基于EEMD-CNN-LSTM的新型综合模型在滑坡位移预测中的应用  

Application of integrated model based on EEMD-CNN-LSTM for landslide-displacement prediction

作　　者：刘航源 陈伟涛[2] 李远耀[3] 徐战亚[4] 李显巨 LIU Hangyuan;CHEN Weitao;LI Yuanyao;XU Zhanya;LI Xianju(Key Laboratory of Geological Survey and Evaluation of Ministry of Education,China University of Geosciences,Wuhan 430074,Hubei,China;School of Computer Science,China University of Geosciences,Wuhan 430074,Hubei,China;Institute of Geological Survey,China University of Geosciences,Wuhan 430074,Hubei,China;School of Geography and Information Engineering,China University of Geosciences,Wuhan 430074,Hubei,China)

机构地区：[1]中国地质大学(武汉)地质探测与评估教育部重点实验室,湖北武汉430074 [2]中国地质大学(武汉)计算机学院,湖北武汉430074 [3]中国地质大学(武汉)地质调查研究院,湖北武汉430074 [4]中国地质大学(武汉)地理与信息工程学院,湖北武汉430074

出　　处：《地质力学学报》2024年第4期633-646,共14页Journal of Geomechanics

基　　金：湖北省重点研发计划(2021BID009);地质探测与评估教育部重点实验室主任基金项目(GLAB2022ZR02)。

摘　　要：滑坡位移预测是滑坡稳定性评价的重要环节。尽管基于深度学习范式的时间序列方法预测滑坡位移取得了一定的成果,但由于滑坡位移数据的非平稳性、周期性和趋势性变化特征,导致当前时间序列模型的滑坡位移的多变量预测容易过拟合。为解决这一问题,针对滑坡位移数据的波动性和由周期项与趋势项位移叠加组成的特性,提出一种基于孤立森林(Isolation Forest,IF)异常检测、集成经验模态分解(Ensemble Empirical Mode Decomposition,EEMD)、卷积神经网络(Convolutional Neural Networks,CNN)和长短期记忆神经网络(Long Short-Term Memory,LSTM)相结合的滑坡位移预测模型。选择三峡库区以降雨为影响因子的阶跃型白家包滑坡为研究对象,引入IF算法对滑坡原始位移数据进行异常检测,使用EEMD方法提取滑坡趋势项和周期项位移,通过CNN捕捉局部周期项和趋势模式,并基于LSTM模型预测总体位移。结果表明,EEMD-CNN-LSTM在预测降雨情况时滑坡总体位移的均方根误差(RMSE)、平均绝对误差(MAE)、评价绝对百分比误差(MAPE)和决定系数(R2)4种指标分别为0.4190、0.3139、0.2379和0.9997,前3种精度评价指标较现有模型分别提升32.3%、25.1%、7.3%。相较于传统的LSTM模型、随机森林方法和EEMD-LSTM方法,EEMD-CNN-LSTM模型在有、无降雨这一外部影响因素下具有显著优势,能够较大地降低过拟合,提高预测的准确性。[Objective]Landslide-displacement prediction is critical when evaluating landslide stability.Despite the achievements of time-series methods based on deep-learning paradigms in predicting landslide displacement,the nonstationary,periodic,and trending characteristics of landslide displacement data cause multivariate predictions of current time-series models to easily overfit.Existing studies primarily focus on improving single models,whereas systematic studies pertaining to multimodel integration methods are scarce.This study aims to develop an integrated model that addresses these challenges and improves prediction accuracy.[Methods]Considering the volatility of landslidedisplacement data and the combined characteristics of their periodic and trending displacement components,a landslidedisplacement prediction model combining isolation forest(IF)anomaly detection,ensemble empirical mode decomposition(EEMD),convolutional neural networks(CNNs),and long short-term memory(LSTM)neural networks is proposed.The stepped Baijiabao landslide in the Three Gorges Reservoir area,which is affected by rainfall,is investigated in this study.First,the IF algorithm is introduced to detect anomalies in the original landslide-displacement data.This enables outliers,which can distort the prediction results,to be identified and excluded.Subsequently,EEMD is adopted to decompose the displacement data into intrinsic mode functions(IMFs),which represent the underlying periodic and trend components.This decomposition allows one to analyze the inherent characteristics of the data more comprehensively.Next,a CNN is employed to capture local periodic and trend patterns within the IMFs.CNNs are particularly effective in recognizing spatial patterns and features,thus rendering them suitable for identifying complex patterns in the displacement data.Finally,the overall displacement is predicted using the LSTM model,which is suitable for accommodating sequential data and capturing long-term dependencies.These techniques are integrated to leverage

关 键 词：滑坡位移预测 时间序列模型 卷积神经网络 集合经验模态分解 深度学习 

分 类 号：P642.22[天文地球—工程地质学] P232[天文地球—地质矿产勘探]