Displacement prediction of periodic term of Baishuihe landslide based on APSO-SVR-GRU model
-
摘要:
滑坡周期项位移的预测，是研究地质灾害中滑坡变形至关重要的一步。由于单一模型易受偶然因素影响，且无法充分利用有效信息，导致其预测精度不高，适用性不强。基于此，文中提出了一种结合自适应粒子群算法（APSO）、支持向量机回归算法（SVR）、门控神经网络算法(GRU)的组合模型。该模型通过自适应粒子群优化算法对支持向量机回归算法进行参数寻优，确定最优参数组合，然后利用最小二乘法对APSO-SVR模型与GRU模型赋权建立最优权重比组合模型。以三峡白水河滑坡作为研究对象，选取降雨量、库水位及位移量作为周期项位移的影响因子，对模型进行训练验证，结果表明：在白水河滑坡周期项位移预测中，文中所提出的APSO-SVR-GRU组合模型与单一模型相比，具有更高的预测精度和稳定性。
Abstract:The prediction of landslide periodic term displacement is a crucial step in the study of landslide deformation in geological disasters. Since single prediction model is susceptible to accidental factors and cannot make full use of effective information, its prediction accuracy is not high and its applicability is not strong. In this paper, a combined prediction model combining adaptive particle swarm optimization (APSO), support vector machine regression (SVR) and gated neural network (GRU) algorithm is proposed. The model uses the adaptive particle swarm optimization algorithm to optimize the parameters of the support vector machine regression algorithm, determines the optimal parameter combination, and then uses the least square method to weight the APSO-SVR model and the GRU model to establish the optimal weight ratio combination model. Taking the Baishuihe landslide of the Three Gorges as the research object, selecting precipitation, reservoir water level and displacement as the influence factors of the periodic term displacement, the model is trained and verified. The results show that: in the Baishuihe landslide periodic term displacement prediction, the APSO-SVR-GRU compared with a single model has higher prediction accuracy and stability.
-
Key words:
- periodic term displacement /
- least squares method /
- SVR /
- GRU /
- APSO
-
-
表 2 组合模型权重分配
Table 2. Weight distribution of combined models
监测点 GRU APSO-SVR 
XD01 0.482 0.518 ZG118 0.437 0.563 
下载: 导出CSV
表 3 监测点XD01和ZG118三种模型预测精度对比
Table 3. Prediction accuracy analysis of three models of monitoring point XD01 andZG118
模型 MAPE/% RMSE/mm XD01 ZG118 XD01 ZG118 GRU 19.89 21.18 11.79 14.51 APSO-SVR 16.27 19.81 10.36 13.75 APSO-SVR-GRU 12.69 14.08 7.02 8.98
下载: 导出CSV
表 4 监测点XD02和ZG93三种模型预测精度对比
Table 4. Prediction accuracy analysis of three models of monitoring point XD02 and ZG93
模型 MAPE/% RMSE/mm XD02 ZG93 XD02 ZG93 GRU 20.48 22.18 15.22 17.79 APSO-SVR 17.21 18.88 12.35 11.36 APSO-SVR-GRU 13.78 14.97 7.68 6.01
下载: 导出CSV
-
[1] 麻凤海,陈霞,季峰,等. 滑坡预测预报研究现状与发展趋势[J]. 徐州工程学院学报(自然科学版),2018,33(2):30 − 33. [MA Fenghai,CHEN Xia,JI Feng,et al. Current status and future development of landslide prediction research[J]. Journal of Xuzhou Institute of Technology (Natural Sciences Edition),2018,33(2):30 − 33. (in Chinese with English abstract)
[2] 刘向峰,郭子钰,王来贵,等. 降雨矿震叠加作用下抚顺西露天矿边坡稳定性分析[J]. 中国地质灾害与防治学报,2021,32(4):40 − 46. [LIU Xiangfeng,GUO Ziyu,WANG Laigui,et al. Analysis on the slope stability of Fushun West Open-pit Mine under superimposed action of rainfall,mine and earthquake[J]. The Chinese Journal of Geological Hazard and Control,2021,32(4):40 − 46. (in Chinese with English abstract)
[3] HÖLL M,KIYONO K,KANTZ H. Theoretical foundation of detrending methods for fluctuation analysis such as detrended fluctuation analysis and detrending moving average[J]. Physical Review E,2019,99:033305. doi: 10.1103/PhysRevE.99.033305
[4] ZHOU C,YIN K,CAO Y,et al. A novel method for landslide displacement prediction by integrating advanced computational intelligence algorithms[J]. Scientific Reports,2018(8):7287. doi: 10.1038/s41598-018-25567-6
[5] 李乃乾,孙晨童. 小波与传统滤波方法提取周期信息的比较研究[J]. 统计与决策,2021,37(1):29 − 34. [LI Naiqian,SUN Chentong. A comparative study on wavelet and traditional filtering methods for extracting cyclical information[J]. Statistics & Decision,2021,37(1):29 − 34. (in Chinese with English abstract)
[6] 宫月,贾瑞生,卢新明,等. 利用经验模态分解及小波变换压制微震信号中的随机噪声[J]. 煤炭学报,2018,43(11):3247 − 3256. [GONG Yue,JIA Ruisheng,LU Xinming,et al. To suppress the random noise in microseismic signal by using empirical mode decomposition and wavelet transform[J]. Journal of China Coal Society,2018,43(11):3247 − 3256. (in Chinese with English abstract) doi: 10.13225/j.cnki.jccs.2017.1667
[7] SHEN C,XUE S. Displacement prediction of rainfall-induced landslide based on machine learning[J]. Journal of Coastal Research,2018,83(10083):272 − 276.
[8] DENG D M,LIANG Y,WANG L Q,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.
[9] 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. [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. (in Chinese with English abstract)
[10] 陈绍桔. 边坡位移时间序列分析预测[J]. 福建建筑,2008(6):58 − 60. [CHEN Shaojie. Time series analysis on the prediction of slope displacement[J]. Fujian Architecture & Construction,2008(6):58 − 60. (in Chinese with English abstract)
[11] 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. (in Chinese with English abstract) doi: 10.13722/j.cnki.jrme.2018.0468
[12] 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 & Communications,2021,34(5):19 − 21. (in Chinese with English abstract) doi: 10.3969/j.issn.1673-1131.2021.05.006
[13] LIU Z Q,GUO D,LACASSE S,et al. Algorithms for intelligent prediction of landslide displacements[J]. Journal of Zhejiang University-SCIENCE A,2020,21(6):412 − 429. doi: 10.1631/jzus.A2000005
[14] 易武. 2007—2012年长江三峡库区秭归县白水河滑坡基本特征及监测数据[R]. 国家冰川冻土沙漠科学数据中心（www.ncdc.ac.cn）, 2016
YI Wu. 2007—2012 the basic features and monitoring data of the Baishui River landslide in the Three Gorges reservoir area of the Yangtze River from 2007 to 2012[R]. National Glacier Permafrost Desert Science Data Center （www.ncdc.ac.cn）, 2016. （ in Chinese）
[15] 方汕澳,许强,修德皓,等. 基于斜率模型的突发型黄土滑坡失稳时间预测[J]. 水文地质工程地质,2021,48(4):169 − 179. [FANG Shan’ao,XU Qiang,XIU Dehao,et al. A study of the predicted instability time of sudden loess landslides based on the SLO model[J]. Hydrogeology & Engineering Geology,2021,48(4):169 − 179. (in Chinese with English abstract)
[16] 张琳,汪廷华,周慧颖. 基于群智能算法的SVR参数优化研究进展[J]. 计算机工程与应用,2021,57(16):50 − 64. [ZHANG Lin,WANG Tinghua,ZHOU Huiying. Research progress on parameter optimization of SVR based on swarm intelligence algorithm[J]. Computer Engineering and Applications,2021,57(16):50 − 64. (in Chinese with English abstract) doi: 10.3778/j.issn.1002-8331.2104-0096
[17] 刘天浩. 滑坡位移序列的支持向量机预测[D]. 沈阳: 东北大学, 2005
LIU Tianhao. Prediction of landslide displacement series by the support vector machine[D]. Shenyang: Northeastern University, 2005. （in Chinese with English abstract）
[18] 方良斌,张宏魏,詹建勇,等. 基于移动平均法的危岩点云数据处理及变形分析[J]. 人民长江,2019,50(4):152 − 156. [FANG Liangbin,ZHANG Hongwei,ZHAN Jianyong,et al. Point cloud data processing of dangerous rock and deformation analysis based on moving average method[J]. Yangtze River,2019,50(4):152 − 156. (in Chinese with English abstract)
[19] 邹世铭,方成刚. 基于APSO-BP神经网络的齿轮表面粗糙度预测模型研究[J]. 工具技术,2021,55(6):47 − 51. [ZOU Shiming,FANG Chenggang. Research on gear surface roughness prediction model based on APSO-BP neural network[J]. Tool Engineering,2021,55(6):47 − 51. (in Chinese with English abstract) doi: 10.3969/j.issn.1000-7008.2021.06.008
[20] 陈贵敏,贾建援,韩琪. 粒子群优化算法的惯性权值递减策略研究[J]. 西安交通大学学报,2006,40(1):53 − 56. [CHEN Guimin,JIA Jianyuan,HAN Qi. Study on the strategy of decreasing inertia weight in particle swarm optimization algorithm[J]. Journal of Xi’an Jiaotong University,2006,40(1):53 − 56. (in Chinese with English abstract) doi: 10.3321/j.issn:0253-987X.2006.01.013
[21] 冯浩,李现伟. PSO算法中学习因子的非线性异步策略研究[J]. 安阳师范学院学报,2015(5):44 − 47. [FENG Hao,LI Xianwei. A study of nonlinear asynchronous strategies for learning factors in PSO algorithms[J]. Journal of Anyang Normal University,2015(5):44 − 47. (in Chinese with English abstract) doi: 10.3969/j.issn.1671-5330.2015.05.012
[22] 吴迪. 基于PSO-SVM的凤县公路边坡地质灾害空间预测[J]. 中国地质灾害与防治学报,2018,29(6):112 − 120. [WU Di. Spatial prediction of highway slope geo-hazards in Feng County based on PSO-SVM[J]. The Chinese Journal of Geological Hazard and Control,2018,29(6):112 − 120. (in Chinese with English abstract)
[23] LI X C,MA X F,XIAO F C,et al. Application of gated recurrent unit (GRU) neural network for smart batch production prediction[J]. Energies,2020,13(22):6121. doi: 10.3390/en13226121
[24] YU X,ZHANG X Q. Enhanced comprehensive learning particle swarm optimization[J]. Applied Mathematics and Computation,2014,242:265 − 276. doi: 10.1016/j.amc.2014.05.044
[25] JIANG H W,LI Y Y,ZHOU C,et al. Landslide displacement prediction combining LSTM and SVR algorithms:A case study of Shengjibao landslide from the Three Gorges Reservoir area[J]. Applied Sciences,2020,10(21):7830. doi: 10.3390/app10217830
[26] GREFF K,SRIVASTAVA R K,KOUTNIK J,et al. LSTM:a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems,2017,28(10):2222 − 2232. doi: 10.1109/TNNLS.2016.2582924
[27] 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. (in Chinese with English abstract)
[28] 陈锐,范小光,吴益平. 基于数据挖掘技术的白水河滑坡多场信息关联准则分析[J]. 中国地质灾害与防治学报,2021,32(6):1 − 8. [CHEN Rui,FAN Xiaoguang,WU Yiping. Analysis on association rules of multi-field information of Baishuihe landslide based on the data mining[J]. The Chinese Journal of Geological Hazard and Control,2021,32(6):1 − 8. (in Chinese with English abstract)
[29] 汤明高,吴川,吴辉隆,等. 水库滑坡地下水动态响应规律及浸润线计算模型—以石榴树包滑坡为例[J]. 水文地质工程地质,2022,49(2):115 − 125. [TANG Minggao,WU Chuan,WU Huilong,et al. Dynamic response and phreatic line calculation model of groundwater in a reservoir landslide:Exemplified by the Shiliushubao landslide[J]. Hydrogeology & Engineering Geology,2022,49(2):115 − 125. (in Chinese with English abstract)
[30] 王家柱,巴仁基,葛华,等. 基于MACD指标的渐变型滑坡临滑预报模型研究[J]. 水文地质工程地质,2022,49(6):133 − 140. [WANG Jiazhu,BA Renji,GE Hua,et al. Research on early-warning prediction model of critical slide of creep landslide based on the MACD index[J]. Hydrogeology & Engineering Geology,2022,49(6):133 − 140. (in Chinese with English abstract)
-
图(11)
表(4)
计量
- 文章访问数: 1578
- PDF下载数: 73
- 施引文献: 0