[1]张明岳,李丽敏*,温宗周.基于变分模态分解和双向长短时记忆神经网络模型的滑坡位移预测[J].山地学报,2021,(6):855-866.[doi:10.16089/j.cnki.1008-2786.000644]
 ZHANG Mingyue,LI liming*,WEN Zongzhou.An Updated Approach to Predict Landslide Displacement by Combining Variational Modal Decomposition with Bidirectional Long Short-Term Memory Neural Network Model[J].Mountain Research,2021,(6):855-866.[doi:10.16089/j.cnki.1008-2786.000644]
点击复制

基于变分模态分解和双向长短时记忆神经网络模型的滑坡位移预测()
分享到:

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2021年第6期
页码:
855-866
栏目:
山区灾害
出版日期:
2021-11-25

文章信息/Info

Title:
An Updated Approach to Predict Landslide Displacement by Combining Variational Modal Decomposition with Bidirectional Long Short-Term Memory Neural Network Model
文章编号:
1008-2786-(2021)6-855-12
作者:
张明岳李丽敏*温宗周
西安工程大学 电子信息学院,西安 710600
Author(s):
ZHANG Mingyue LI liming* WEN Zongzhou
1. College of Electronic Information, Xi'an Polytechnic University, Xi'an 710600, China
关键词:
滑坡位移 动态预测 变分模态分解 双向长短时记忆神经网络 新滩滑坡 八字门滑坡
Keywords:
landslide displacement dynamic prediction variational mode decomposition bidirectional long short-term memory network Xintan landslide Bazimen landslide
分类号:
TP391.9
DOI:
10.16089/j.cnki.1008-2786.000644
文献标志码:
A
摘要:
滑坡变形的定量预测是滑坡预警系统中的重要组成部分,滑坡变形受其自身地质条件和众多环境因素共同影响,具有动态、复杂和非线性等特点。针对目前滑坡累积位移—时间序列分析研究中随机性位移无法分解与预测、传统预测模型难以模拟滑坡动态演化特性等问题,本文建立了一种基于组合变分模态分解(Variational Mode Decomposition, VMD)和双向长短时记忆(Bidirectional Long Short-Term Memory, Bi-LSTM)神经网络的复合性滑坡位移动态预测模型。该模型首先利用时间序列分析和VMD将滑坡累积位移分解为趋势项、周期项和随机项位移分量,通过分析滑坡的演化特征和诱发滑坡的关键因素,为各位移分量选择合适的影响因素; 然后采用多项式拟合预测趋势项位移、Bi-LSTM神经网络对周期项位移和随机项位移进行多数据驱动的动态预测; 最后将各位移分量叠加得到累积位移预测值。以新滩滑坡和八字门滑坡为样本,利用实地观测数据,对本模型的预测精度与工程实用性进行对比评估。实验结果表明,本文提出的模型能较好地表征位移“阶跃式”的变形特征。在预测周期项位移时,Bi-LSTM网络相较于长短时记忆神经网络(Long Short-Term Memory, LSTM)和支持向量机(Support Vector Machine, SVM)具有更高的预测精度,平均相对误差(Mean Relative Error, MRE)分别降低了1.339%和7.817%,均方根误差( Root Mean Square Error, RMSE)分别降低了6.761 mm和27.163 mm。说明该模型不仅预测精度高,且更稳定,可以为滑坡防灾减灾工程的实际应用提供新的思路。
Abstract:
Landslide is a complex nonlinear dynamic evolution process of earth surface, governed primarily by local geological conditions with environmental complexity. Quantitative prediction of downslope movement is an indispensable component of landslide early warning system. There have been two technical troubles in predicting slope deformation, among which one is that random displacement could not be decomposed and predicted by numerically resolving of the observed cumulative displacements and time series of a landslide, and another is that the dynamic evolution of a landslide could not be feasibly simulated simply by traditional prediction model.In this study, a dynamic model of displacement prediction was introduced for composite landslides based on a combination of Variational Mode Decomposition(VMD)with Bidirectional Long-Short-Term Memory(Bi-LSTM)neural network.In our proposed model, it used time series analysis and VMD to decompose the observed cumulative displacements of a slope into three components, viz. trend term, periodic term and random term; Then by analyzing the evolution pattern of a landslide and its key factors triggering landslides, appropriate influencing factors were selected for each displacement component; Polynomial fitting was used to predict trend term displacement, and Bi-LSTM neural network to make multi-data-driven dynamic prediction for periodic term as well as random term; A cumulative displacement prediction was obtained by a summation of each component. For accuracy verification and engineering practicability of the model, field observations from two known landslides in China, the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation. The case study verified that the model proposed in this paper can better characterize the “stepwise” deformation characteristics of a slope. As compared with short-term memory neural network and support vector machine, Bi-LSTM neural network had higher prediction accuracy in predicting the periodic term of slope deformation, with the Average Relative Error reduced by 1.339% and 7.817%, respectively, and the Root Mean Square Error reduced by 6.761 mm and 27.163 mm respectively. Conclusively, this model not only has high prediction accuracy, but also is more stable, which can provide a new insight for practical landslide prevention and control engineering.

参考文献/References:

[1] 吴善百, 廖丽萍, 韦遥, 等. 初始干密度对桂东南降雨型花岗岩残积土滑坡起动模式的影响[J]. 山地学报, 2020,38(6):881-893. [WU Shanbai, LIAO Liping, WEI Yao, et al. Effects of initial dry density on the initiation mode of rainfall-induced granite residual soil landslide, southeastern Guangxi province, China [J]. Mountain Research, 2020,38(6):881-893] DOI: 10.16089/j.cnki.1008-2786.000564
[2] 徐辉, 刘海知. 诱发滑坡的多尺度降雨特征[J]. 山地学报, 2019,37(6):858-867. [XU Hui, LIU Haizhi. Multi-scale rainfall characteristics of rainfall-induced landslides [J]. Mountain Research, 2019, 37(6): 858-867] DOI: 10.16089/j.cnki.1008-2786.000476
[3] 安冬, 宋琨, 仪政, 等. 一种基于EEMD-RFR的水库滑坡台阶状位移预测模型[J]. 山地学报, 2021,39(1):143-150. [AN Dong, SONG Kun, YI Zheng, et al. A prediction model for reservoir landslide step-like displacements using combined EEMD and RFR method [J]. Mountain Research, 2021,39(1):143-150] DOI: 10.16089/j.cnk.1008-2786.000582
[4] 韩贺鸣, 张磊, 施斌, 等. 基于光纤监测和PSO-SVM模型的马家沟滑坡深部位移预测研究[J]. 工程地质学报, 2019,27(4):853-861. [HAN Heming, ZHANG Lei, SHI Bin, et al. Prediction of deep displacement of Majiagou landslide based on optical fiber monitoring and PSO-SVM model [J]. Journal of Engineering Geology, 2019,27(4):853-861] DOI: 10.13544/j.cnki.jeg.2018-257
[5] 李仕波, 李德营, 张玉恩, 等. 基于LS-SVM模型的白水河滑坡台阶状位移预测[J]. 长江科学院院报, 2019,36(4):55-59+76. [LI Shibo, LI Deying, ZHANG Yuen, et al. Displacement prediction of Baishuihe step-like landslide by Least Square Support Vector Machine [J]. Journal of Yangtze River Scientific Research Institute, 2019,36(4):55-59+76] DOI: 10.11988/ckyyb.20170944
[6] 廖康, 吴益平, 李麟玮, 等. 基于时间序列与GWO-ELM模型的滑坡位移预测[J]. 中南大学学报(自然科学版), 2019,50(3):619-626. [LIAO Kang, WU Yiping, LL Linwei, et al. Displacement prediction model of landslide based on time series and GWO-ELM [J]. Journal of Central South University(Science and Technology), 2019,50(3):619-626] DOI: 10.11817/j.issn.1672-7207.2019.03.015
[7] SONG Jingkuan, GUO Yuyu, GAO Lianli, et al. From deterministic to generative: Multimodal stochastic RNNs for video captioning [J]. IEEE Transactions on Neural Networks and Learning Systems, 2019,30(10):3047-3058. DOI: 10.1109/TNNLS.2018.2851077
[8] SHEN Shuilong, NJOCK P G A, ZHOU Annan, et al. Dynamic prediction of jet grouted column diameter in soft soil using Bi-LSTM deep learning [J]. Acta Geotechnica, 2021,16(1):303-315. DOI: 10.1007/s11440-020-01005-8
[9] 周飞, 许强, 亓星, 等. 灌溉诱发突发性黄土滑坡机理研究[J].山地学报, 2020,38(1):73-82. [ZHOU Fei, XU Qiang, QI Xing, et al. The mechanism study of the Irrigation-induced sudden loess landslide [J]. Mountain Research, 2020,38(1):73-82] DOI: 10.16089/j.cnki.1008-2786.000492
[10] 高彩云. 基于智能算法的滑坡位移预测与危险性评价研究[D]. 北京: 中国矿业大学(北京), 2016. [GAO Caiyun. Research on landslide displacement prediction and risk assessment based on intelligent algorithms [D]. Beijing: China University of Mining and Technology(Beijing), 2016]
[11] XING Yin, YUE Jianping, CHEN Chuang, et al. Dynamic displacement forecasting of Dashuitian landslide in China using variational mode decomposition and stack long short-term memory network [J]. Applied Sciences, 2019,9: 2951. DOI: 10.3390/app9152951
[12] ZHOU Chao, YIN, Kunlong, CAO Ying, et al. Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method [J]. Landslides, 2018,15(11):2211-2225. DOI: 10.1007/s10346-018-1022-0
[13] SHIHABUDHEN K V, PILLAI G N, PEETHAMBARAN B. Prediction of landslide displacement with controlling factors using Extreme Learning Adaptive Neuro-Fuzzy Inference System(ELANFIS)[J]. Applied Soft Computing, 2017,61:892-904. DOI: 10.1016/j.asoc.2017.09.001
[14] ZHANG Junrong, TANG Huiming, WEN Tao, et al. A hybrid landslide displacement prediction method based on CEEMD and DTW-ACO-SVR—cases studied in the Three Gorges Reservoir area [J]. Sensors, 2020,20:4287. DOI: 10.3390/s20154287
[15] 韩斐, 牛瑞卿, 李士垚, 等. 基于变分模态分解和深度置信神经网络模型的滑坡位移预测[J]. 长江科学院院报, 2020,37(8):61-68. [HAN Fei, NIU Ruiqing, LI Shiyao, et al. Landslide displacement prediction based on variational modal decomposition and deep confidence neural network model [J]. Journal of Yangtze River Scientific Research Institute, 2020,37(8):61-68] DOI: 10.11988 /ckyyb.20190638
[16] JIN Long, LI Shuai, HU Bin. RNN models for dynamic matrix inversion: A Control-theoretical perspective [J]. IEEE Transactions on Industrial Informatics, 2018,14(1):189-199. DOI: 10.1109/TII.2017.2717079
[17] HOCHREITER S, SCHMIDHUBER J. Long short-term memory [J]. Neural Computation, 1997(9):1735-1780. DOI: 10.1162/neco.1997.9.8.1735
[18] ZHAO Zheng, CHEN Weihai, WU Xingming, et al. LSTM network: A deep learning approach for short-term traffic forecast [J]. IET Intelligent Transport Systems, 2017,11(2):68-75. DOI: 10.1049/iet-its.2016.0208
[19] WANG Shouxiang, WANG Xuan, WANG Shaomin, et al. Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting [J]. Electrical Power and Energy Systems, 2019,109(7):470-479. DOI: 10.1016/j.ijepes.2019.02.022
[20] WEI Qiang, JI Zongcheng, LI Zhiheng, et al. A study of deep learning approaches for medication and adverse drug event extraction from clinical text [J]. Journal of the American Medical Informatics Association, 2020,27(1):13-21. DOI: 10.1093/jamia/ocz063
[21] 郭冠呈, 刘书明, 李俊禹, 等. 基于双向长短时神经网络的水量预测方法研究[J]. 给水排水, 2018,54(3):123-126. [GUO Guancheng, LIU Shuming, LI Junyu, et al. Study on water quality prediction method based on bidirectional long and short time neural network [J]. Water and Wastewater Engineering, 2018,54(3):123-126] DOI: 10.13789/j.cnki.wwe1964.2018.0083
[22] 李越超. 基于QPSO-LSSVM的边坡变形预测[J]. 山地学报, 2015,33(3):374-378. [LI Yuechao. Forecasting of slope displacement based on QPSO-LSSVM method [J]. Mountain Research, 2015,33(3):374-378] DOI: 10.16089/j.cnki.1008-2786.000047
[23] 郭璐, 贺可强, 贾玉跃. 水库型堆积层滑坡位移方向协调性参数及其失稳判据研究[J].水利学报, 2018,49(12):1532-1540. [GUO Lu, HE Keqiang, JIA Yuyue. Research on the displacement direction coordination parameter of colluvial landslide induced by reservoir and its warning destabilized criterion [J]. Journal of Hydraulic Engineering, 2018,49(12):1532-1540] DOI: 10.13243/j.cnki.slxb.20180520
[24] 冯子帆, 成枢, 董娟. 残差修正的GM(1,1)模型在滑坡位移预测中的应用[J]. 地理空间信息, 2019,17(9):113-115+11. [FENG Zifan, CHENG Shu, DONG Juan. Application of residual modified GM(1,1)model in landslide displacement prediction [J]. Geospatial Information, 2019,17(9):113-115+11] DOI: 10.3969/j.issn.1672-4623.2019.09.034
[25] LI Yuanyao, SUN Ronglin, YIN Kunlong, et al. Forecasting of landslide displacements using a chaos theory based wavelet analysis-volterra filter model [J]. Nature, 2019,9:19853. DOI: 10.1038/s41598-019-56405-y
[26] 郭子正, 殷坤龙, 黄发明, 等. 基于地表监测数据和非线性时间序列组合模型的滑坡位移预测[J]. 岩石力学与工程学报, 2018,37(S1):3392-3399. [GUO Zizheng, YIN Kunlong, HUANG Faming, et al. Landslide displacement prediction based on surface monitoring data and nonlinear time series combined model [J]. Chinese Journal of Rock Mechanics and Engineering, 2018,37(S1):3392-3399] DOI: 10.13722/j.cnki.jrme.2016.1534
[27] 王尚庆. 长江三峡滑坡监测预测预报[M]. 北京:地质出版社, 1999:59-68. [WANG Shangqing. Monitoring and forecasting of landslides in the Three Gorges of Yangtze River [M]. Beijing: Geological Publishing House, 1999:59-68]
[28] 殷坤龙, 姜清辉, 汪洋. 新滩滑坡运动全过程的非连续变形分析与仿真模拟[J]. 岩石力学与工程学, 2002,21(7):959-962. [YIN Kunlong, JIANG Qinghui, WANG Yang. Numerical simulation on the movement process of Xintan landslide by DDA method [J]. Chinese Journal of Rock Mechanics and Engineering, 2002,21(7):959-962] DOI: 10.3321/j.issn:1000-6915.2002.07.005
[29] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition [J]. IEEE Transactions on Signal Processing, 2014,62(3):531-544. DOI: 10.1109/TSP.2013.2288675
[30] LI Haodong, XU Ying, AN Dong, et al. Application of a flat variational modal decomposition algorithm in fault diagnosis of rolling bearings [J]. Journal of Low Frequency Noise, Vibration and Active Control, 2020,39(2):335-351. DOI: 10.1177/1461348419846730
[31] 叶正伟. 长江新滩滑坡的历史分析,趋势预测与启示[J]. 灾害学, 2000,15(3):31-35. [YE Zhengwei. Analysis of the history and developing trend of Xintan landslides and the enlightenment elicited from its detailed expatiation [J]. Journal of Catastrophe, 2000,15(3):31-35]
[32] 李麟玮, 吴益平, 苗发盛, 等. 基于变分模态分解与GWO-MIC-SVR模型的滑坡位移预测研究[J]. 岩石力学与工程学报, 2018,37(6):1395-1406. [LI Linwei, WU Yiping, MIAO Fasheng, et al. Displacement prediction of landslides based on variational mode decomposition and GWO-MIC-SVR model [J]. Chinese Journal of Rock Mechanics and Engineering, 2018,37(6):1395-1406] DOI: 10.13722/j.cnki.jrme.2017.1508
[33] GUO Zizheng, CHEN Lixia, GUI Lei, et al. Landslide displacement prediction based on variational mode decomposition and WA-GWO-BP model [J], Landslides, 2020, 17(3): 567-583. DOI: 10.1007/s10346-019-01314-4
[34] 李丽敏, 张明岳, 温宗周, 等. 基于奇异谱分析法和长短时记忆网络组合模型的滑坡位移预测[J]. 信息与控制, 2021,50(4):459-469+482. [LI Limin, ZHANG Mingyue, WEN Zongzhou, et al. Landslide displacement prediction based on singular spectrum analysis and a combined long short-term memory network model [J]. Information and Control, 2021, 50(4):459-469+482] DOI: 10.13976/j.cnki.xk.2021.0424
[35] 李麟玮. 三峡库区库岸堆积层滑坡位移预测与稳定性评价方法研究[D]. 武汉: 中国地质大学, 2021. [LI Linwei. Research on displacement prediction and stability evaluation method of landslides in reservoir bank deposits in Three Gorges Reservoir area [D]. Wuhan: China University of Geosciences, 2021] DOI: 10.27492/d.cnki.gzdzu.2021.000132
[36] 杨背背, 殷坤龙, 杜娟. 基于时间序列与长短时记忆网络的滑坡位移动态预测模型[J].岩石力学与工程学报, 2018,37(10):2334-2343. [YANG Beibei, YIN Kunlong, DU Juan. A model for predicting landslide displacement based on time series and long and short term memory neural network [J]. Chinese Journal of Rock Mechanics and Engineering, 2018,37(10):2334-2343] DOI: 10.13722/j.cnki.jrme.2018.0468

备注/Memo

备注/Memo:
收稿日期(Received date):2021-04-27; 改回日期(Accepted date):2021-12-20
基金项目(Foundation item):陕西省自然科学基础研究计划资助项目(2019JQ-206); 陕西省教育厅科学研究资助项目(17JK0346); 陕西省技术创新引导专项—科技成果转移与推广计划资助项目(2020CGXNG-009)。[Natural Science Basic Research Plan in Shaanxi Province of China(2019JQ-206); Scientific Research Funding Project of the Ministry of Education in Shaanxi Province of China(17JK0346); Technical Innovation Guidance Special Project-Funded Project of the Transfer and Promotion Plan of Scientific and Technological Achievements in Shaanxi Province of China(2020CGXNG-009)]
作者简介(Biography):张明岳(1996-),男,硕士研究生,主要研究方向:智能算法及其在地质灾害中的应用。 [ZHANG Mingyue(1996-), male, M.Sc. candidate, research on intelligent algorithm and its application in geological disasters] E-mail: 894864527@qq.com
*通讯作者(Corresponding author):李丽敏(1985-),女,博士,副教授,主要研究方向:地质灾害监测预警。[LI Limin(1985-), female, Ph.D., associate professor, research on geological disaster monitoring and early warning] E-mail: liliminxiaomi@126.com
更新日期/Last Update: 2021-11-30