«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

卷:

第44卷

期数:

2022年第06期

页码:

1096-1110

栏目:

纪念刘国昌先生诞辰110周年专辑

出版日期:

2022-11-15

文章信息/Info

Title:

Displacement Prediction of Landslide Based on SPA-SSA-SVR Model—Taking Bazimen and Baishuihe Landslides in Three Gorges Reservoir Area, China as Examples

文章编号:

1672-6561(2022)06-1096-15

作者:

杨 玲; 魏 静^*; 许子伏

(北京交通大学 土木建筑工程学院,北京 100044)

Author(s):

YANG Ling;  WEI Jing^*;  XU Zi-fu

(School of Civil Engineering, Beijing Jiaotong University, Beijing 100044, China)

关键词:

位移预测;  滑坡;  平滑先验法;  麻雀搜索算法;  支持向量机回归;  波形相似度;  三峡库区

Keywords:

displacement prediction;  landslide;  smoothness priors approach;  sparrow search algorithm;  support vector regression;  waveform similarity;  Three Gorges reservoir area

分类号:

P621.22

DOI:

10.19814/j.jese.2022.07043

文献标志码:

A

摘要:

为定量化平滑先验法中正则化参数的取值及提高滑坡位移预测精度,提出一种基于平滑先验法(SPA)-麻雀搜索算法(SSA)-支持向量机回归(SVR)模型的滑坡位移预测方法。以三峡库区八字门和白水河滑坡为研究对象,首先采用平滑先验法分解累计位移序列和影响因素序列,基于波形相似度确定最优正则化参数并得到位移分解结果,利用灰色关联度确定波动项位移预测时最优输入序列,然后使用BP神经网络和麻雀搜索算法优化支持向量机回归模型,分别拟合预测趋势项位移和波动项位移,最后将位移分量叠加得到累计位移。结果表明:基于SPA-SSA-SVR模型的八字门滑坡监测点ZG110位移预测均方根误差(RMSE)为4.32 mm,白水河滑坡监测点ZG118、DX-01位移预测均方根误差分别为3.44和4.81 mm,比基于经验模态分解(EMD)-果蝇优化(FOA)-最小二乘支持向量机(LSSVM)模型得到的均方根误差分别减少8.59、3.82和11.58 mm,证明基于SPA-SSA-SVR模型的滑坡位移预测方法预测效果较好; 平滑先验分解中正则化参数的最优取值随累计位移时间序列的增加而趋于某一固定值,同一滑坡不同监测点和相同地区相同类型滑坡的正则化参数取值基本一致,八字门和白水河滑坡所在地区的最优正则化参数都为6。基于SPA-SSA-SVR模型的滑坡位移预测方法能在一定程度上考虑滑坡位移分解变形影响效应,为同类滑坡的预测预报提供思路。

Abstract:

In order to quantify the value of the regularization parameter in smoothness priors approach and improve the prediction accuracy of landslide displacement, a new method for predicting the landslide displacement based on smoothness priors approach(SPA)-sparrow search algorithm(SSA)-support vector regression(SVR)model was proposed; the Bazimen and Baishuihe landslides in Three Gorges reservoir area were taken as examples; the cumulative displacement-time curve was decomposed into fluctuation and trend terms by using SPA, the optimal regularization parameter of SPA was determined by analyzing the waveform similarity of the fluctuation term displacement and the influencing factor curves, then the optimal decomposition was obtained. SPA was also used to decompose the influencing factor sequences into stochastic and periodic terms, and the optimal influencing factor inputs sequences, when predicting the fluctuation term displacement was determined by calculating the correlation degree between the stochastic and fluctuation terms. The trend displacement was fitted by the BP neural network, and the fluctuation displacement was predicted by combating SSA and SVR model. Finally, the cumulative displacement was found to be the addition of the two component prediction values. The results show that the root mean square error(RMSE)of landslide displacement prediction for monitoring points ZG110 of Bazimen landslide based on SPA-SSA-SVR model is 4.32 mm, the RMSE values of monitoring points ZG118 and DX-01 in Baishuihe landslide are 3.44 and 4.81 mm, which are 8.59, 3.82 and 11.58 mm lower than the RMSE values by using empirical mode decomposition(EMD)-fruit fly optimization algorithm(FOA)-least square support vector machine(LSSVM)model, so the new method for predicting the landslide displacement is applicable; the optimal value of the regularization parameter in SPA tends to a fixed value with the increase of the cumulative displacement time series; the different monitoring points for the same landslide and the same type of landslide in the same area are basically the same regularization parameter, the optimal values in the regions of Bazimen and Baishuihe landslides are 6. The new method for predicting the landslide displacement based on SPA-SSA-SVR model can take into account the influence of landslide displacement decomposition to a certain extent, which provides ideas for the prediction of similar landslides.

参考文献/References:

[1] LAN H X,TIAN N M,LI L P,et al.Kinematic-based Landslide Risk Management for the Sichuan-Tibet Grid Interconnection Project(STGIP)in China[J].Engineering Geology,2022,308:106823.
[2] 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(增2):477-486,507.
ZHANG Zhen-kun,ZHANG Dong-mei,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(S2):477-486,507.
[3] LAN H X,TIAN N M,LI L P,et al.Poverty Control Policy May Affect the Transition of Geological Disaster Risk in China[J].Humanities and Social Sciences Communications,2022,9:80.
[4] 邓冬梅,梁 烨,王亮清,等.基于集合经验模态分解与支持向量机回归的位移预测方法:以三峡库区滑坡为例[J].岩土力学,2017,38(12):3660-3669.
DENG Dong-mei,LIANG Ye,WANG Liang-qing,et al.Displacement Prediction Method Based on Ensemble Empirical Mode Decomposition and Support Vector Machine Regression:A Case of Landslides in Three Gorges Reservoir Area[J].Rock and Soil Mechanics,2017,38(12):3660-3669.
[5] 黄观文,王家兴,杜 源,等.顾及降雨及库水位因素的滑坡时滞分析与预测:以三峡库区新铺滑坡为例[J].地球科学与环境学报,2021,43(3):621-631.
HUANG Guan-wen,WANG Jia-xing,DU Yuan,et al.Time-delay Analysis and Prediction of Landslide Considering Precipitation and Reservoir Water Level:A Case Study of Xinpu Landslide in Three Gorges Re-servoir Area,China[J].Journal of Earth Sciences and Environment,2021,43(3):621-631.
[6] LIN Z,SUN X Y,JI Y F.Landslide Displacement Prediction Model Using Time Series Analysis Method and Modified LSTM Model[J].Electronics,2022,11(10):1519.
[7] LI H J,XU Q,HE Y S,et al.Modeling and Predicting Reservoir Landslide Displacement with Deep Belief Network and EWMA Control Charts:A Case Study in Three Gorges Reservoir[J].Landslides,2020,17(3):693-707.
[8] GUO Z Z,CHEN L X,GUI L,et al.Landslide Displacement Prediction Based on Variational Mode Decomposition and WA-GWO-BP Model[J].Landslides,2020,17(3):567-583.
[9] 张 凯,张 科,保 瑞,等.基于优化经验模态分解和聚类分析的滑坡位移智能预测研究[J].岩土力学,2021,42(1):211-223.
ZHANG Kai,ZHANG Ke,BAO Rui,et al.Intelligent Prediction of Landslide Displacements Based on Optimized Empirical Mode Decomposition and K-Mean Clustering[J].Rock and Soil Mechanics,2021,42(1):211-223.
[10] TARVAINEN M P,RANTA-AHO P O,KARJALAINEN P A.An Advanced Detrending Method with Application to HRV Analysis[J].IEEE Transactions on Biomedical Engineering,2002,49(2):172-175.
[11] ZHU Q,TIAN X,WANG C W,et al.Learning Your Heart Actions from Pulse:ECG Waveform Reconstruction from PPG[J].IEEE Internet of Things Journal,2021,8(23):16734-16748.
[12] 姚依欣,王 勇,詹金刚,等.利用平滑先验信息方法分离高频GPS数据静态永久变形与地震波[J].测绘学报,2018,47(4):490-497.
YAO Yi-xin,WANG Yong,ZHAN Jin-gang,et al.Separating Static Offset and Seismic Wave from High-rate GPS Data by the Smoothness Priors Method[J].Acta Geodaetica et Cartographica Sinica,2018,47(4):490-497.
[13] 葛红平,刘晓波,熊小明.SPA散布熵和GK聚类相结合的滚动轴承故障诊断[J].机械科学与技术,2021,40(8):1257-1263.
GE Hong-ping,LIU Xiao-bo,XIONG Xiao-ming.Fault Diagnosis Method of Rolling Bearing Combining with SPA Dispersion Entropy and GK Clustering[J].Mechanical Science and Technology for Aerospace Engineering,2021,40(8):1257-1263.
[14] 黄海峰,易 武,易庆林,等.滑坡位移分解预测中的平滑先验分析方法[J].水文地质工程地质,2014,41(5):95-100.
HUANG Hai-feng,YI Wu,YI Qing-lin,et al.Smoo-thness Priors Approach in Landslide Displacement Prediction[J].Hydrogeology & Engineering Geology,2014,41(5):95-100.
[15] 刘纪平,梁恩婕,徐胜华,等.顾及样本优化选择的多核支持向量机滑坡灾害易发性分析评价[J].测绘学报,2022,51(10):2034-2045.
LIU Ji-ping,LIANG En-jie,XU Sheng-hua,et al.Multi-kernel Support Vector Machine Considering Sample OptimizationSelection for Analysis and Eva-luation of Landslide Disaster Susceptibility[J].Acta Geodaetica et Cartographica Sinica,2022,51(10):2034-2045.
[16] 孟彩霞,吴 迪,雷 雨.基于麻雀搜索算法优化的BP神经网络卫星钟差预报[J].大地测量与地球动力学,2022,42(2):125-131.
MENG Cai-xia,WU Di,LEI Yu.BP Neural Network for Satellite Clock Bias Prediction Based on Sparrow Search Algorithm[J].Journal of Geodesy and Geodynamics,2022,42(2):125-131.
[17] 马飞燕,李向新.基于改进麻雀搜索算法-核极限学习机耦合算法的滑坡位移预测模型[J].科学技术与工程,2022,22(5):1786-1793.
MA Fei-yan,LI Xiang-xin.Landslide Displacement Prediction Model Using Improved SSA-KELM Coupling Algorithm[J].Science Technology and Engineering,2022,22(5):1786-1793.
[18] 别锋锋,朱鸿飞,彭 剑,等.基于VMD-MSE与SSA-SVM的往复式压缩机气阀故障诊断[J].振动与冲击,2022,41(19):289-295.
BIE Feng-feng,ZHU Hong-fei,PENG Jian,et al.Fault Diagnosis of Reciprocating Compressor Air Va-lve Based on VMD-MSE and SSA-SVM[J].Journal of Vibration and Shock,2022,41(19):289-295.
[19] 陈万志,李昊哲,刘恒嘉,等.融合LSTM和优化SVM的风力发电机组故障预测方法[J].辽宁工程技术大学学报(自然科学版),2022,41(4):379-384.
CHEN Wan-zhi,LI Hao-zhe,LIU Heng-jia,et al.Wind Turbine Fault Prediction Method Based on LSTM and Optimized SVM[J].Journal of Liaoning Technical University(Natural Science),2022,41(4):379-384.
[20] 魏鹏飞,樊小朝,史瑞静,等.基于改进麻雀搜索算法优化支持向量机的短期光伏发电功率预测[J].热力发电,2021,50(12):74-79.
WEI Peng-fei,FAN Xiao-chao,SHI Rui-jing,et al.Short-term Photovoltaic Power Generation Forecast Based on Improved Sparrow Search Algorithm Optimized Support Vector Machine[J].Thermal Power Generation,2021,50(12):74-79.
[21] 高淑萍,沈渠旺,宋国兵,等.采用余弦相似度的混合三端直流输电线路保护原理[J].西安交通大学学报,2022,56(9):92-103.
GAO Shu-ping,SHEN Qu-wang,SONG Guo-bing,et al.Cosine Similarity-based Protection of Hybrid Three-terminal DC Transmission Line[J].Journal of Xi’an Jiaotong University,2022,56(9):92-103.
[22] 李 斌,张纪航,刘海金,等.基于波形相似度分析的直流输电线路故障测距[J].电力自动化设备,2019,39(9):27-32,53.
LI Bin,ZHANG Ji-hang,LIU Hai-jin,et al.Fault Location of HVDC Transmission Lines Based on Waveform Similarity Analysis[J].Electric Power Automation Equipment,2019,39(9):27-32,53.
[23] 赵雅逊.基于位移监测数据的滑坡预警方法研究[D].大连:大连理工大学,2021.
ZHAO Ya-xun.Research on Early Warning Methods of Landslide Based on Displacement Monitoring Data[D].Dalian:Dalian University of Technology,2021.
[24] 侯家其.基于分布式水文模型和深度神经网络的滑坡预测研究[D].重庆:重庆交通大学,2021.
HOU Jia-qi.Landslide Prediction Based on Distributed Hydrological Model and Deep Neural Network[D].Chongqing:Chongqing Jiaotong University,2021.
[25] 姜南林.基于改进麻雀搜索算法优化长短期记忆网络的短期电力负荷预测研究[D].南昌:南昌大学,2021.
JIANG Nan-lin.Research on Short-term Power Load Forecasting Based on Improved Sparrow Search Algorithm to Optimize Long Short-term Memory Network[D].Nanchang:Nanchang University,2021.
[26] XUE J K,SHEN B.A Novel Swarm Intelligence Optimization Approach:Sparrow Search Algorithm[J].Systems Science & Control Engineering,2020,8(1):22-34.
[27] 吕 鑫,慕晓冬,张 钧,等.混沌麻雀搜索优化算法[J].北京航空航天大学学报,2021,47(8):1712-1720.
LYU Xin,MU Xiao-dong,ZHANG Jun,et al.Chaos Sparrow Search Optimization Algorithm[J].Journal of Beijing University of Aeronautics and Astronautics,2021,47(8):1712-1720.
[28] 黄敬宇.融合t分布和Tent混沌映射的麻雀搜索算法研究[D].兰州:兰州大学,2021.
HUANG Jing-yu.Research on Sparrow Search Algorithm Based on Fusion of t Distribution and Tent Chao-tic Mapping[D].Lanzhou:Lanzhou University,2021.
[29] 张袆袆.库水升降条件下滑坡渗流场特征及稳定性演化规律研究:以八字门滑坡分析为例[D].青岛:青岛理工大学,2021.
ZHANG Hui-hui.Study on the Seepage Field Characteristics and Stability Evolution Law of Landslide Under Reservoir Fluctuation:Taking the Analysis of Bazimen Landslide as an Example[D].Qingdao:Qingdao University of Technology,2021.
[30] 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 Lin-wei.Displacement Prediction and Stability Evaluation Methods of Reservoir Colluvial Landslides in Three Gorges Reservoir Area[D].Wuhan:China University of Geosciences,2021.
[31] 易 武.2007～2012年长江三峡库区秭归县八字门滑坡基本特征及监测数据[DB/OL].(2016-10-17)[2022-07-02].DOI:10.12072/ncdc.Sanxia.db0025.2020.
YI Wu.Basic Characteristics and Monitoring Data of the Bazimen Landslide in Zigui County,Three Gorges Reservoir Area of Yangtze River from 2007 to 2012[DB/OL].(2016-10-17)[2022-07-02].DOI:10.12072/ncdc.Sanxia.db0025.2020.
[32] 兰恒星,周成虎,李焯芬,等.瞬时孔隙水压力作用下的降雨滑坡稳定性响应分析:以香港天然降雨滑坡为例[D].中国科学:E辑,技术科学,2003,33(增1):119-136.
LAN Heng-xing,ZHOU Cheng-hu,LI Chao-fen,et al.Rainfall-induced Landslide Stability Analysis in Response to Transient Pore Pressure:A Case Study of Natural Terrain Landslide in Hong Kong[J].Science in China:Series E,Technological Sciences,2003,33(S1):119-136.
[33] 黄发明,汪 洋,董志良,等.基于灰色关联度模型的区域滑坡敏感性评价[J].地球科学,2019,44(2):664-676.
HUANG Fa-ming,WANG Yang,DONG Zhi-liang,et al.Regional Landslide Susceptibility Mapping Based on Grey Relational Degree Model[J].Earth Science,2019,44(2):664-676.
[34] 邓茂林,周 剑,易庆林,等.三峡库区靠椅状土质滑坡变形特征及机制分析[J].岩土工程学报,2020,42(7):1296-1303.
DENG Mao-lin,ZHOU Jian,YI Qing-lin,et al.Characteristics and Mechanism of Deformation of Chair-shaped Soil Landslides in Three Gorges Reservoir Area[J].Chinese Journal of Geotechnical Engineering,2020,42(7):1296-1303.
[35] 兰恒星,彭建兵,祝艳波,等.黄河流域地质地表过程与重大灾害效应研究与展望[J].中国科学:地球科学,2022,52(2):199-221.
LAN Heng-xing,PENG Jian-bing,ZHU Yan-bo,et al.Research on Geological and Surfacial Processes and Major Disaster Effects in the Yellow River Basin[J].Science China:Earth Sciences,2022,52(2):199-221.

相似文献/References:

[1]邓通发,桂勇,罗嗣海,等.降雨条件下花岗岩残坡积土路堑边坡稳定性研究[J].地球科学与环境学报,2012,34(04):88.
　DENG Tong-fa,GUI Yong,LUO Si-hai,et al.Study on Slope Stability of Granite Residual Soil Cutting Excavation with Rainfall[J].Journal of Earth Sciences and Environment,2012,34(06):88.
[2]王志兵,邹永胜,李斌,等.桂东南花岗岩风化土与残余节理的微观结构及演化[J].地球科学与环境学报,2020,42(03):405.[doi:10.19814/j.jese.2019.10040]
　WANG Zhi-bing,ZOU Yong-sheng,LI Bin,et al.Micro-structure and Evolution of Relict Joints and Weathered Granite Soils in the Southeastern Guangxi, China[J].Journal of Earth Sciences and Environment,2020,42(06):405.[doi:10.19814/j.jese.2019.10040]
[3]祝艳波,韩宇涛,苗帅升,等.黄土-三趾马红土滑坡滑带土剪切力学特性影响因素[J].地球科学与环境学报,2021,43(04):744.[doi:10.19814/j.jese.2021.05024]
　ZHU Yan-bo,HAN Yu-tao,MIAO Shuai-sheng,et al.Influencing Factors on the Shear Strength of Sliding Zone of Loess-Hipparion Red Clay Landslide[J].Journal of Earth Sciences and Environment,2021,43(06):744.[doi:10.19814/j.jese.2021.05024]
[4]张雪,魏云杰*,杨成生,等.云南昭通地区滑坡隐患InSAR广域识别与监测[J].地球科学与环境学报,2025,47(01):128.[doi:10.19814/j.jese.2024.04030]
　ZHANG Xue,WEI Yun-jie*,YANG Cheng-sheng,et al.InSAR Wide-area Identification and Monitoring of Landslide Hazards in Zhaotong Area of Yunnan, China[J].Journal of Earth Sciences and Environment,2025,47(06):128.[doi:10.19814/j.jese.2024.04030]

备注/Memo

备注/Memo:

收稿日期:2022-07-26
基金项目:国家自然科学基金项目(41772289)
作者简介:杨 玲(1999-),女,河北石家庄人,工学硕士研究生,E-mail:20125980@bjtu.edu.cn。
*通讯作者:魏 静(1973-),女,北京市人,副教授,工学博士,E-mail:jingwei@bjtu.edu.cn。

常用功能

更新日期/Last Update: 2022-11-25