Combining Numerical Simulation and Deep Learning for Landslide Displacement Prediction: An Attempt to Expand the Deep Learning Dataset

被引:15
作者
Xu, Wenhan [1 ,2 ]
Xu, Hong [1 ]
Chen, Jie [2 ]
Kang, Yanfei [1 ,2 ,3 ]
Pu, Yuanyuan [2 ]
Ye, Yabo [2 ]
Tong, Jue [2 ]
机构
[1] Minist Nat Resources, Chongqing Engn Res Ctr Automat Monitoring Geol Ha, Technol Innovat Ctr Geohazards Automat Monitoring, Chongqing 401120, Peoples R China
[2] Chongqing Univ, State Key Lab Coal Mine Disaster Dynam & Control, Chongqing 400044, Peoples R China
[3] Chongqing Univ, Sch Civil Engn, Chongqing 400044, Peoples R China
基金
中国国家自然科学基金;
关键词
landslide displacements; deep learning; numerical simulations; time series similarity; 3 GORGES RESERVOIR; TIME-SERIES ANALYSIS; MEMORY NEURAL-NETWORK; BAIJIABAO LANDSLIDE; MODE DECOMPOSITION; FAILURE; SUSCEPTIBILITY; ALGORITHMS; AREA;
D O I
10.3390/su14116908
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Effective landslide hazard prevention requires accurate landslide prediction models, and the data-driven approaches based on deep learning models are gradually becoming a hot research topic. When training deep learning models, it is always preferable to have a large dataset, while most available landslide monitoring data are limited. For data missing or data sparseness problems, conventional interpolation methods based on mathematical knowledge lack mechanism interpretability. This paper proposes that numerical simulations can be used to expand the deep learning dataset we need. Taking the Jiuxianping landslide in the Three Gorges Reservoir Area (TGRA) as the geological background, a finite element numerical model was established, and the landslide displacement time series data were solved considering the boundary conditions of reservoir water level change and precipitation. Next, based on three metrics: Euclidean distance, cosine similarity, and dynamic time warping (DTW) distance, the time series similarity between the displacement data obtained from simulation and data obtained from actual monitoring were verified. Finally, the combined deep learning model was built to predict the displacement of the Jiuxianping landslide. The model was trained on both the simulated and monitored datasets and tested by the last 12 monitored data points. Prediction results with the testing set showed that the models trained using the expanded training set from numerical simulations exhibited lower prediction errors, and the errors had a more concentrated distribution. The results suggest that this landslide displacement prediction method combining numerical simulation and deep learning can solve the problem of inadequate datasets due to low monitoring frequency, as well as provide an interpretation of the physical mechanism for data vacancy filling.
引用
收藏
页数:20
相关论文
共 61 条
[41]   A CLOSED-FORM EQUATION FOR PREDICTING THE HYDRAULIC CONDUCTIVITY OF UNSATURATED SOILS [J].
VANGENUCHTEN, MT .
SOIL SCIENCE SOCIETY OF AMERICA JOURNAL, 1980, 44 (05) :892-898
[42]   Hybrid Machine Learning Approaches for Landslide Susceptibility Modeling [J].
Vu Viet Nguyen ;
Binh Thai Pham ;
Ba Thao Vu ;
Prakash, Indra ;
Jha, Sudan ;
Shahabi, Himan ;
Shirzadi, Ataollah ;
Dong Nguyen Ba ;
Kumar, Raghvendra ;
Chatterjee, Jyotir Moy ;
Dieu Tien Bui .
FORESTS, 2019, 10 (02)
[43]   A new hybrid method for establishing point forecasting, interval forecasting, and probabilistic forecasting of landslide displacement [J].
Wang, Hong ;
Long, Guangyu ;
Liao, Jianxing ;
Xu, Yan ;
Lv, Yan .
NATURAL HAZARDS, 2022, 111 (02) :1479-1505
[44]   Research on the impact of the water-level-fluctuation zone on landslide stability in the Three Gorges Reservoir Area [J].
Wang, Hongde ;
Yang, Qiang ;
Pan, Shuhua ;
Ding, Weicui ;
Gao, Youlong .
APPLIED MECHANICS AND CIVIL ENGINEERING II, 2012, 188 :37-+
[45]   A hybrid intelligent approach for constructing landslide displacement prediction intervals [J].
Wang, Yankun ;
Tang, Huiming ;
Wen, Tao ;
Ma, Junwei .
APPLIED SOFT COMPUTING, 2019, 81
[46]   Interval Estimation of Landslide Displacement Prediction Based on Time Series Decomposition and Long Short-Term Memory Network [J].
Xing, Yin ;
Yue, Jianping ;
Chen, Chuang .
IEEE ACCESS, 2020, 8 :3187-3196
[47]   Unsaturated slope stability around the Three Gorges Reservoir under various combinations of rainfall and water level fluctuation [J].
Xiong, Xi ;
Shi, Zhenming ;
Xiong, Yonglin ;
Peng, Ming ;
Ma, Xiaolong ;
Zhang, Feng .
ENGINEERING GEOLOGY, 2019, 261
[48]   GIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China [J].
Xu, Chong ;
Dai, Fuchu ;
Xu, Xiwei ;
Lee, Yuan Hsi .
GEOMORPHOLOGY, 2012, 145 :70-80
[49]   Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area, China [J].
Xu, Shiluo ;
Niu, Ruiqing .
COMPUTERS & GEOSCIENCES, 2018, 111 :87-96
[50]   Time series analysis and long short-term memory neural network to predict landslide displacement [J].
Yang, Beibei ;
Yin, Kunlong ;
Lacasse, Suzanne ;
Liu, Zhongqiang .
LANDSLIDES, 2019, 16 (04) :677-694