Improved GRU landslide displacement prediction model based on multifractal

doi:10.3785/j.issn.1008-973X.2024.07.010

Journal of ZheJiang University (Engineering Science)

2024, Vol. 58

Issue (7): 1407-1416 DOI: 10.3785/j.issn.1008-973X.2024.07.010

Improved GRU landslide displacement prediction model based on multifractal

Man XU1(

),Dongmei ZHANG1,Xiang YU1,Jiang LI2,*(

),Yiping WU3

1. School of Computer Science, China University of Geosciences (Wuhan), Wuhan 430074, China
2. Information Center, Department of Natural Resources of Hubei Province, Wuhan 430071, China
3. Faculty of Engineering, China University of Geosciences (Wuhan), Wuhan 430074, China

Download:

HTML

PDF(2282KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

The traditional memory network model has poor prediction accuracy on a non-stationary mutation data segment due to the gate mechanism has difficulty in learning sequence change trends. A multifractal algorithm was introduced to improve the gating control of the gated recurrent unit (GRU), and dynamically update the gating weight by quantifying the change characteristics of the sequence. The state fusion of the recurrent neural network unit was introduced to learn the long-range correlation of data. The landslide cumulative displacement was decomposed into trend term, periodic term and random term through the variational mode decomposition algorithm. The decomposed terms were trained and predicted by using the improved GRU. The monitoring points ZG93 and ZG118 of the Baishuihe landslide in the Three Gorges Reservoir area were selected for simulation experiments. Experimental results show that compared with traditional models, the new model learns the characteristics of the landslide displacement deformation trend better and has a higher prediction accuracy.

Key words： landslide cumulative displacement multifractal gated recurrent unit (GRU) variational mode decomposition recurrent neural network

Received: 26 June 2023 Published: 01 July 2024

CLC:

P 642

Fund: 国家自然科学基金联合基金重点支持项目（U1911205）；湖北省自然资源厅科技项目（ZRZY2024KJ22）.

Corresponding Authors: Jiang LI E-mail: xuman@cug.edu.cn;johnlee1124@126.com

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Man XU
	Dongmei ZHANG
	Xiang YU
	Jiang LI
	Yiping WU

Cite this article:

Man XU,Dongmei ZHANG,Xiang YU,Jiang LI,Yiping WU. Improved GRU landslide displacement prediction model based on multifractal. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1407-1416.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2024.07.010 OR https://www.zjujournals.com/eng/Y2024/V58/I7/1407

基于多重分形的改进GRU滑坡位移预测模型

门控机制设计难以学习序列变化趋势，导致传统记忆网络模型对滑坡位移非平稳跃变段预测效果较差. 基于多重分形改进门控循环单元（GRU），通过量化序列的变化特征来动态更新门控权重，引入循环神经网络单元的状态融合策略以学习数据的长程相关性特征. 采用变分模态分解算法将滑坡累积位移分解成趋势项、周期项及随机项，利用改进GRU进行位移分量的训练和预测. 选取三峡库区白水河滑坡监测点ZG93、ZG118进行仿真实验. 实验结果表明，相比传统预测模型，新模型的滑坡位移形变趋势特征学习能力更强，预测精度更高.

关键词： 滑坡累积位移, 多重分形, 门控循环单元(GRU), 变分模态分解, 循环神经网络

Fig.1 Principles of gated recurrent unit

Fig.2 Structure of improved gated recurrent unit based on multifractal

Fig.3 State fusion of recurrent neural network

Fig.4 Flow chart of landslide displacement prediction

Fig.5 Geological overview map of Baishuihe landslide^[4]

Tab.1 Root mean square error of prediction results under different input window settings

Tab.2 Comparative experiment parameter settings

Fig.6 Cumulative displacement-time curves for different monitoring points

Fig.7 Cumulative displacement-time curve and spectral width-time curve for monitoring point ZG118

Fig.8 Curves of landslide displacement component-time for monitoring point ZG118

Fig.9 Reservoir water level-time curve and periodic term-time curve for monitoring point ZG118

Fig.10 Curves of periodic term, random term and corresponding spectral width with time at monitoring point ZG118

Fig.11 Prediction curves of different models for landslide displacement components

Fig.12 Prediction curves of different models for periodic term and random term in mutation data segment

Tab.3 Prediction accuracy and error of landslide displacement components for different models

Fig.13 Prediction curves for overall data segment of cumulative displacement with different models

Fig.14 Prediction curves for mutation data segment of cumulative displacement with different models

Tab.4 Prediction accuracy and error of cumulative displacement for different models

Tab.5 Prediction accuracy and error of cumulative displacement for partial mutation data segment with different models


[1]	叶润青, 付小林, 郭飞, 等三峡水库运行期地质灾害变形特征及机制分析[J]. 工程地质学报, 2021, 29 (3): 680- 692 YE Runqing, FU Xiaolin, GUO Fei, et al Deformation characteristics and mechanism analysis of geological hazards during operation period of Three Gorges Reservoir[J]. Journal of Engineering Geology, 2021, 29 (3): 680- 692

[2]	李骅锦, 许强, 何雨森, 等 “阶跃式” 滑坡位移预测及阈值分析的 ARMA-(LASSO-ELM)-Copula模型[J]. 岩石力学与工程学报, 2017, 36 (Suppl.2): 4075- 4084 LI Huajin, XU Qiang, HE Yusen, et al An ARMA-(LASSO-ELM)-Copula farmework for landslide displacement prediction and threshold computing of the displacement of step-like landslides[J]. Chinese Journal of Rock Mechanics and Engineering, 2017, 36 (Suppl.2): 4075- 4084

[3]	许强, 汤明高, 徐开祥, 等滑坡时空演化规律及预警预报研究[J]. 岩石力学与工程学报, 2008, 27 (6): 1104- 1112 XU Qiang, TANG Minggao, XU Kaixiang, et al Research on space-timeevolution laws and early warning-prediction of landslides[J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27 (6): 1104- 1112 doi: 10.3321/j.issn:1000-6915.2008.06.003

[4]	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

[5]	张俊, 殷坤龙, 王佳佳, 等基于时间序列与 PSO-SVR 耦合模型的白水河滑坡位移预测研究[J]. 岩石力学与工程学报, 2015, 34 (2): 382- 391 ZHANG Jun, YIN Kunlong, WANG Jiajia, et al Displacement prediction of Baishuihe landslide based on time series and PSO-SVR model[J]. Chinese Journal of Rock Mechanics and Engineering, 2015, 34 (2): 382- 391

[6]	XU S, NIU R Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area, China[J]. Computers and Geosciences, 2018, 111: 87- 96 doi: 10.1016/j.cageo.2017.10.013

[7]	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 XU Feng, FAN Chunju, XU Jianxun, et al Displacement prediction of landslide based on variational mode decomposition and AMPSO-SVM coupling model[J]. Journal of Shanghai Jiao Tong University, 2018, 52 (10): 1388- 1395

[8]	陈伟, 雷帮军, 黄海峰基于门控循环单元的滑坡位移预测和灾害预警方法[J]. 长江信息通信, 2021, 34 (5): 19- 21 CHEN Wei, LEI Bangjun, HUANG Haifeng Landslide displacement prediction and disaster early warning method based on gated recurrent unit[J]. Changjiang Information and Communication, 2021, 34 (5): 19- 21 doi: 10.3969/j.issn.1673-1131.2021.05.006

[9]	黄发明, 殷坤龙, 杨背背, 等基于时间序列分解和多变量混沌模型的滑坡阶跃式位移预测[J]. 地球科学, 2018, 43 (3): 887- 898 HUANG Faming, YIN Kunlong, YANG Beibei, et al Step-like displacement prediction of landslide based on time series decomposition and multivariate chaos model[J]. Earth Science, 2018, 43 (3): 887- 898

[10]	徐峰, 汪洋, 杜娟, 等基于时间序列分析的滑坡位移预测模型研究[J]. 岩石力学与工程学报, 2011, 30 (4): 746- 751 XU Feng, WANG Yang, DU Juan, et al Study of displacement prediction model of landslide based on time series analysis[J]. Chinese Journal of Rock Mechanics and Engineering, 2011, 30 (4): 746- 751

[11]	朱治军, 李后强小波分析在分形科学中的应用[J]. 应用基础与工程科学学报, 1994, 2 (4): 275- 281 ZHU Zhijun, LI Houqiang Application of wavelet analysis in fractals[J]. Journal of Applied Basic and Engineering Science, 1994, 2 (4): 275- 281

[12]	林大超, 安凤平, 郭章林, 等滑坡位移的多模态支持向量机模型预测[J]. 岩土力学, 2011, 32 (Suppl.1): 451- 458 LIN Dachao, AN Fengping, GUO Zhanglin, et al Prediction of landslide displacements through multimode support vector machine model[J]. Rock and Soil Mechanics, 2011, 32 (Suppl.1): 451- 458

[13]	邓冬梅. 基于集合经验模态分解的水库库岸滑坡阶跃型位移预测研究[D]. 武汉: 中国地质大学, 2018. DENG Dongmei. Study of stepwise displacement prediction for reservoir landslides based on ensemble empirical mode decomposition [D]. Wuhan: China University of Geosciences, 2018.

[14]	李麟玮, 吴益平, 苗发盛, 等考虑变形状态动态切换的阶跃型滑坡位移区间预测方法[J]. 岩石力学与工程学报, 2019, 38 (11): 2272- 2287 LI Linwei, WU Yiping, MIAO Fasheng, et al Displacement interval prediction method for step-like landslides considering deformation state dynamic switching[J]. Chinese Journal of Rock Mechanics and Engineering, 2019, 38 (11): 2272- 2287

[15]	易利容, 王绍宇, 殷丽丽, 等基于多变量 LSTM 的工业传感器时序数据预测[J]. 智能计算机与应用, 2018, 8 (5): 13- 16 YI Lirong, WANG Shaoyu, YIN Lili, et al Forecasting of industrial sensor time series based on multivariable LSTM[J]. Intelligent Computer and Applications, 2018, 8 (5): 13- 16 doi: 10.3969/j.issn.2095-2163.2018.05.003

[16]	HOCHREITER S. Untersuchungen zu dynamischen neuronalen Netzen [D]. Munich: Technical University of Munich, 1991. HOCHREITER S. Investigations on dynamic neural networks [D]. Munich: Technical University of Munich, 1991.

[17]	HOCHREITER S, SCHMIDHUBER J Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780 doi: 10.1162/neco.1997.9.8.1735

[18]	CHO K, VAN MERRIËNBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder–decoder for statistical machine translation [C]/ / Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing . Doha: Association for Computational Linguistics, 2014: 1724–1734.

[19]	管孝艳, 杨培岭, 吕烨基于多重分形理论的农田土壤特性空间变异性分析[J]. 应用基础与工程科学学报, 2011, 19 (5): 712- 720 GUAN Xiaoyan, YANG Peiling, LV Ye Analysis on spatial variability of soil properties based on multifractal theory[J]. Journal of Basic Science and Engineering, 2011, 19 (5): 712- 720 doi: 10.3969/j.issn.1005-0930.2011.05.003

[20]	ZHOU, G B, WU J, ZHANG C L, et al Minimal gated unit for recurrent neural networks[J]. International Journal of Automation and Computing, 2016, 13 (3): 226- 234 doi: 10.1007/s11633-016-1006-2

[21]	张振坤, 张冬梅, 李江, 等基于多头自注意力机制的LSTM-MH-SA滑坡位移预测模型研究[J]. 岩土力学, 2022, 43 (Suppl.2): 477- 486 ZHANG Zhenkun, ZHANG Dongmei, LI Jiang, et al LSTM-MH-SA landslide displacement prediction model based on multi-head self-attention mechanism[J]. Rock and Soil Mechanics, 2022, 43 (Suppl.2): 477- 486

[22]	刘艺梁, 殷坤龙, 汪洋, 等基于经验模态分解和神经网络的滑坡变形预测研究[J]. 安全与环境工程, 2013, 20 (4): 14- 17 LIU Yiliang, YIN Kunlong, WANG Yang, et al Study of landslide deformation prediction based on EMD and neural network[J]. Safety and Environmental Engineering, 2013, 20 (4): 14- 17 doi: 10.3969/j.issn.1671-1556.2013.04.004

[1]	Xianglong LUO,Yafei WANG,Yanbo WANG,Lixin WANG. Structural deformation prediction of monitoring data based on bi-directional gate board learning system[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(4): 729-736.

[2]	Fan XIONG,Tian CHEN,Bai-cheng BIAN,Jun LIU. Chip surface character recognition based on convolutional recurrent neural network[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(5): 948-956.

[3]	Wei SUN,Heng LIU,Jian-feng TAO,Hao SUN,Cheng-liang LIU. IndRNN-1DLCNN based fault diagnosis of independent metering valve-controlled hydraulic cylinder system[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(10): 2028-2041.

[4]	Hong-zhao DONG,Zhen WANG,Nan ZHANG,Yi-ni SHE,Ying-ying LIN. Seq2Seq prediction method of state of charge of electric bus battery[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(10): 2051-2059.

[5]	Nan ZHANG,Hong-zhao DONG,Yi-ni SHE. Seq2Seq prediction of bus trajectory on exclusive bus lanes[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(8): 1482-1489.

[6]	Mao-xia RAN,Qin-yuan HUANG,Xin LIU,Hong SONG,Hao WU. Internal defect detection of arc magnets based on optimized variational mode decomposition[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(11): 2158-2168.

[7]	Ji-jun TONG,Yan-jie BAI,Jian-wei PAN,Jia-feng YANG,Lu-rong JIANG. Ballistocardiogram and respiratory signal separation based on variational mode decomposition[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(10): 2058-2066.

[8]	Jing-chang WANG,Ling CHEN,Shan-shan YU,Chen-shu JIANG,Yong WU. Multi-factor perceived short-term tourist number prediction model based on gated recurrent unit[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(12): 2357-2364.

Viewed

Full text

Abstract

Cited

Shared

Discussed