Recurrent neural networks for complicated seismic dynamic response prediction of a slope system

Abstract Earthquake-induced landslides have resulted in huge casualties and considerable financial repercussions, and slope dynamic response analysis has always been a hot issue. The prediction of the dynamic response of a slope before the occurrence of future earthquakes will benefit disaster prevention and reduction. Traditional methods (such as the finite element method) are mostly based on simplified physical mechanisms and cannot accurately predict the dynamic response of complicated slope systems. This article innovatively applies novel recurrent neural networks to the prediction of the slope dynamic response. Using the results of large-scale shaking-table tests, we introduced a moving-steps strategy and established three recurrent neural network models: Simple-RNN, LSTM and GRU models. Moreover, a multi-layer perceptron prediction model was trained for comparative verification. We also conducted three experiments to investigate the effect of the data volume on the models. Results show that recurrent neural networks perform well in the analysis of the seismic dynamic response of a slope and provide better predictions than the multi-layer perceptron network. When there are many data, the LSTM and GRU models have advantages, and the confidence indexes of their predictions with normalized error within ±5% are 84.5% and 86.4%, respectively. It is concluded that recurrent neural networks are suitable for the time-series prediction of dynamic responses to seismic loads. To some extent, this paper may help reduce the future risks and losses of earthquake-triggered landslide disasters.

[1]  K. Yin,et al.  Time series analysis and long short-term memory neural network to predict landslide displacement , 2019, Landslides.

[2]  P. Samui.  Slope stability analysis: a support vector machine approach , 2008 .

[3]  Changjun Zhou,et al.  Forecasting stock prices with long-short term memory neural network based on attention mechanism , 2020, PloS one.

[4]  Jian Zhou,et al.  Slope stability prediction for circular mode failure using gradient boosting machine approach based on an updated database of case histories , 2019, Safety Science.

[5]  Changwei Yang,et al.  Shaking Table Test on Dynamic Response of Bedding Rock Slopes With Weak Structural Plane Under Earthquake , 2020, Frontiers in Physics.

[6]  C. Westen,et al.  Distribution pattern of earthquake-induced landslides triggered by the 12 May 2008 Wenchuan earthquake , 2010 .

[7]  Ruiyang Zhang,et al.  Deep long short-term memory networks for nonlinear structural seismic response prediction , 2019, Computers & Structures.

[8]  Miao Yu,et al.  Review of soil liquefaction characteristics during major earthquakes of the twenty-first century , 2013, Natural Hazards.

[9]  XinHua Xue,et al.  Application of a support vector machine for prediction of slope stability , 2014 .

[10]  Danial Jahed Armaghani,et al.  Evaluating Slope Deformation of Earth Dams Due to Earthquake Shaking Using MARS and GMDH Techniques , 2020, Applied Sciences.

[11]  Ping Sun,et al.  Landslide hazards triggered by the 2008 Wenchuan earthquake, Sichuan, China , 2009 .

[12]  K. Allstadt,et al.  Earthquake‐Induced Chains of Geologic Hazards: Patterns, Mechanisms, and Impacts , 2019, Reviews of Geophysics.

[13]  Nikos D. Lagaros,et al.  Computationally efficient seismic fragility analysis of geostructures , 2009 .

[14]  S. Lacasse,et al.  Algorithms for intelligent prediction of landslide displacements , 2020, Journal of Zhejiang University-SCIENCE A.

[15]  Li Min Zhang,et al.  Impact of the 2008 Wenchuan Earthquake in China on Subsequent Long-Term Debris Flow Activities in the Epicentral Area , 2017 .

[16]  Ritika Singh,et al.  Stock prediction using deep learning , 2016, Multimedia Tools and Applications.

[17]  Mahdi Hasanipanah,et al.  A Monte Carlo technique in safety assessment of slope under seismic condition , 2017, Engineering with Computers.

[18]  Liu Yang,et al.  Inverse Analysis of Rock Creep Model Parameters Based on Improved Simulated Annealing Differential Evolution Algorithm , 2018, Geotechnical and Geological Engineering.

[19]  Li Tong-chun.  Slope aseismic stability analysis method based on static and dynamic finite elements , 2010 .

[20]  Bahareh Kalantar,et al.  Machine-Learning-Based Classification Approaches toward Recognizing Slope Stability Failure , 2019, Applied Sciences.

[21]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[22]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[23]  P. Samui,et al.  Slope Stability Analysis Using Rf, Gbm, Cart, Bt and Xgboost , 2021, Geotechnical and Geological Engineering.

[24]  Qiang Xu,et al.  Effect of lithology and structure on seismic response of steep slope in a shaking table test , 2014, Journal of Mountain Science.

[25]  Yoshua Bengio,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2010, AISTATS.

[26]  Yong Yu,et al.  A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures , 2019, Neural Computation.

[27]  Jian-jing Zhang,et al.  Shaking table test of seismic responses of anchor cable and lattice beam reinforced slope , 2020, Journal of Mountain Science.

[28]  Nhat-Duc Hoang,et al.  Hybrid artificial intelligence approach based on metaheuristic and machine learning for slope stability assessment: A multinational data analysis , 2016, Expert Syst. Appl..

[29]  Branko Glisic,et al.  Neural network-based seismic response prediction model for building structures using artificial earthquakes , 2020 .

[30]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[31]  Zhigang Zeng,et al.  Landslide Deformation Prediction Based on Recurrent Neural Network , 2013, Neural Processing Letters.

[32]  Michael Sakellariou,et al.  A study of slope stability prediction using neural networks , 2005 .

[33]  Masoud Monjezi,et al.  Prediction of seismic slope stability through combination of particle swarm optimization and neural network , 2015, Engineering with Computers.

[34]  Hyo Seon Park,et al.  Convolutional neural network-based safety evaluation method for structures with dynamic responses , 2020, Expert Syst. Appl..

[35]  Yang Liu,et al.  Physics-guided Convolutional Neural Network (PhyCNN) for Data-driven Seismic Response Modeling , 2019, Engineering Structures.

[36]  Yu Huang,et al.  Stochastic seismic response of a slope based on large-scale shaking-table tests , 2020 .

[37]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[38]  Hao Lei,et al.  Shaking Table Tests for Seismic Response of Oblique Overlapped Tunnel , 2021 .

[39]  Hongyuan Liu,et al.  Experimental study on failure behaviour of deep tunnels under high in-situ stresses , 2015 .

[40]  Kongming Yan,et al.  Dynamic Response and Dynamic Failure Mode of a Weak Intercalated Rock Slope Using a Shaking Table , 2016, Rock Mechanics and Rock Engineering.

[41]  Yusuf Erzin,et al.  The use of neural networks for the prediction of the critical factor of safety of an artificial slope subjected to earthquake forces , 2012 .

[42]  B. Pradhan,et al.  Assessment of earthquake-induced slope deformation of earth dams using soft computing techniques , 2018, Landslides.

[43]  B. Khazai,et al.  Evaluation of factors controlling earthquake-induced landslides caused by Chi-Chi earthquake and comparison with the Northridge and Loma Prieta events , 2004 .

[44]  Nikos D. Lagaros,et al.  Simulating the seismic response of embankments via artificial neural networks , 2009, Adv. Eng. Softw..

[45]  Meei-Ling Lin,et al.  Seismic slope behavior in a large-scale shaking table model test , 2006 .

[46]  Danial Jahed Armaghani,et al.  Applying various hybrid intelligent systems to evaluate and predict slope stability under static and dynamic conditions , 2019, Soft Comput..

[47]  Tugrul U. Daim,et al.  Using artificial neural network models in stock market index prediction , 2011, Expert Syst. Appl..

[48]  Q. Jiang,et al.  Shaking Table Model Test on the Dynamic Response of Anti-dip Rock Slope , 2018, Geotechnical and Geological Engineering.

[49]  Hyeonjoon Moon,et al.  Background Information of Deep Learning for Structural Engineering , 2017 .