Abstract
A good prediction of landslide displacement is an essential component for implementing an early warning system. In the Three Gorges Reservoir Area (TGRA), many landslides deform distinctly and in steps from April to September each year under the influence of seasonal rainfall and periodic fluctuation in reservoir water level. The sliding becomes more uniform again from October to April. This landslide deformation pattern leads to accumulated displacement versus time showing a step-wise curve. Most of the existing predictive models express static relationships only. However, the evolution of a landslide is a complex nonlinear dynamic process. This paper proposes a dynamic model to predict landslide displacement, based on time series analysis and long short-term memory (LSTM) neural network. The accumulated displacement was decomposed into a trend term and a periodic term in the time series analysis. A cubic polynomial function was selected to predict the trend displacement. By analyzing the relationships between landslide deformation, rainfall, and reservoir water level, a LSTM model was used to predict the periodic displacement. The LSTM approach was found to properly model the dynamic characteristics of landslides than static models, and make full use of the historical information. The performance of the model was validated with the observations of two step-wise landslides in the TGRA, the Baishuihe landslide and Bazimen landslide. The application of the model to those two landslides demonstrates that the LSTM model provides a good representation of the measured displacements and gives a more reliable prediction of landslide displacement than the static support vector machine (SVM) model. It is concluded that the proposed model can be used to effectively predict the displacement of step-wise landslides in the TGRA.
Similar content being viewed by others
Notes
In supervised machine learning, the percentages of train set and validation set can usually be 50% and 50%. But when the dataset is not large, this division may be not reasonable. As the displacement is measured on a monthly cycle, only 125 and 113 measured values can be obtained from the GPS monitoring points of the two landslides. For similar size of database (73 data points), Xu and Niu (2018) divided the trainset into two part: 70% for training and 30% for validation and got a well-trained LSTM model. This division was selected for this study.
References
Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. Neural Netw IEEE Trans 5(2):157–166
Bogaard T, Greco R (2018) Invited perspectives: hydrological perspectives on precipitation intensity-duration thresholds for landslide initiation: proposing hydrometeorological thresholds. Nat Hazard Earth Sys 18(1):31–39
Cao Y, Yin K, Alexander DE, Zhou C (2016) Using an extreme learning machine to predict the displacement of step-like landslides in relation to controlling factors. Landslides 13(4):725–736
Chen S, Chou W (2012) Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach. The 15th International IEEE Conference on Intelligent, pp. 1821–1826
China Institute of Geo-Environment Monitoring (2017) Bulletin of geologic hazards from January to December in 2016. China Institute of Geo-Environment Monitoring, Beijing
Corominas J, Moya J, Ledesma A, Lloret A, Gili JA (2005) Prediction of ground displacements and velocities from groundwater level changes at the Vallcebre landslide (Eastern Pyrenees, Spain). Landslides 2(2):83–96
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
Du J, Yin K, Lacasse S (2013) Displacement prediction in colluvial landslides, Three Gorges Reservoir, China. Landslides 10(2):203–218
Eberhart R, Kennedy J (1995) A new optimizer using particle swarm theory. Proceedings of the 6th International Symposium on Micro Machine and Human Science. Nagoya, Japan, IEEE, pp 39–43
Fan Y, Qian Y, Xie F, Soong FK (2014) TTS synthesis with bidirectional LSTM based recurrent neural networks. Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH):1964–1968
Fan X, Xu Q, Scaringi G, Dai L, Li W, Dong X, Zhu X, Pei X, Dai K, Havebith HB (2017) Failure mechanism and kinematics of the deadly June 24th 2017 Xinmo landslide, Maoxian, Sichuan, China. Landslides 14(6):2129–2146
Fan X, Xu Q, Scaringi G (2018) Brief communication: post-seismic landslides, the tough lesson of a catastrophe. Nat Hazards Earth Syst Sci 18:397–403
Felix A, Jürgen S (2000) Recurrent nets that time and count. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, pp 3:189–194
Froude M, Petley D (2018) Global fatal landslide occurrence from 2004 to 2016. Nat Hazards Earth Syst Sci 18(8):2161–2181
Glade T, Anderson M, Crozier MJ (2005) Landslide hazard and risk: issues, concepts and approach. In: Landslide hazard and risk. Wiley, Hoboken, pp 1–40
Graves A, Mohamed A, Hinton G (2013) Speech recognition with deep recurrent neural networks. Proceedings of the International Conference on Acoustics, Speech and Signal Processing Acoustics, pp. 6645–6649
Han M, Xi J, Xu S, Yin F (2004) Prediction of chaotic time series based on the recurrent predictor neural network. IEEE Trans Signal Process 52(12):3409–3416
Haque U, Blum P, da Silva PF, Andersen P, Pilz J, Chalov SR, Malet JP, Auflič MJ, Andres N, Poyiadji E, Lamas PC, Zhang W, Peshevski I, Pétursson HG, Kurt T, Dobrev N, García-Davalillo JC, Halkia M, Ferri S, Gaprindashvili G, Engström J, Keellings D (2016) Fatal landslides in Europe. Landslides 13(6):1545–1554
Hasim S, Andrew S, Francoise B (2014) Long short-term memory recurrent neural network architectures for large scale acoustic modeling. Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 338–342
Helmstetter A, Sornette D, Grasso J et al (2004) Slider block friction model for landslides: application to Vaiont and La Clapiere landslides. J Geophys Res 109(B2):1–15
Hochreite S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Hong H, Pourghasemi H, Pourtaghi Z (2016) Landslide susceptibility assessment in Lianhua County (China): a comparison between a random forest data mining technique and bivariate and multivariate statistical models. Geomorphology 259:105–118
Hsu C, Chang C, Lin C (2010). A practical guide to support vector classification. Technical Report, National Taiwan University
Huang F, Yin K, Zhang G, Gui L, Yang B, Liu L (2016) Landslide displacement prediction using discrete wavelet transform and extreme learning machine based on chaos theory. Environ Earth Sci 75:1376–1394
Huang F, Huang J, Jiang S, Zhou C (2017) Landslide displacement prediction based on multivariate chaotic model and extreme learning machine. Eng Geol 218:173–186
Hyndman RJ, Koehler AB (2006) Another look at measures of forecast accuracy. Int J Forecast 22(4):679–688
Kayacan E, Ulutas B, Kaynak O (2010) Grey system theory-based models in time series prediction. Expert Syst Appl 37:1784–1789
Li H, Xu Q, He Y, Deng J (2018) Prediction of landslide displacement with an ensemble-based extreme learning machine and copula models. Landslides 15:2047–2059
Lian C, Zeng Z, Yao W, Tang H (2015) Multiple neural networks switched prediction for landslide displacement. Eng Geol 186:91–99
Liu B, Shao J, Xu W, Chen H, Shi C (2014) Comparison on landslide nonlinear displacement analysis and prediction with computational intelligence approaches. Landslides 11(5):889–896
Liu Y, Qin Z, Hu B, Feng S (2018) State fusion entropy for continuous and site-specific analysis of landslide stability changing regularities. Nat Hazards Earth Syst Sci 18:1187–1199
Ma X, Tao Z, Wang Y, Yu H, Wang Y (2015) Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transp Res Part C Emerg Technol 54:187–197
Ma J, Tang H, Liu X, Hu X, Sun M, Song Y (2017) Establishment of a deformation forecasting model for a step-like landslide based on decision tree C5.0 and two-step cluster algorithms: a case study in the Three Gorges Reservoir area, China. Landslides 14(3):1275–1281
Miao H, Wang G, Yin K, Kamai T, Li Y (2014) Mechanism of the slow-moving landslides in Jurassic red-strata in the Three Gorges Reservoir, China. Eng Geol 171:59–69
Miao F, Wu Y, Xie Y, Li Y (2018) Prediction of landslide displacement with step-like behavior based on multialgorithm optimization and a support vector regression model. Landslides 15(3):475–488
Mufundirwa A, Fujii Y, Kodama J (2010) A new practical method for prediction of geomechanical failure-time. Int J Rock Mech Min Sci 47(7):1079–1090
Qin S, Jiao J, Wang S (2002) A nonlinear dynamical model of landslide evolution. Geomorphology 43(1–2):77–85
Reichenbach P, Rossi M, Malamud B, Mihir M, Guzzetti F (2018) A review of statistically-based landslide susceptibility models. Earth-Sci Rev 180:60–91
Reimers N, Gurevych I (2017). Optimal hyperparameters for deep LSTM-networks for sequence labeling tasks. arXiv preprint arXiv:1707.06799
Roering J, Mackey B, Handwerger A et al (2015) Beyond the angle of repose: a review and synthesis of landslide processes in response to rapid uplift, Eel River, Northern California. Geomorphology 236:109–131
Saito M (1965) Forecasting the time of occurrence of a slope failure. In: Proceedings of the 6th International Mechanics and Foundation Engineering pp: 537–541
Scaringi G, Fan X, Xu Q, Liu C, Ouyang C, Domènech G, Yang F, Dai L (2018) Some considerations on the use of numerical methods to simulate past landslides and possible new failures: the case of the recent Xinmo landslide (Sichuan, China). Landslides 15:1359–1375
Smola A, Scholkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222
Tan F, Hu X, He C, Zhang Y, Zhang H, Zhou C, Wang Q (2018) Identifying the main control factors for different deformation stages of landslide. Geotech Geo Eng 36(1):469–482
Thiebers (2014) Integration of a limit-equilibrium model into a landslide early warning system. Landslides 11(5):859–875
Tomas R, Li Z, Liu P, Singleton A, Hoey T, Cheng X (2014) Spatiotemporal characteristics of the Huangtupo landslide in the Three Gorges region (China) constrained by radar interferometry. Geophys J Int 197(1):213–232
Vincent P, Larochelle H, Lajoie I et al (2010) Stacked denoising autoencoders: learning useful representation in a deep network with a local denoising criterion. J Mach Learn Res 11(12):3371–3408
Xu S, Niu R (2018) Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorge area, China. Comput Geosci 111:87–96
Yang B, Yin K, Xiao T, Chen L, Du J (2017) Annual variation of landslide stability under the effect of water level fluctuation and rainfall in the Three Gorges Reservoir, China. Environ Earth Sci 76:564–580
Yao W, Zeng Z, Lian C, Tang H (2015) Training enhanced reservoir computing predictor for landslide displacement. Eng Geol 188:101–109
Yin Y, Huang B, Wang W, Wei Y, Ma X, Ma F, Zhao C (2016) Reservoir-induced landslides and risk control in Three Gorges project on Yangtze river, China. J Rock Mech Geotech Eng 8(5):577–595
Zhang H, Huang X (2018) Trend and spatiotemporal distribution of fatal landslides triggered by non-seismic effects in China. Landslides 15:1663–1674
Zhou C, Yin K, Cao Y, Ahmed B (2016) Application of time series analysis and PSO-SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China. Eng Geol 204:108–120
Zhou C, Yin K, Cao Y, Intrieri E, Ahmed B, Catani F (2018a) Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method. Landslides 15:2211–2225. https://doi.org/10.1007/s10346-018-1022-0
Zhou C, Yin K, Cao Y, Ahmed B, Li Y, Catani F, Pourghasemie HR (2018b) Landslide susceptibility modeling applying machine learning methods: a case study from Longju in the Three Gorges Reservoir area, China. Comput Geosci 112:23–27
Acknowledgments
The authors wish to thank Dr. Du Juan, Dr. Huang Faming, Dr. Miao Fasheng, and Dr. Zhou Chao for their assistance in collecting the data.
Funding
This research was supported by the National Natural Sciences Foundation of China (no. 41572292) and the Research Council of Norway (Klima 2050). The first author wishes to thank the China Scholarship Council (CSC) and the Norwegian Geotechnical Institute (NGI) for funding her research period at NGI.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yang, B., Yin, K., Lacasse, S. et al. Time series analysis and long short-term memory neural network to predict landslide displacement. Landslides 16, 677–694 (2019). https://doi.org/10.1007/s10346-018-01127-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-018-01127-x