[1]安 冬a,宋 琨a,b*,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,(1):143-150.[doi:10.16089/j.cnki.1008-2786.000582]
 AN Donga,SONG Kuna,b*,et al.A Prediction Model for Reservoir Landslide Step-Like Displacements Using Combined EEMD and RFR Method[J].Mountain Research,2021,(1):143-150.[doi:10.16089/j.cnki.1008-2786.000582]
点击复制

一种基于EEMD-RFR的水库滑坡台阶状位移预测模型()
分享到:

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2021年第1期
页码:
143-150
栏目:
山地技术
出版日期:
2021-01-25

文章信息/Info

Title:
A Prediction Model for Reservoir Landslide Step-Like Displacements Using Combined EEMD and RFR Method
文章编号:
1008-2786-(2021)1-143-08
作者:
安 冬a宋 琨ab*仪 政a易庆林a
三峡大学 a. 湖北长江三峡滑坡国家野外科学观测研究站; b. 防灾减灾湖北省重点实验室,湖北 宜昌 443002
Author(s):
AN DongaSONG Kunab*YI ZhengaYI Qinglina
a.National Field Observation and Research Station of Landslides in Three Gorges Reservoir Area of Yangtze River; b. Hubei Key Laboratory of Disaster Prevention and Mitigation,China Three Gorges University, Yichang 443002, Hubei China
关键词:
水库滑坡 台阶状位移 位移预测模型 集合经验模态分解(EEMD) 随机森林(RFR)
Keywords:
reservoir landslide step-like displacement displacement prediction model ensemble empirical mode decomposition(EEMD) random forest regression(RFR)
分类号:
P642
DOI:
10.16089/j.cnki.1008-2786.000582
文献标志码:
A
摘要:
水库滑坡的位移与周期性的库水波动和季节性降雨等诱发因素关系密切,由于库水位升降和降雨的作用,滑坡累计位移变形曲线呈明显的“台阶状”,准确、及时地预测此类台阶状位移对提升该变形的认识具有重要意义。为深入了解诱发因素对水库滑坡位移的影响,预测其变形演化趋势,本研究提出了一种基于集合经验模态分解(EEMD)和随机森林回归模型(RFR)的滑坡位移预测模型。以水库滑坡——三峡库区白家包滑坡2007年4月至2018年12月的变形数据为例,进行“台阶状”位移的预测与模型检验。通过EEMD方法将累计位移分解为趋势项和周期项,其中趋势项采取最小二乘法的三次多项式拟合; 周期项基于诱发因素组合和滑坡位移的响应变化,建立RFR模型进行预测。根据时间序列加法,将趋势项和周期项预测值叠加,获得总位移预测值。结果表明EEMD-RFR模型基本反映了滑坡累计位移的“台阶状”变化趋势,相关系数R达到0.997。通过与两种BP神经网络预测方法的对比,反映EEMD-RFR模型具有更好的预测效果。本研究为水库滑坡台阶状位移预测提供了一种有效的新方法,对了解水库滑坡长期变形具有一定意义。
Abstract:
The displacement of reservoir landslide is closely related to triggering factors, such as the reservoir water periodic fluctuation and seasonal rainfall. The cumulative displacement of the landslide shows an obvious step-like shape due to the effect of reservoir water level rise or drawdown, and rainfall. Accurate and timely prediction of such step-like displacement has become a difficult problem for disaster warning personnel. In order to understand the influence of triggering factors on the reservoir landslide deformation behavior, a displacement prediction model was proposed to predict the landslide deformation trend, which was combined EEMD(Ensemble Empirical Mode Decomposition)and RFR(Random Forest Regression)method. The displacement data of Baijiabao Landslide in the Three Gorges Reservoir, China was taken as a case in the study. The data from April 2007 to December 2018 was carried out to verify the proposed prediction model for step-like displacement. The EEMD method was applied to decompose the cumulative displacement into trend term and periodic term. The trend term was fitted by cubic polynomial of least square method, and the period term was predicted by the RFR model. In the RFR model, the response of triggering factors and landslide displacement change was considered. The predicted displacement of periodic term and trend term was superposed to achieve the cumulative displacement according to the displacement time series. The results demonstrated that the combined EEMD and RFR model reflected the step-like variation trend of the cumulative displacement of reservoir landslide basically, and the correlation coefficient, R, reached to 0.997. To verify the model, another two prediction methods of BP neural network was employed to predict the step-like displacement of Baijiabao Landslide. The compared results showed that the combined EEMD and RFR model was better than the BP neural network method. The proposed model provides a new and effective method to predict the reservoir landslide step-like displacements. It is significant to understand the long-term deformation behavior of reservoir landslides.

参考文献/References:

[1] 闫友彪,陈元琰. 机器学习的主要策略综述[J]. 计算机应用研究, 2004(7):4-10+13. [YAN Youbiao, CHEN Yuanyan. A survey on machine learning and its main strategy [J]. Application Research of Computers, 2004(7):4-10+13] DOI:10.3969/j.issn.1001-3695.2004.07.002
[2] 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
[3] 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 Dongmei, LIANG Ye, WANG Liangqing, 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] DOI: 10.16285/j.rsm.2017.12.034
[4] 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] DOI: 10.16285/j.rsm.2020.1300
[5] DU Juan, YIN Kunlong, LACASSE S. Displacement prediction in colluvial landslides, Three Gorges Reservoir, China [J]. Landslides, 2013, 10(2):203-218. DOI: 10.1007/s10346-012-0326-8
[6] 张凯翔, 牛瑞卿, 胡友健等. 基于小波变换及外因响应的滑坡位移预测[J]. 中国矿业大学学报, 2017, 46(4):924-931. [ZHANG Kaixiang, NIU Ruiqing, HU Youjian, et al. Landslide displacement prediction based on wavelet transform and external cause [J]. Journal of China University of Mining & Technology, 2017, 46(4):924-931] DOI: 10.13247/j.cnki.jcumt.000716
[7] 朱权洁,姜福兴,尹永明, 等. 基于小波分形特征与模式识别的矿山微震波形识别研究[J]. 岩土工程学报, 2012, 34(11): 2036-2042. [ZHU Quanjie, JIANG Fuxing, YIN Yongming, et al. Classification of mine microseismic events based on wavelet-fractal method and pattern recognition [J]. Chinese Journal of Geotechnical Engineering, 2012, 34(11):2036-2042]
[8] 赵久彬,刘元雪,刘娜, 等. 海量监测数据下分布式BP神经网络区域滑坡空间预测方法[J]. 岩土力学, 2019, 40(7): 2866-2872. [ZHAO Jiubin, LIU Yuanxue, LIU Na, et al. Spatial prediction method of regional landslide based on distributed bp neural network algorithm under massive monitoring data [J]. Rock and Soil Mechanics, 2019, 40(7):2866-2872] DOI: 10.16285/j.rsm.2018.0593
[9] 曹洋兵,晏鄂川,谢良甫. 考虑环境变量作用的滑坡变形动态灰色—进化神经网络预测研究[J]. 岩土力学, 2012, 33(3): 848-852. [CAO Yangbing, YAN echuan, XIE Liangfu. Study of landslide deformation prediction based on gray model-evolutionary neural network model considering function of environmental variables [J]. Rock and Soil Mechanics, 2012, 33(3):848-852] DOI: 10.16285/j.rsm.2012.03.014
[10] ZHOU Chao, YIN Kunlong, CAO Ying, et al. Application of time series analysis and PSO–SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China [J]. Engineering Geology, 2016(204):108-120. DOI: 10.1016/j.enggeo.2016.02.009
[11] 胡至华, 袁路, 马东涛, 等. 基于EEMD分形和LS-SVM的次声信号识别泥石流类型[J].山地学报, 2020, 38(4): 619-629. [HU Zhihua, YUAN Lu, MA Dongtao, et al. Identification of debris flow types by infrasound signals based on EEMD fractal and LS-SVM [J]. Mountain Research, 2020, 38(4):619-629] DOI: 10.16089/j.cnki.1008-2786.000539
[12] 李麟玮,吴益平,苗发盛, 等. 基于不同Bootstrap方法和KELM-BPNN模型的滑坡位移区间预测[J]. 岩石力学与工程学报, 2019, 38(5):912-926. [LI Linwei, WU Yiping, MIAO Fasheng, et al. Landslide displacement interval prediction based on different Bootstrap methods and KELM-BPNN model [J]. Chinese Journal of Rock Mechanics and Engineering, 2019, 38(5):912-926] DOI: 10.13722/j.cnki.jrme.2018.1380
[13] LI Huajin, XU Qiang, HE Yusen, et al. Prediction of landslide displacement with an ensemble-based extreme learning machine and copula models [J]. Landslides, 2018,15(10). DOI: 10.1007/s10346-018-1020-2
[14] YOUSSEF A M, POURGHASEMI H R, POURTAGHI Z S, et al. Erratum to: Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia [J]. Landslides, 2016, 13(5):1315-1318. DOI: 10.1007/s10346-015-0667-1
[15] 杨光辉,简文星,张树坡, 等. 基于集成学习的阶跃型滑坡阶跃点判别分析[J]. 中国地质灾害与防治学报, 2019, 30(4): 1-8. [YANG Guanghui, JIAN Wenxing, ZHANG Shupo, et al. Discriminant step points of step-landslides based on ensemble learning [J]. The Chinese Journal of Geological Hazard and Control, 2019, 30(4):1-8] DOI: 10.16031/j.cnki.issn.1003-8035.2019.04.01
[16] BREIMAN L. Random Forests [J]. Machine Learning, 2001, 45(1):5-32. DOI: 10.1023/A:1010933404324
[17] WU Zhaohua, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method [J]. Advances in Adaptive Data Analysis, 2009, 1(1):1-41. DOI: 10.1142/S1793536909000047
[18] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971):903-995. DOI: 10.1098/rspa.1998.0193
[19] 陈可,李野,陈澜. EEMD分解在电力系统故障信号检测中的应用[J]. 计算机仿真, 2010, 27(3): 263-266. [CHEN Ke, LI Ye, CHEN Lan. Ensemble empirical mode decomposition for power quality detection applications [J].Computer Simulation, 2010, 27(3):263-266] DOI: 10.3969/j.issn.1006-9348.2010.03.065
[20] 刘勇, 秦志萌, 刘曼, 等. 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. [LIU Yong, QIN Zhimeng, LIU man, et al. Landslide displacement prediction method based on state division [J]. Geological Science and Technology Information, 2018, 37(1):184-189] DOI: 10.19509/j.cnki.dzkq.2018.0125
[21] CAO Ying, YIN Kunlong, ALEXANDER D E, et al. Using an extreme learning machine to predict the displacement of step-like landslides in relation to controlling factors [J]. Landslides, 2016(13):725-736. DOI: 10.1007/s10346-015-0596-z
[22] 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), 2016:37-42. [GAO Caiyun, Research on displacement prediction and risk assessment of landslide based on intelligent algorithm [D]. Beijing: China University of Mining & Technology, Beijing, 2016: 37-42]
[23] 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, 2018:44-50. [DENG Dongmei. Study of stepwise displacement prediction for reservoir landslides based on ensemble empirical mode decomposition [D]. Wuhan: China University of Geosciences, 2018: 44-50]

备注/Memo

备注/Memo:
收稿日期(Received date):2020-08-14; 改回日期(Accepted date):2021-01-12
基金项目(Foundation item):国家自然科学基金(41702378)。[National Natural Science Foundation of China(41702378)]
作者简介(Biography):安冬(1997-),男,硕士研究生,主要研究方向:环境地质及灾害防治。[AN Dong(1997-), male, M.Sc. candidate, research on environmental geology and disaster prevention and control] E-mail:545438132@qq.com
*通讯作者(Corresponding author):宋琨(1983-),男,博士,教授。主要研究方向:地质灾害演化机理。[SONG Kun(1983-), male, Ph.D.,professor, research on evolution mechanism of geological disasters]E-mail:songkun@ctgu.edu.cn
更新日期/Last Update: 2021-01-30