A novel GRU–TimeMixerKAN hybrid model for robust landslide displacement forecasting: a case study of the Three Gorges Reservoir Area

Abstract

Landslides, as prevalent geohazards, exhibit complex and nonlinear evolutionary dynamics, frequently triggered by the coupled effects of reservoir water-level fluctuations and extreme precipitation. Such events are often characterized by abrupt, step-like deformation, posing significant challenges for accurate long-term displacement forecasting. To address the limitations of conventional models, including poor generalization, low robustness to chaotic disturbances, and insufficient capacity for nonlinear representation, we propose a hybrid deep learning framework termed GRU–TimeMixerKAN. This model synergistically integrates the sequential modeling capabilities of Gated Recurrent Units (GRU), the temporal-feature decoupling mechanism of TimeMixer, and the high-order nonlinear approximation power of the Kolmogorov–Arnold Network (KAN). Enhancements such as differencing-based detrending, sliding-window sampling, and automated hyperparameter optimization via Optuna are incorporated to further refine performance. The efficacy of the proposed model is evaluated using long-term displacement monitoring data from three reactivated reservoir landslides in the Three Gorges Reservoir Area (TGRA), with its performance benchmarked against nine state-of-the-art deep learning baselines. The results demonstrate that GRU–TimeMixerKAN consistently achieves the lowest Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), alongside competitive Symmetric Mean Absolute Percentage Error (sMAPE) and the highest Coefficient of Determination (R²). These findings underscore its superior capability in capturing displacement trends, responding to sudden changes, and generalizing robustly across diverse landslide cases. This study presents an effective and scalable methodology for advancing intelligent early warning and prediction systems for landslides.

Keywords

Landslide prediction / GRU–TimeMixerKAN / Time series forcasting / Deep learning / Three Gorges Reservoir

References

[1] Chen, S.-Y., Chou, W.-Y. (2012). Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach. In: 2012 15th International IEEE Conference on Intelligent Transportation Systems. pp 1821–1826.

[2] Chi M, Chen G, Guo L, Chen X. A DDA-DNN-based approach for micro-analysis and prediction of shear characteristics in unsaturated granular materials. Engineering Analysis with Boundary Elements, 2025, 179 106438

[3] Cinar YG, Mirisaee H, Goswami P, Gaussier E, Aït-Bachir A. Period-aware content attention RNNs for time series forecasting with missing values. Neurocomputing, 2018, 312: 177-186

[4] Deng C, Zhang G, Liu Y, Nie X, Li Z, Liu J, Zhu D. Advantages and disadvantages of terracing: A comprehensive review. International Soil and Water Conservation Research, 2021, 9: 344-359

[5] Du J, Yin K, Lacasse S. Displacement prediction in colluvial landslides, Three Gorges Reservoir, China. Landslides, 2013, 10(2): 203-18

[6] Froude MJ, Petley DN. Global fatal landslide occurrence from 2004 to 2016. Natural Hazards and Earth System Sciences, 2018, 18: 2161-2181

[7] Gariano SL, Guzzetti F. Landslides in a changing climate. Earth-Science Reviews, 2016, 162: 227-252

[8] Gong W, Juang CH, Wasowski J. Geohazards and human settlements: Lessons learned from multiple relocation events in Badong, China – Engineering geologist’s perspective. Engineering Geology, 2021, 285 106051

[9] Guo Y, Wu W, Du M, Liu X, Wang J, Bryant CR. Modeling climate change impacts on rice growth and yield under global warming of 1.5 and 2.0 °C in the Pearl River Delta, China. Atmosphere, 2019, 10: 567

[10] Han H, Shi B, Zhang L. Prediction of landslide sharp increase displacement by SVM with considering hysteresis of groundwater change. Engineering Geology, 2021, 280 105876

[11] Hong D, Zhang B, Li H, Li Y, Yao J, Li C, Werner M, Chanussot J, Zipf A, Zhu XX. Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks. Remote Sensing of Environment, 2023, 299: 113856

[12] Hong D, Zhang B, Li X, Li Y, Li C, Yao J, Yokoya N, Li H, Ghamisi P, Jia X, Plaza A. SpectralGPT: Spectral remote sensing foundation model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46: 5227-5244

[13] Hu X, Fu X, Peng M, Zhang G, Shi Z, Zhu Y, Li Y. Experimental and numerical study on the breaching mechanisms of landslide dams with non-uniform structures. Engineering Geology, 2024, 330: 107414

[14] Huang B, Yin Y, Liu G, Wang S, Chen X, Huo Z. Analysis of waves generated by Gongjiafang landslide in Wu Gorge, three Gorges reservoir, on November 23, 2008. Landslides, 2012, 9: 395-405

[15] Huggel C, Clague JJ, Korup O. Is climate change responsible for changing landslide activity in high mountains?. Earth Surface Processes and Landforms, 2012, 37: 77-91

[16] Intrieri E, Carlà T, Gigli G. Forecasting the time of failure of landslides at slope-scale: A literature review. Earth-Science Reviews, 2019, 193: 333-349

[17] Iverson RM. A constitutive equation for mass-movement behavior. The Journal of Geology, 1985, 93: 143-160

[18] Iverson RM. Landslide triggering by rain infiltration. Water Resources Research, 2000, 36: 1897-1910

[19] Iverson RM. Regulation of landslide motion by dilatancy and pore pressure feedback. Journal of Geophysical Research: Earth Surface., 2005,

[20] Keqiang H, Xiangran L, Xueqing Y, Dong G. The landslides in the Three Gorges Reservoir Region, China and the effects of water storage and rain on their stability. Environmental Geology, 2008, 55: 55-63

[21] Krkač M, Špoljarić D, Bernat S, Arbanas SM. Method for prediction of landslide movements based on random forests. Landslides, 2017, 14: 947-960

[22] Kuster C, Rezgui Y, Mourshed M. Electrical load forecasting models: A critical systematic review. Sustainable Cities and Society, 2017, 35: 257-270

[23] Li D, Sun Y, Yin K, Miao F, Glade T, Leo C. Displacement characteristics and prediction of Baishuihe landslide in the Three Gorges Reservoir. Journal of Mountain Science, 2019, 16: 2203-2214

[24] Li D, Yin K, Leo C. Analysis of Baishuihe landslide influenced by the effects of reservoir water and rainfall. Environmental Earth Sciences, 2010, 60: 677-687

[25] Li L, Wu Y, Miao F, Xue Y, Huang Y. A hybrid interval displacement forecasting model for reservoir colluvial landslides with step-like deformation characteristics considering dynamic switching of deformation states. Stochastic Environmental Research and Risk Assessment, 2021, 35: 1089-1112

[26] Li Y, Qi X, Liu G, Zhang Y, Zhu N, Zhang Q, Guo X, Wang D, Hu H, Chen Z, Xiao L. High performance of low-temperature processed perovskite solar cells based on a polyelectrolyte interfacial layer of PEI. Organic Electronics, 2019, 65: 19-25

[27] Lian C, Zeng Z, Yao W, Tang H. Multiple neural networks switched prediction for landslide displacement. Engineering Geology, 2015, 186: 91-99

[28] Ling Q, Zhang Q, Zhang J, Kong L, Zhang W, Zhu L. Prediction of landslide displacement using multi-kernel extreme learning machine and maximum information coefficient based on variational mode decomposition: a case study in Shaanxi, China. Natural Hazards, 2021, 108: 925-946

[29] Liu B, Liu P, Lu W, Olofsson T. Explainable artificial intelligence (XAI) for material design and engineering applications: A quantitative computational framework. International Journal of Mechanical System Dynamics, 2025, 5: 236-265

[30] Liu B, Liu P, Wang Y, Li Z, Lv H, Lu W. Explainable machine learning for multiscale thermal conductivity modeling in polymer nanocomposites with uncertainty quantification. Composite Structures, 2025, 370: 119292

[31] Liu B, Lu W. Surrogate models in machine learning for computational stochastic multi-scale modelling in composite materials design. International Journal of Hydromechatronics, 2022,

[32] Liu B, Lu W, Olofsson T, Zhuang X, Rabczuk T. Stochastic interpretable machine learning based multiscale modeling in thermal conductivity of polymeric graphene-enhanced composites. Composite Structures, 2024, 327 117601

[33] Liu B, Penaka SR, Lu W, Feng K, Rebbling A, Olofsson T. Data-driven quantitative analysis of an integrated open digital ecosystems platform for user-centric energy retrofits: A case study in northern Sweden. Technology in Society, 2023, 75 102347

[34] Liu B, Vu-Bac N, Rabczuk T. A stochastic multiscale method for the prediction of the thermal conductivity of polymer nanocomposites through hybrid machine learning algorithms. Composite Structures, 2021, 273 114269

[35] Liu B, Vu-Bac N, Zhuang X, Fu X, Rabczuk T, et al. . Stochastic full-range multiscale modeling of thermal conductivity of polymeric carbon nanotubes composites: A machine learning approach. Composite Structures, 2022, 289 115393

[36] Liu B, Vu-Bac N, Zhuang X, Fu X, Rabczuk T. Stochastic integrated machine learning based multiscale approach for the prediction of the thermal conductivity in carbon nanotube reinforced polymeric composites. Composites Science and Technology, 2022, 224 109425

[37] Liu B, Vu-Bac N, Zhuang X, Lu W, Fu X, Rabczuk T. Al-DeMat: A web-based expert system platform for computationally expensive models in materials design. Advances in Engineering Software, 2023,

[38] Liu B, Vu-Bac N, Zhuang X, Rabczuk T. Stochastic multiscale modeling of heat conductivity of polymeric clay nanocomposites. Mechanics of Materials, 2020, 142 103280

[39] Liu B, Wang Y, Rabczuk T, Olofsson T, Lu W. Multi-scale modeling in thermal conductivity of polyurethane incorporated with phase change materials using physics-informed neural networks. Renewable Energy, 2024, 220 119565

[40] Liu Z, Shao J, Xu W, Chen H, Shi C. Comparison on landslide nonlinear displacement analysis and prediction with computational intelligence approaches. Landslides, 2014, 11: 889-896

[41] Lu X, Miao F, Xie X, Li D, Xie Y. A new method for displacement prediction of “step-like” landslides based on VMD-FOA-SVR model. Environmental Earth Sciences, 2021, 80: 542

[42] Luo S, Huang D, Peng J, Tomás R. Influence of permeability on the stability of dual-structure landslide with different deposit-bedding interface morphology: The case of the Three Gorges Reservoir Area, China. Engineering Geology, 2022, 296 106480

[43] Miao F, Wu Y, Li L, Liao K, Xue Y. Triggering factors and threshold analysis of baishuihe landslide based on the data mining methods. Natural Hazards, 2021, 105: 2677-2696

[44] Montesino Pouzols F, Lendasse A. Effect of different detrending approaches on computational intelligence models of time series. The 2010 International Joint Conference on Neural Networks (IJCNN), 2010, IEEE: 1-8

[45] Nava L, Carraro E, Reyes-Carmona C, Puliero S, Bhuyan K, Rosi A, Monserrat O, Floris M, Meena SR, Galve JP, Catani F. Landslide displacement forecasting using deep learning and monitoring data across selected sites. Landslides, 2023, 20: 2111-2129

[46] Neaupane KM, Achet SH. Use of backpropagation neural network for landslide monitoring: A case study in the higher Himalaya. Engineering Geology, 2004, 74: 213-226

[47] Niu Z, Zhong G, Yu H. A review on the attention mechanism of deep learning. Neurocomputing, 2021, 452: 48-62

[48] Pudasaini SP, Jaboyedoff M. A general analytical model for superelevation in landslide. Landslides, 2020, 17: 1377-1392

[49] Samek W, Montavon G, Lapuschkin S, Anders CJ, Müller KR. Explaining deep neural networks and beyond: a review of methods and applications. Proceedings of the IEEE, 2021, 109: 247-278

[50] Tacher L, Bonnard C, Laloui L, Parriaux A. Modelling the behaviour of a large landslide with respect to hydrogeological and geomechanical parameter heterogeneity. Landslides, 2005, 2: 3-14

[51] Ubrani A, Motwani SWang J, Reddy GRM, Prasad VK, Reddy VS. LSTM- and GRU-based time series models for market clearing price forecasting of indian deregulated electricity markets. Soft computing and signal processing, 2019, Springer: 693-700

[52] van Steijn H. Debris-flow magnitude—frequency relationships for mountainous regions of Central and Northwest Europe. Geomorphology, 1996, 15: 259-273

[53] van Westen CJ, Castellanos E, Kuriakose SL. Spatial data for landslide susceptibility, hazard, and vulnerability assessment: An overview. Engineering Geology, 2008, 102: 112-131

[54] Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J. Y., & Zhou, J. (2024). TimeMixer: Decomposable multiscale mixing for time series forecasting.

[55] Wang FW, Zhang YM, Huo ZT, Matsumoto T, Huang BL. The July 14, 2003 Qianjiangping landslide, Three Gorges Reservoir, China. Landslides, 2004,

[56] Wang J, Cui Q, Sun X. A novel framework for carbon price prediction using comprehensive feature screening, bidirectional gate recurrent unit and Gaussian process regression. Journal of Cleaner Production, 2021, 314 128024

[57] Wang L, Xiao T, Liu S, Zhang W, Yang B, Chen L. Quantification of model uncertainty and variability for landslide displacement prediction based on Monte Carlo simulation. Gondwana Research, 2023, 123: 27-40

[58] Wang Y, Zhu X, Qiu C, Yu L. SUMOylated NICD in endothelial cell suppresses tumor angiogenesis. Journal of Molecular and Cellular Cardiology, 2020, 140: 15-16

[59] Xia M, Shao H, Ma X, de Silva CW. A stacked GRU-RNN-based approach for predicting renewable energy and electricity load for smart grid operation. IEEE Transactions on Industrial Informatics, 2021, 17: 7050-7059

[60] Xia Y, Zhang C, Wang C, Liu H, Sang X, Liu R, Zhao P, An G, Fang H, Shi M, Li B. Prediction of bending strength of glass fiber reinforced methacrylate-based pipeline UV-CIPP rehabilitation materials based on machine learning. Tunnelling and Underground Space Technology, 2023, 140: 105319

[61] Yang B, Yin K, Lacasse S, Liu Z. Time series analysis and long short-term memory neural network to predict landslide displacement. Landslides, 2019, 16: 677-694

[62] Yang H, Song K, Chen L, Qu L. Hysteresis effect and seasonal step-like creep deformation of the Jiuxianping landslide in the Three Gorges Reservoir region. Engineering Geology, 2023, 317 107089

[63] Yi, W. (2020). Basic characteristics and monitoring data of Baishui River landslide in Zigui County, Three Gorges Reservoir Area of the Yangtze River from 2007 to 2012. National Cryosphere Desert Data Center. https://doi.org/10.12072/ncdc.Sanxia.db0026.2020

[64] Yi, W., & Huang, H. (2020a). Deformation monitoring data of Shuping landslide in Zigui County of the Three Gorges Reservoir Area of the Yangtze River from 2007 to 2012. National Cryosphere Desert Data Center. https://doi.org/10.12072/sanxia.020.2018.db

[65] Yi, W., & Huang, H. (2020b). 2007–2012 Deformation monitoring data of Bazimen landslide in Zigui County, Three Gorges Reservoir Area. National Cryosphere Desert Data Center. https://doi.org/10.12072/ncdc.Sanxia.db0004.2020

[66] Zhang J, Tang H, Tannant DD, Lin C, Xia D, Liu X, Zhang Y, Ma J. Combined forecasting model with CEEMD-LCSS reconstruction and the ABC-SVR method for landslide displacement prediction. Journal of Cleaner Production, 2021, 293: 126205

[67] Zhang L, Shi B, Zhu H, Yu XB, Han H, Fan X. PSO-SVM-based deep displacement prediction of Majiagou landslide considering the deformation hysteresis effect. Landslides, 2021, 18: 179-193

[68] Zhang W, Li H, Tang L, Gu X, Wang L, Wang L. Displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks. Acta Geotechnica, 2022, 17: 1367-1382

[69] Zhang W, Wu C, Tang L, Gu X, Wang L. Efficient time-variant reliability analysis of Bazimen landslide in the Three Gorges Reservoir Area using XGBoost and LightGBM algorithms. Gondwana Research, 2023, 123: 41-53

[70] Zhang X, Xia Y, Zhang C, Liu B, Wang C, Fang H, Wang J. A prediction model for dyke-dam piping based on data augmentation and interpretable ensemble learning. Engineering Failure Analysis, 2025, 182: 110174

[71] Zhang X, Xia Y, Zhang C, Wang C, Liu B, Fang H. An archimedes optimization algorithm based extreme gradient boosting model for predicting the bending strength of UV cured glass fiber reinforced polymer composites. Polymer Composites, 2025,

[72] Zhou C, Yin K, Cao Y, Ahmed B. Application of time series analysis and PSO–SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China. Engineering Geology, 2016, 204: 108-120

[73] Zhou C, Yin K, Cao Y, Intrieri E, Ahmed B, Catani F. Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method. Landslides, 2018, 15: 2211-2225

[74] Zhu CH, Hu GD. Time series prediction of landslide displacement using SVM model: Application to Baishuihe Landslide in Three Gorges Reservoir Area, China. Applied Mechanics and Materials, 2012, 239–240: 1413-1420

[75] Zou Z, Yang Y, Fan Z, Tang H, Zou M, Hu X, Xiong C, Ma J. Suitability of data preprocessing methods for landslide displacement forecasting. Stochastic Environmental Research and Risk Assessment, 2020, 34: 1105-1119

Funding

National Natural Science Foundation of China(52130905)

RIGHTS & PERMISSIONS

The Author(s)