Deformation-Scaled Conformal Prediction for Short-Term Landslide Displacement: A Granular Uncertainty Assessment Framework for Decision Support
Keywords:
Conformal prediction, Landslide displacement, Prediction interval, Uncertainty quantification, Granular computing, Decision supportAbstract
Deterministic forecasts conceal whether a predicted landslide displacement is sufficiently reliable for operational decision-making. This study develops a lightweight uncertainty-aware framework that represents a monitored slope through four spatial granules and three deformation-state granules. Daily records of displacement from global navigation satellite system (GNSS) monitoring points, rainfall, and reservoir water level at the Xinpu reservoir landslide were aggregated into four series corresponding to Zones I–IV. A LightGBM model predicted the seven-day displacement increment from a 30-day history, while split conformal prediction (Split-CP) and deformation-scaled conformal prediction (DSCP) constructed nominal 90% prediction intervals around the point forecasts. DSCP scales calibration residuals by the root-mean-square magnitude of the preceding 14-day displacement increments. During the chronological test period in 2021, LightGBM achieved an overall mean absolute error of 1.243 mm, 46.2% lower than that of persistence. Split-CP attained 86.20% empirical coverage with a mean width of 5.396 mm, while DSCP increased coverage to 89.69% and reduced the mean interval score by 7.2%, with a modest 4.5% increase in interval width. Interval width was strongly associated with forecast-origin deformation velocity (overall Spearman’s ρ = 0.768). Conditional evaluation nevertheless revealed a failure mode: coverage in the rapid state of Zone III was only 68.0%. The results demonstrate that uncertainty should be evaluated across spatial and deformation-state granules rather than inferred from an aggregate accuracy score. The proposed framework provides a point forecast, prediction interval, and relative confidence index for monitoring prioritization without requiring modifications to the base predictor.
Downloads
References
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. Journal of Rock Mechanics and Geotechnical Engineering, 8, 577-595. https://doi.org/10.1016/j.jrmge.2016.08.001
Tang, H., Wasowski, J., & Juang, C. H. (2019). Geohazards in the Three Gorges Reservoir Area, China: Lessons learned from decades of research. Engineering Geology, 261, 105267. https://doi.org/10.1016/j.enggeo.2019.105267
Casagli, N., Intrieri, E., Tofani, V., Gigli, G., & Raspini, F. (2023). Landslide detection, monitoring and prediction with remote-sensing techniques. Nature Reviews Earth & Environment, 4, 51-64. https://doi.org/10.1038/s43017-022-00373-x
Jiang, H., Li, Y., Zhou, C., Hong, H., Glade, T., & Yin, K. (2020). Landslide displacement prediction combining LSTM and SVR algorithms: A case study of Shengjibao landslide from the Three Gorges Reservoir Area. Applied Sciences, 10, 7830. https://doi.org/10.3390/app10217830
Yang, B., Yin, K., Lacasse, S., & Liu, Z. (2019). Time series analysis and long short-term memory neural network to predict landslide displacement. Landslides, 16, 677-694. https://doi.org/10.1007/s10346-018-01127-x
Zhang, W., Li, H., Tang, L., Gu, X., Wang, L., & Wang, L. (2022). Displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks. Acta Geotechnica, 17, 1367-1382. https://doi.org/10.1007/s11440-022-01495-8
Wang, Y., Tang, H., Huang, J., Wen, T., Ma, J., & Zhang, J. (2022). A comparative study of different machine learning methods for reservoir landslide displacement prediction. Engineering Geology, 298, 106544. https://doi.org/10.1016/j.enggeo.2022.106544
Nava, L., Carraro, E., Reyes-Carmona, C., Puliero, S., Bhuyan, K., Rosi, A., Monserrat, O., Floris, M., Meena, S. R., Galve, J. P., & Catani, F. (2023). Landslide displacement forecasting using deep learning and monitoring data across selected sites. Landslides, 20, 2111-2129. https://doi.org/10.1007/s10346-023-02104-9
Lian, C., Zeng, Z., Wang, X., Yao, W., Su, Y., & Tang, H. (2020). Landslide displacement interval prediction using lower upper bound estimation method with pre-trained random vector functional link network initialization. Neural Networks, 130, 286-296. https://doi.org/10.1016/j.neunet.2020.07.020
Zheng, Z., Li, Y., Zhang, Y., Wen, L., Wang, T., & Sun, X. (2025). Failure probability assessment of step-like landslide using a hybrid interval prediction method under uncertain conditions. Journal of Rock Mechanics and Geotechnical Engineering, 17, 7265-7287. https://doi.org/10.1016/j.jrmge.2025.08.008
Wang, L., Xiao, T., Liu, S., Zhang, W., Yang, B., & Chen, L. (2023). Quantification of model uncertainty and variability for landslide displacement prediction based on Monte Carlo simulation. Gondwana Research, 123, 27-40. https://doi.org/10.1016/j.gr.2023.03.006
Ren, X., Liu, W., Yang, W., Mao, L., & Li, H. (2025). Landslide deformation uncertainty quantification using conformalized graph neural networks: A case study in Sichuan Province, China. IEEE Access, 13, 86719-86731. https://doi.org/10.1109/ACCESS.2025.3568273
Vovk, V., Gammerman, A., & Shafer, G. (2005). Algorithmic learning in a random world. Springer. https://doi.org/10.1007/b106715
Lei, J., G'Sell, M., Rinaldo, A., Tibshirani, R. J., & Wasserman, L. (2018). Distribution-free predictive inference for regression. Journal of the American Statistical Association, 113, 1094-1111. https://doi.org/10.1080/01621459.2017.1307116
Lei, J., & Wasserman, L. (2014). Distribution-free prediction bands for non-parametric regression. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 76, 71-96. https://doi.org/10.1111/rssb.12021
Barber, R. F., Candès, E. J., Ramdas, A., & Tibshirani, R. J. (2023). Conformal prediction beyond exchangeability. The Annals of Statistics, 51, 816-845. https://doi.org/10.1214/23-AOS2276
Zadeh, L. A. (1997). Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets and Systems, 90, 111-127. https://doi.org/10.1016/S0165-0114(97)00077-8
Pedrycz, W. (2013). Granular computing: Analysis and design of intelligent systems. CRC Press. https://doi.org/10.1201/9781315216737
Ye, X., Zhu, H.-H., Cheng, G., Pei, H.-F., Shi, B., Schenato, L., & Pasuto, A. (2024). Thermo-hydro-poro-mechanical responses of a reservoir-induced landslide tracked by high-resolution fiber optic sensing nerves. Journal of Rock Mechanics and Geotechnical Engineering, 16, 1018-1032. https://doi.org/10.1016/j.jrmge.2023.04.004
Zheng, W., Sun, Q., Hu, J., Lu, Z., Zhu, K., Ye, X., Huang, G., Hu, M., Zhu, J., & Li, Z. (2023). Investigating kinematics and triggers of slow-moving reservoir landslide using an improved MT-InSAR method. Geomatics, Natural Hazards and Risk, 14, 2289835. https://doi.org/10.1080/19475705.2023.2289835
Zhu, W., He, Q., Wu, J., Wang, Y., Li, Z., Zhan, J., & Zhang, B. (2025). Identifying reservoir landslide deformation evolution stages with time series InSAR: Application to the Xinpu landslide in China's Three Gorges region. Journal of Hydrology, 663, 134136. https://doi.org/10.1016/j.jhydrol.2025.134136
Zhou, C., Ye, M., Xia, Z., Wang, W., Luo, C., & Muller, J.-P. (2025). An interpretable attention-based deep learning method for landslide prediction based on multi-temporal InSAR time series: A case study of Xinpu landslide in the TGRA. Remote Sensing of Environment, 318, 114580. https://doi.org/10.1016/j.rse.2024.114580
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29, 1189-1232. https://doi.org/10.1214/aos/1013203451
Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1724–1734. https://doi.org/10.3115/v1/D14-1179
Gneiting, T., & Raftery, A. E. (2007). Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102, 359-378. https://doi.org/10.1198/016214506000001437
Khosravi, A., Nahavandi, S., Creighton, D., & Atiya, A. F. (2011). Comprehensive review of neural network-based prediction intervals and new advances. IEEE Transactions on Neural Networks, 22, 1341-1356. https://doi.org/10.1109/TNN.2011.2162110
Chang, F., Dong, S., Yin, H., Ye, X., Wu, Z., Zhang, W., & Zhu, H. (2025). 3D displacement time series prediction of a north-facing reservoir landslide powered by InSAR and machine learning. Journal of Rock Mechanics and Geotechnical Engineering, 17, 4445-4461. https://doi.org/10.1016/j.jrmge.2024.10.033
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yongfei Wu, Gang Cheng, Haoran Zhang, Daisong Yang, Jingjing Xia (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
