Deep seated Landslides are very dangerous geological events that pose a substantial menace to human life and property. The phenomenon is occurring with increasing frequency and potential presence due to the continuous change in weather conditions caused by global warming. The hidden nature of this dangerous phenomenon is becoming more pronounced. Therefore, constructing an early warning system for short-term forecasting of displacement in deep-seated slopes is critical for preventing property loss and hazards. In this study, a framework for deep slope displacement forecasting was proposed, utilizing numerous neural networks which are Artificial Neural Networks (ANNs), Deep Neural Networks (DNNs), 1D-Convolutional Neural Networks (1D-CNNs) model and three different deep learning time series: Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs) and 8-years hourly collected data from Northern Slope Lushan mountain area which situated on the right bank of the Talowan River in central Taiwan as a specific research case. Two displacement datasets measured at 40m and 70m combine with groundwater measure value at multiple stations, were respectively divide into two subsets: 90% for learning and 10% for testing. To be more particular, the deep displacement of the slope will be associated with a groundwater storage phenomenon and forecasted using direct multi-step window sliding - a numerical time series related technique that involves the creation of individual models for each step in the forecast horizon, the processed numerical data were then fed into the suggested deep learning models. The best individual models after training process were then will be used to construct a slope landslide early warning system. The results indicated that the deep learning approach provided stability and effectively avoided overfitting, with RNNs model show best forecasting ability with MAPE in both selected forecasting depths. Thus, providing a reliable result for the purpose of constructing management strategies can significantly contribute to road network and infrastructure system in Lushan hot spring slope area in Taiwan which ensuring adequate serviceability for this economic area.

[1] A. Ageenko, L. C. Hansen, K. L. Lyng, L. Bodum, and J. J. Arsanjani, "Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study," ISPRS International Journal of Geo-Information, vol. 11, no. 6, 2022, doi: 10.3390/ijgi11060324.
[2] J. Novotný, "Varnes landslide classification," 1978.
[3] S. Das, S. Sarkar, and D. P. Kanungo, "Rainfall-induced landslide (RFIL) disaster in Dima Hasao, Assam, Northeast India," Landslides, vol. 19, no. 11, pp. 2801-2808, 2022/11/01 2022, doi: 10.1007/s10346-022-01962-z.
[4] J. Dou, U. Paudel, T. Oguchi, S. Uchiyama, and Y. Hayakawa, "Shallow and Deep-Seated Landslide Differentiation Using Support Vector Machines: A Case Study of the Chuetsu Area, Japan," Terrestrial Atmospheric and Oceanic Sciences, 05/05 2015, doi: 10.3319/TAO.2014.12.02.07(EOSI).
[5] B. Thai Pham et al., "Landslide Susceptibility Assessment by Novel Hybrid Machine Learning Algorithms," Sustainability, vol. 11, no. 16, 2019, doi: 10.3390/su11164386.
[6] F. Cotecchia, F. Santaloia, and V. Tagarelli, "Towards A Geo-Hydro-Mechanical Characterization of Landslide Classes: Preliminary Results," Applied Sciences, vol. 10, no. 22, doi: 10.3390/app10227960.
[7] B. M. Marrapu and R. S. Jakka, "Landslide hazard zonation methods: A critical Review," Int J Civ Eng Res, vol. 5, no. 3, pp. 215-20, 2014.
[8] B.-G. Chae, H. J. Park, F. Catani, A. Simoni, and M. Berti, "Landslide prediction, monitoring and early warning: a concise review of state-of-the-art," Geosciences Journal, vol. 21, pp. 1033-1070, 12/01 2017, doi: 10.1007/s12303-017-0034-4.
[9] C. Zhou, K. Yin, Y. Cao, B. Ahmed, and X. Fu, "A novel method for landslide displacement prediction by integrating advanced computational intelligence algorithms," Scientific Reports, vol. 8, no. 1, p. 7287, 2018/05/08 2018, doi: 10.1038/s41598-018-25567-6.
[10] L. Alzubaidi et al., "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions," Journal of Big Data, vol. 8, no. 1, p. 53, 2021/03/31 2021, doi: 10.1186/s40537-021-00444-8.
[11] K. Sim, M. Lee, and S. Y. Wong, "A review of landslide acceptable risk and tolerable risk," Geoenvironmental Disasters, vol. 9, 01/25 2022, doi: 10.1186/s40677-022-00205-6.
[12] D. N. Petley, F. Mantovani, M. H. Bulmer, and A. Zannoni, "The use of surface monitoring data for the interpretation of landslide movement patterns," Geomorphology, vol. 66, no. 1, pp. 133-147, 2005/03/01/ 2005, doi: https://doi.org/10.1016/j.geomorph.2004.09.011.
[13] H. Keqiang, W. Zhiliang, M. Xiaoyun, and L. Zengtao, "Research on the displacement response ratio of groundwater dynamic augment and its application in evaluation of the slope stability," Environmental Earth Sciences, vol. 74, no. 7, pp. 5773-5791, 2015/10/01 2015, doi: 10.1007/s12665-015-4595-0.
[14] G. Preisig, "Forecasting the long-term activity of deep-seated landslides via groundwater flow and slope stability modelling," Landslides, vol. 17, no. 7, pp. 1693-1702, 2020/07/01 2020, doi: 10.1007/s10346-020-01427-1.
[15] S. Srivastava, N. Anand, S. Sharma, S. Dhar, and L. K. Sinha, "Monthly Rainfall Prediction Using Various Machine Learning Algorithms for Early Warning of Landslide Occurrence," in 2020 International Conference for Emerging Technology (INCET), 5-7 June 2020 2020, pp. 1-7, doi: 10.1109/INCET49848.2020.9154184.
[16] Y.-F. Lee and Y.-Y. Chi, "Rainfall-induced landslide risk at Lushan, Taiwan," Engineering Geology, vol. 123, no. 1, pp. 113-121, 2011/11/11/ 2011, doi: https://doi.org/10.1016/j.enggeo.2011.03.006.
[17] H.-H. Lin, M.-L. Lin, J.-H. Lu, C.-C. Chi, and L. Y. Fei, "Deep-seated gravitational slope deformation in Lushan, Taiwan: Transformation from cleavage-controlled to weakened rockmass-controlled deformation," Engineering Geology, vol. 264, p. 105387, 2020/01/01/ 2020, doi: https://doi.org/10.1016/j.enggeo.2019.105387.
[18] G. B. Crosta and F. Agliardi, "Failure forecast for large rock slides by surface displacement measurements," Canadian Geotechnical Journal, vol. 40, no. 1, pp. 176-191, 2003/02/01 2003, doi: 10.1139/t02-085.
[19] J. Xu et al., "Field investigation of force and displacement within a strata slope using a real-time remote monitoring system," Environmental Earth Sciences, vol. 77, no. 15, p. 552, 2018/07/27 2018, doi: 10.1007/s12665-018-7729-3.
[20] A. Mufundirwa, Y. Fujii, and J. Kodama, "A new practical method for prediction of geomechanical failure-time," International Journal of Rock Mechanics and Mining Sciences, vol. 47, no. 7, pp. 1079-1090, 2010/10/01/ 2010, doi: https://doi.org/10.1016/j.ijrmms.2010.07.001.
[21] J.-H. Wu, "Seismic landslide simulations in discontinuous deformation analysis," Computers and Geotechnics, vol. 37, no. 5, pp. 594-601, 2010/07/01/ 2010, doi: https://doi.org/10.1016/j.compgeo.2010.03.007.
[22] J. Jiang et al., "Numerical simulation of Qiaotou Landslide deformation caused by drawdown of the Three Gorges Reservoir, China," Environmental Earth Sciences, vol. 62, no. 2, pp. 411-419, 2011/01/01 2011, doi: 10.1007/s12665-010-0536-0.
[23] W. Fu and Y. Liao, "Non-linear shear strength reduction technique in slope stability calculation," Computers and Geotechnics, vol. 37, no. 3, pp. 288-298, 2010/04/01/ 2010, doi: https://doi.org/10.1016/j.compgeo.2009.11.002.
[24] T. Peternel, M. Janža, E. Šegina, N. Bezak, and M. Maček, "Recognition of Landslide Triggering Mechanisms and Dynamics Using GNSS, UAV Photogrammetry and In Situ Monitoring Data," Remote Sensing, vol. 14, no. 14, doi: 10.3390/rs14143277.
[25] J. Corominas et al., "Recommendations for the quantitative analysis of landslide risk," Bulletin of Engineering Geology and the Environment, vol. 73, no. 2, pp. 209-263, 2014/05/01 2014, doi: 10.1007/s10064-013-0538-8.
[26] H. Li, Q. Xu, Y. He, and J. Deng, "Prediction of landslide displacement with an ensemble-based extreme learning machine and copula models," Landslides, vol. 15, no. 10, pp. 2047-2059, 2018/10/01 2018, doi: 10.1007/s10346-018-1020-2.
[27] C. Liu, Z. Jiang, X. Han, and W. Zhou, "Slope displacement prediction using sequential intelligent computing algorithms," Measurement, vol. 134, pp. 634-648, 2019/02/01/ 2019, doi: https://doi.org/10.1016/j.measurement.2018.10.094.
[28] A. Aggarwal, M. Alshehri, M. Kumar, O. Alfarraj, P. Sharma, and K. R. Pardasani, "Landslide data analysis using various time-series forecasting models," Computers & Electrical Engineering, vol. 88, p. 106858, 2020/12/01/ 2020, doi: https://doi.org/10.1016/j.compeleceng.2020.106858.
[29] X. Hu et al., "Landslide displacement prediction using kinematics-based random forests method: A case study in Jinping Reservoir Area, China," Engineering Geology, vol. 283, p. 105975, 2021/03/20/ 2021, doi: https://doi.org/10.1016/j.enggeo.2020.105975.
[30] L. Zhang, B. Shi, H. Zhu, X. B. Yu, H. Han, and X. Fan, "PSO-SVM-based deep displacement prediction of Majiagou landslide considering the deformation hysteresis effect," Landslides, vol. 18, no. 1, pp. 179-193, 2021/01/01 2021, doi: 10.1007/s10346-020-01426-2.
[31] B. Hu, G. Su, J. Jiang, J. Sheng, and J. Li, "Uncertain Prediction for Slope Displacement Time-Series Using Gaussian Process Machine Learning," IEEE Access, vol. PP, pp. 1-1, 01/31 2019, doi: 10.1109/ACCESS.2019.2894807.
[32] W. Zhang et al., "State-of-the-art review of soft computing applications in underground excavations," Geoscience Frontiers, vol. 11, no. 4, pp. 1095-1106, 2020/07/01/ 2020, doi: https://doi.org/10.1016/j.gsf.2019.12.003.
[33] Y. Fu, M. Lin, Y. Zhang, G. Chen, and Y. Liu, "Slope stability analysis based on big data and convolutional neural network," Frontiers of Structural and Civil Engineering, vol. 16, no. 7, pp. 882-895, 2022/07/01 2022, doi: 10.1007/s11709-022-0859-4.
[34] H. Pei, F. Meng, and H. Zhu, "Landslide displacement prediction based on a novel hybrid model and convolutional neural network considering time-varying factors," Bulletin of Engineering Geology and the Environment, vol. 80, no. 10, pp. 7403-7422, 2021/10/01 2021, doi: 10.1007/s10064-021-02424-x.
[35] W. Xu et al., "Combining Numerical Simulation and Deep Learning for Landslide Displacement Prediction: An Attempt to Expand the Deep Learning Dataset," Sustainability, vol. 14, no. 11, doi: 10.3390/su14116908.
[36] B. Yang, K. Yin, S. Lacasse, and Z. Liu, "Time series analysis and long short-term memory neural network to predict landslide displacement," Landslides, vol. 16, 01/15 2019, doi: 10.1007/s10346-018-01127-x.
[37] J. Xu, Y. Jiang, and C. Yang, "Landslide Displacement Prediction during the Sliding Process Using XGBoost, SVR and RNNs," Applied Sciences, vol. 12, no. 12, doi: 10.3390/app12126056.
[38] S. Yang, A. Jin, W. Nie, C. Liu, and Y. Li, "Research on SSA-LSTM-Based Slope Monitoring and Early Warning Model," Sustainability, vol. 14, no. 16, doi: 10.3390/su141610246.
[39] W. Zhang, H. Li, L. Tang, X. Gu, L. Wang, and L. Wang, "Displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks," Acta Geotechnica, vol. 17, no. 4, pp. 1367-1382, 2022/04/01 2022, doi: 10.1007/s11440-022-01495-8.
[40] I. H. Sarker, "Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions," SN Computer Science, vol. 2, no. 6, p. 420, 2021/08/18 2021, doi: 10.1007/s42979-021-00815-1.
[41] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998, doi: 10.1109/5.726791.
[42] D. Huang, J. He, Y. Song, Z. Guo, X. Huang, and Y. Guo, "Displacement Prediction of the Muyubao Landslide Based on a GPS Time-Series Analysis and Temporal Convolutional Network Model," Remote Sensing, vol. 14, no. 11, doi: 10.3390/rs14112656.
[43] J. L. Elman, "Finding Structure in Time," Cognitive Science, https://doi.org/10.1207/s15516709cog1402_1 vol. 14, no. 2, pp. 179-211, 1990/03/01 1990, doi: https://doi.org/10.1207/s15516709cog1402_1.
[44] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997, doi: 10.1162/neco.1997.9.8.1735.
[45] K. Cho et al., "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation," 2014. [Online]. Available: https://doi.org/10.3115/v1/d14-1179
https://aclanthology.org/D14-1179/.
[46] F. Di Nunno, G. de Marinis, and F. Granata, "Short-term forecasts of streamflow in the UK based on a novel hybrid artificial intelligence algorithm," Scientific Reports, vol. 13, no. 1, p. 7036, 2023/04/29 2023, doi: 10.1038/s41598-023-34316-3.
[47] Y. Xiao, N. Ju, C. He, Z. Xiao, and Z. Ma, "Week-ahead shallow landslide displacement prediction using chaotic models and robust LSTM," (in English), Frontiers in Earth Science, Brief Research Report vol. 10, 2022-September-08 2022, doi: 10.3389/feart.2022.965071.
[48] M. Li, M. Li, Q. Ren, H. Li, and L. Song, "DRLSTM: A dual-stage deep learning approach driven by raw monitoring data for dam displacement prediction," Advanced Engineering Informatics, vol. 51, p. 101510, 2022/01/01/ 2022, doi: https://doi.org/10.1016/j.aei.2021.101510.
[49] M. Abadi et al., "Tensorflow: a system for large-scale machine learning," in Osdi, 2016, vol. 16, no. 2016: Savannah, GA, USA, pp. 265-283.
[50] F. Chollet, "keras," ed, 2015.
[51] J. Han and M. Kamber, Data Mining, Southeast Asia Edition: Concepts and Techniques. Morgan kaufmann, 2006.
[52] L. Al Shalabi and Z. Shaaban, "Normalization as a preprocessing engine for data mining and the approach of preference matrix," in Dependability of Computer Systems, 2006. DepCos-RELCOMEX'06. International Conference on, 2006: IEEE, pp. 207-214.
[53] J.-S. Chou and N.-T. Ngo, "Time series analytics using sliding window metaheuristic optimization-based machine learning system for identifying building energy consumption patterns," Applied Energy, vol. 177, pp. 751-770, 2016/09/01/ 2016, doi: https://doi.org/10.1016/j.apenergy.2016.05.074.
[54] A. Bhatt, W. Ongsakul, N. M. M, and J. G. Singh, "Sliding window approach with first-order differencing for very short-term solar irradiance forecasting using deep learning models," Sustainable Energy Technologies and Assessments, vol. 50, p. 101864, 2022/03/01/ 2022, doi: https://doi.org/10.1016/j.seta.2021.101864.
[55] S. Khan, D. B. Kirschbaum, T. A. Stanley, P. M. Amatya, and R. A. Emberson, "Global Landslide Forecasting System for Hazard Assessment and Situational Awareness," (in English), Frontiers in Earth Science, Original Research vol. 10, 2022-July-04 2022, doi: 10.3389/feart.2022.878996.
[56] (2017). Mountain Slope Monitoring Guidelines of the Geotechnical Society of the Republic of China (TGS-SLOPEM106).
[57] Z. Li, T. Tang, and C. Gao, "Long Short-Term Memory Neural Network Applied to Train Dynamic Model and Speed Prediction," Algorithms, vol. 12, no. 8, doi: 10.3390/a12080173.
[58] H. Lee and J. Song, "Introduction to convolutional neural network using Keras; an understanding from a statistician," Communications for Statistical Applications and Methods, vol. 26, pp. 591-610, 11/30 2019, doi: 10.29220/CSAM.2019.26.6.591.
[59] A. L. van Natijne, T. A. Bogaard, T. Zieher, J. Pfeiffer, and R. C. Lindenbergh, "Machine learning nowcasting of the Vögelsberg deep-seated landslide: why predicting slow deformation is not so easy," EGUsphere, vol. 2022, pp. 1-38, 2022, doi: 10.5194/egusphere-2022-950.
[60] Z. Lin, X. Sun, and Y. Ji, "Landslide Displacement Prediction Model Using Time Series Analysis Method and Modified LSTM Model," Electronics, vol. 11, no. 10, doi: 10.3390/electronics11101519.
[61] Z. Lin, X. Sun, and Y. Ji, "Landslide Displacement Prediction Based on Time Series Analysis and Double-BiLSTM Model," International Journal of Environmental Research and Public Health, vol. 19, no. 4, doi: 10.3390/ijerph19042077.
[62] Y.-g. Zhang, J. Tang, Z.-y. He, J. Tan, and C. Li, "A novel displacement prediction method using gated recurrent unit model with time series analysis in the Erdaohe landslide," Natural Hazards, vol. 105, no. 1, pp. 783-813, 2021/01/01 2021, doi: 10.1007/s11069-020-04337-6.
[63] Z. Zou et al., "Suitability of data preprocessing methods for landslide displacement forecasting," Stochastic Environmental Research and Risk Assessment, vol. 34, no. 8, pp. 1105-1119, 2020/08/01 2020, doi: 10.1007/s00477-020-01824-x.
[64] B. Yang, K. Yin, S. Lacasse, and Z. Liu, "Time series analysis and long short-term memory neural network to predict landslide displacement," Landslides, vol. 16, no. 4, pp. 677-694, 2019/04/01 2019, doi: 10.1007/s10346-018-01127-x