, Han H Q, Fu Y P. Lowest stability state of landslides under rising and descending of reservoir water level: A case study on Three Gorges area[J]. Geotechnical Investigation & Surveying, 2012, 40(4): 42-46(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-GCKC201204011.htm [2] 焦朋朋, 陈洪凯, 张金浩, 等. 三峡库区消落带滑坡灾害引发生态环境问题的研究进展[J]. 重庆师范大学学报: 自然科学版, 2022, 39(2): 46-55. https://www.cnki.com.cn/Article/CJFDTOTAL-CQSF202202007.htmJiao P P, Chen H K, Zhang J H, et al. Research progress on ecological environment problems caused by landslides in water-level-fluctuating zone of Three Gorges Reservoir area[J]. Journal of Chongqing Normal University: Natural Science, 2022, 39(2): 46-55(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-CQSF202202007.htm [3] 唐军峰, 唐雪梅, 肖鹏, 等. 库水位升降与降雨作用下大型滑坡体渗流稳定性分析[J]. 地质科技通报, 2021, 40(4): 153-161. doi: 10.19509/j.cnki.dzkq.2021.0409Tang J F, Tang X M, Xiao P, et al. Analysis of seepage stability of large-scale landslide under water-level fluctuation and rainfall[J]. Bulletin of Geological Science and Technology, 2021, 40(4): 153-161(in Chinese with English abstract). doi: 10.19509/j.cnki.dzkq.2021.0409 [4] 许强. 滑坡的变形破坏行为与内在机理[J]. 工程地质学报, 2012, 20(2): 145-151. doi: 10.3969/j.issn.1004-9665.2012.02.001Xu Q. Theoretical studies on prediction of landslides using slope deformation process data[J]. Journal of Engineering Geology, 2012, 20(2): 145-151(in Chinese with English abstract). doi: 10.3969/j.issn.1004-9665.2012.02.001 [5] 易庆林, 张明玉, 文凯. 三峡库区白水河滑坡变形特征及影响因素的阶段分析[J]. 三峡大学学报: 自然科学版, 2017, 39(1): 38-42. https://www.cnki.com.cn/Article/CJFDTOTAL-WHYC201701007.htmYi Q L, Zhang M Y, Wen K. Periodic analysis of deformation characteristics and influential factors of Baishuihe landslide in Three Gorges Reservoir area[J]. Journal of China Three Gorges University: Natural Sciences, 2017, 39(1): 38-42(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-WHYC201701007.htm [6] 杨登芳, 胡新丽, 徐楚, 等. 基于物理模型试验的多层滑带滑坡变形演化特征[J]. 地质科技通报, 2022, 41(2): 300-308. doi: 10.19509/j.cnki.dzkq.2021.0069Yang D F, Hu X L, Xu C, et al. Deformation, and evolution characteristics of landslides with multiple sliding zones based on physical model test[J]. Bulletin of Geological Science and Technology, 2022, 41(2): 300-308(in Chinese with English abstract). doi: 10.19509/j.cnki.dzkq.2021.0069 [7] 刘勇, 秦志萌, 刘曼. 基于状态划分的滑坡位移预测方法研究[J]. 地质科技情报, 2018, 37(1): 184-189. doi: 10.19509/j.cnki.dzkq.2018.0125Liu Y, Qin Z M, Liu M. Landslide displacement prediction method based on state division[J]. Geological Science and Technology Information, 2018, 37(1): 184-189(in Chinese with English abstract). doi: 10.19509/j.cnki.dzkq.2018.0125 [8] 刘勇, 胡宝丹, 陈喆. 滑坡监测点多信息相似性度量方法研究[J]. 岩土力学, 2019, 40(10): 4001-4010. doi: 10.16285/j.rsm.2018.2186Liu Y, Hu B D, Chen Z. A similarity measurement method for multiple information data of landslide[J]. Rock and Soil Mechanics, 2019, 40(10): 4001-4010(in Chinese with English abstract). doi: 10.16285/j.rsm.2018.2186 [9] 张德成. 滑坡预测预报研究[D]. 昆明: 昆明理工大学, 2015.Zhang D C. Research on landslide prediction and forecast[D]. Kunming: Kunming University of Science and Technology, 2015. [10] 向家松, 文宝萍, 陈明. 结构复杂滑坡活动对库水位变化的响应特征: 以三峡库区柴湾滑坡为例[J]. 水文地质工程地质, 2017, 44(4): 71-77. https://www.cnki.com.cn/Article/CJFDTOTAL-SWDG201704011.htmXiang J S, Wen B P, Chen M. Activity response of a landslide with complex structure to fluctuation of reservoir water level: A case study of the Chaiwan landslide in the Three Gorges Reservoir[J]. Hydrogeology & Engineering Geology, 2017, 44(4): 71-77(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-SWDG201704011.htm [11] 胡新丽, 唐辉明, 李长冬. 基于参数反演的保扎滑坡变形破坏机理研究[J]. 工程地质学报, 2011, 19(6): 795-801. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ201106000.htmHu X L, Tang H M, Li C D. Deformation mechanism of Baozha landslide with parametric back analysis[J]. Journal of Engineering Geology, 2011, 19(6): 795-801(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ201106000.htm [12] 邬爱清, 丁秀丽, 李会中. 非连续变形分析方法模拟千将坪滑坡启动与滑坡全过程[J]. 岩石力学与工程学报, 2006, 25(7): 1297-1303. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX200607000.htmWu A Q, Ding X L, Li H Z. Numerical simulation of startup and whole failure process of Qianjiangping landslide using discontinuous deformation analysis method[J]. Chinese Journal of Rock Mechanics and Engineering, 2006, 25(7): 1297-1303(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX200607000.htm [13] Qi S W, Yan F Z, Wang S J, et al. Characteristics, mechanism and development tendency of deformation of Maoping landslide after commission of Geheyan Reservoir on the Qingjiang River, Hubei Province, China[J]. Engineering Geology, 2006, 86(1): 37-51. [14] Xie M L, Zheng W H. Landslide evolution assessment based on InSAR and real-time monitoring of a large reactivated landslide, Wenchuan, China[J]. Engineering Geology, 2020, 277(10): 57-81. [15] Long J J, Li C D, Liu Y, et al. A multi-feature fusion transfer learning method for displacement prediction of rainfall reservoir-induced landslide with step-like deformation characteristics[J]. Engineering Geology, 2022, 297(10): 64-94. [16] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. Conference on Neural Information Processing Systems, 2014, 3(1): 2672-2680. [17] 陈阳, 王怀彬. 基于生成对抗网络的网络入侵检测系统[J]. 天津理工大学学报, 2021, 37(3): 25-29. https://www.cnki.com.cn/Article/CJFDTOTAL-TEAR202103005.htmChen Y, Wang H B. Network intrusion detection system based on generative adversarial networks[J]. Journal of Tianjin University of Technology, 2021, 37(3): 25-29(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-TEAR202103005.htm [18] He Z, Liu H, Wang Y W, et al. Generative adversarial networks-based semi-supervised learning for hyperspectral image classification[J]. Remote Sensing, 2017, 9(10): 1-7. [19] 徐峰, 范春菊, 徐勋建, 等. 基于变分模态分解和AMPSO-SVM耦合模型的滑坡位移预测[J]. 上海交通大学学报, 2018, 52(10): 1388-1395. https://www.cnki.com.cn/Article/CJFDTOTAL-SHJT201810031.htmXu F, Fan C J, Xu X J, et al. Displacement prediction of landslide based on variational mode decomposition and AMPSO-SVM coupling model[J]. Journal of Shanghai Jiaotong University, 2018, 52(10): 1388-1395(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-SHJT201810031.htm [20] 鲁涛. 范家坪、白水河滑坡形成机理及后期演化趋势预测[D]. 湖北宜昌: 山峡大学, 2012.Lu T. Study of formation mechanism and later trend prediction of Fanjiaping landslide and Baishuihe landslide[D]. Yichang, Hubei: China Three Gorges University, 2012(in Chinese with English abstract). [21] 覃瀚萱, 桂蕾, 余玉婷, 等. 基于滑坡灾害预警分级的应急处置措施[J]. 地质科技通报, 2021, 40(4): 187-195. doi: 10.19509/j.cnki.dzkq.2021.0412Qin H X, Gui L, Yu Y T, et al. Emergency measures based on early warning classification of landslide[J]. Bulletin of Geological Science and Technology, 2021, 40(4): 187-195(in Chinese with English abstract). doi: 10.19509/j.cnki.dzkq.2021.0412 -