Step-like landslide displacement prediction is influenced by multiple characteristic factors, and the feature selection models using different sampling methods significantly affect the prediction results. Taking the Linbang accumulation body landslide in the Houziyan reservoir area of the Dadu River as an example. Step-like landslide displacement was accurately predicted through the establishment of a novel integrated prediction model that combined stratified sampling-based sequential forward and backward selection(SFS, SBS), LSTM(long short-term memory network), and an attention mechanism. Traditionally, the random sampling method in feature selection was abandoned, and a stratified sampling approach was innovatively adopted for the first time. The stratified sampling method specifically addressed the regularity of periodic displacement, particularly the data distribution characteristics near step inflection points, which significantly enhanced the model’s ability to characterize features during critical deformation stages. Additionally, an attention mechanism was introduced, endowing the model with the capability to dynamically adjust its focus on historical time-series information, thereby enabling more precise prediction of displacement mutations. The results show evaluation metrics for monitoring points 1-5 and 2-5 as RMSE(root mean square error) values of 3.16 and 1.56, MAPE(mean absolute percentage error) values of 0.27 and 0.83, and R2 values of 0.978 and 0.984.The model’s robustness was further validated using two typical step-like landslides in the Three Gorges Reservoir area: Baishuihe and Bazimen. It is evident that the stratified sampling approach combined with the attention mechanism can effectively enhance the prediction accuracy of step-like landslides.
LI Chao-gang, JU Neng-pan, HE Chao-yang, XIE Ming-li, XU Lie.
Stepped Landslide Displacement Prediction Based on Stratified Sampling and Attention Mechanism[J].
Science Technology and Engineering, 2026, 26(2): 476-489 DOI:10.12404/j.issn.1671-1815.2502396
HouShengshan, LiAng, HanBing, et al. An approach of geo-hazard warning system in Ya’an, Sichuan and its analysis[J]. The Chinese Journal of Geological Hazard and Control, 2014, 25(4): 134-138.
XuQiang, LuHuiyan, LiWeile, et al. Types of potential landslide and corresponding identification technologies[J]. Geomatics and Information Science of Wuhan University, 2022, 47(3): 377-387.
GuoZizheng, YinKunlong, LiuQingli, et al. Rainfall warning of creeping landslide in Yunyang County of Three Gorges Reservoir Region based on displacement ratio mode[J]. Earth Science, 2020, 45(2): 672-684.
LiLongqi, WangMengyun, ZhaoHaoqiu, et al. Predicting displacement of Baishuihe landslide using CEEMDAN-BA-SVR-Adaboost model[J]. Journal of Yangtze River Scientific Research Institute, 2021, 38(6): 52-59.
YangBeibei, YinKunlong, DuJuan, et al. A model for predicting landslide displacement based on time series and long and short term memory neural network[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(10): 2334-2343.
[12]
DaiK, ChenC, ShiX L, et al. Dynamic landslides susceptibility evaluation in Baihetan Dam area during extensive impoundment by integrating geological model and InSAR observations[J]. International Journal of Applied Earth Observation and Geoinformation, 2023, 116. DOI: 10.1016/j.jag.2022.103157.
[13]
DuH, SongD Q, ChenZ, et al. Prediction model oriented for landslide displacement with step-like curve by applying ensemble empirical mode decomposition and the PSO-ELM method[J]. Journal of Cleaner Production, 2020, 270. DOI: 10.1016/j.jclepro.2020.122248.
[14]
ZhangJ R, LinC Y, TangH M, et al. Input-parameter optimization using a SVR based ensemble model to predict landslide displacements in a reservoir area: a comparative study[J]. Applied Soft Computing, 2024, 150. DOI: 10.1016/j.asoc.2023.111107.
WanZhi, DongHui, LiuBaochen. On choice of hyper-parameters of support vector machines for time series regression and prediction with orthogonal design[J]. Rock and Soil Mechanics, 2010, 31(2): 503-508.
AnDong, SongKun, YiZheng, et al. A prediction model for rese-rvoir landslide step-like displacements using combined EEMD and RFR method[J]. Mountain Research, 2021, 39(1): 143-150.
WangZhiwei, WangLi, HuangGuanwen, et al. Research on multi-source heterogeneous data fusion algorithm of landslide monitoring based on BP neural network[J]. Journal of Geomechanics, 2020, 26(4): 575-582.
[21]
LiH J, XuQ, HeY S, et al. Prediction of landslide displacement with an ensemble-based extreme learning machine and copula models[J]. Landslides, 2018, 15(6): 2047-2059.
[22]
WangY K, TangH M, HuangJ S, et al. A comparative study of different machine learning methods for reservoir landslide displacement prediction[J]. Engineering Geology, 2022, 298. DOI: 10.1016/j.enggeo.2022.106544.
ZhangLei, JuNengpan, HeChaoyang, et al. Real-time anomaly detection and analysis of time series data for crack gauge in landslides[J]. Chinese Journal of Rock Mechanics and Engineering, 2024, 43(1): 206-215.
ChenLang, ChenYu, HeJunlin, et al. Prediction of landslide displacement based on previous accumulated rainfall and Gaussian process regression model[J]. Chinese Journal of Rock Mechanics and Engineering, 2024, 43(S1): 3491-3497.
ZhangWengang, GuXin, LiuHanlong, et al. Probabilistic back analysis of soil parameters and displacement prediction of unsaturated slopes using Bayesian updating[J]. Rock and Soil Mechanics, 2022, 43(4): 1112-1122.
LiJunfeng, ZhangXiaoqiong, MaTao, et al. An interpretable landslide displacement prediction model based on XGBoost and SHAP[J]. Journal of Engineering Geology, 2025, 33(4): 1428-1438.
XuJiangbo, HouXinmin, WuXiong, et al. Research on slope displacement prediction based on MIC-XGBoost-LSTM model[J]. China Journal of Highway and Transport, 2024, 37(10): 38-48.
YangWanli, HeYongqiang, ZhangJianliang, et al. Long term displacement prediction of landslides based on GCformer[J]. Science Technology and Engineering, 2025, 25(12): 4913-4919.
[35]
MaJ W, XiaD, GuoH X, et al. Metaheuristic-based support vector regression for landslide displacement prediction: a comparative study[J]. Landslides, 2022, 19(10): 2489-2511.
[36]
CaiZ L, XuW Y, MengY D, et al. Prediction of landslide displacement based on GA-LSSVM with multiple factors[J]. Bulletin of Engineering Geology and the Environment, 2016, 75(2): 637-646.
[37]
ZhuX, MaS Q, XuQ, et al. A WD-GA-LSSVM model for rainfall-triggered landslide displacement prediction[J]. Journal of Mountain Science, 2018, 15(1): 156-166.
FengYu, TuPengfei, ZengHuaien, et al. A method for identifying critical displacement threshold of landslide step under combined effects of rainfall and reservoir water level[J]. Chinese Journal of Rock Mechanics and Engineering, 2023, 42(11): 2788-2805.
[40]
ZengT R, JiangH G, LiuQ L, et al. Landslide displacement prediction based on variational mode decomposition and MICGWO-LSTM model[J]. Landslide, 2022, 17(11): 567-583.
ZengZijian, XiaoHui, XuHaning, et al. Landslide surface displacement prediction based on CRITIC weight method and PSO-SVR model[J]. Science Technology and Engineering, 2024, 24(35): 14940-14946.
LuoChaolei, XuHaning, XiaoHui, et al. Landslide displacement prediction based on whale optimization hybrid neural network[J]. Science Technology and Engineering, 2024, 24(16): 6610-6616.
[45]
ZhangK, ZhangK, CaiC, et al. Displacement prediction of step-like landslides based on feature optimization and VMD-Bi-LSTM: a case study of the Bazimen and Baishuihe landslides in the Three Gorges, China[J]. Bulletin of Engineering Geology and the Environment, 2021, 80(11): 8481-8502.
ShangMin, XiongDebing, ZhangHuiqiang, et al. Landslide displacement prediction model based on timeseries and mixed kernel function SA-SVR[J]. Journal of Engineering Geology, 2022, 30(2): 575-588.
MaFeiyan, LiXiangxin. Landslide displacement prediction model using improved SSA-KELM coupling algorithm[J]. Science Technology Engineering, 2022, 22(5): 1786-1793.
[50]
WangH Y, AoY, WangC G, et al. A dynamic prediction model of landslide displacement based on VMD-SSO-LSTM approach[J]. Scientific Reports, 2024, 14(5). DOI: 10.1038/s41598-024-59517-2.
[51]
WangT L, LuoR, MaT X, et al. Study and verification on an improved comprehensive prediction model of landslide displacement[J]. Bulletin of Engineering Geology and the Environment, 2024, 83(90). DOI: 10.1007/s10064-024-03581-5.
[52]
MengS Q, ShiZ M, MingP, et al. Landslide displacement prediction with step-like curve based on convolutional neural network coupled with bi-directional gated recurrent unit optimized by attention mechanism[J]. Engineering Applications of Artificial Intelligence, 2024, 133. DOI: 10.1016/j.engappai.2024.108078.
LiuHangyuan, ChenWeitao, LiYuanyao, et al. Application of a novel integrated model based on EEMD-CNN-LSTM in landslide displacement prediction[J]. Journal of Geomechanics, 2024, 30(4): 633-646.
ShenFu, LiuSirui, XuXiaoyuan, et al. Joint short-term multi-load forecasting of integrated energy system based on multi-scale feature extraction[J]. High Voltage Engineering, 2024, 50(7): 2948-2930.
LongZhiyou, WanZhaolong, DongShi, et al. Displacement prediction of highway slope based on variational mode decomposition and extreme gradient boosting[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(7): 2320-2332.
[59]
LadhaL, DeepaT. Feature selection methods and algorithms[J]. International Journal on Computer Science and Engineering, 2011, 3(5): 1787-1797.
[60]
HamedS K, AbA M J, YaakubM R. Fake news detection model on social media by leveraging sentiment analysis of news content and emotion analysis of users’ comments[J]. Sensors, 2023, 23(4). DOI: 10.3390/s23041748.