Prediction of Rainfall-Induced Slope Stability Spatiotemporal Evolution Based on a Hybrid Transformer–LSTM Deep Learning Framework
Open Access
- 13 June 2026
- journal article
- research article
- Published by MDPI AG in Geohazards
- Vol. 7 (2) , 75
Abstract
Rainfall is a critical factor inducing slope instability, and accurate prediction of the factor of safety (FOS) of slopes under rainfall conditions is of paramount importance for disaster prevention and mitigation. Conventional numerical simulation methods incur high computational costs, while individual machine learning models are often insufficient to adequately capture the nonlinear spatiotemporal evolution characteristics of multiple factors under coupled multi-physics fields. To address these limitations, this paper proposes a Transformer–LSTM prediction framework. First, a fluid–structure coupling model for rainfall-affected slopes is constructed using COMSOL, and multi-factor orthogonal experiments are performed to generate multi-dimensional time-series data. Subsequently, a Transformer–LSTM fusion deep learning model is built, in which LSTM is employed to extract the temporal dynamic characteristics of rainfall infiltration, and the self-attention mechanism of the Transformer is leveraged to enhance feature extraction and global dependency modeling of key disaster-causing factors. Experimental results demonstrate that the Transformer–LSTM model significantly outperforms traditional PSO-LSTM, PSO-SVM, and standalone Transformer or LSTM models in terms of both prediction accuracy and generalization capability. Its coefficient of determination (R2) remains above 0.94, and key evaluation metrics—including mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE)—attain the lowest values among the compared models. Furthermore, the SHAP (SHapley Additive exPlanations) interpretability framework is introduced to quantitatively elucidate the model’s predictive decision-making and to establish a physically grounded causal mapping with geotechnical mechanisms. It is confirmed that effective cohesion and slope angle exert a dominant interactive effect on the degradation of slope stability, providing data-driven support for wide-area monitoring of rainfall-induced landslides.Keywords
Funding Information
- Ningxia Hui Autonomous Region Key Research and Development Program Project (2025BEE04001)
This publication has 19 references indexed in Scilit:
- Study on unsaturated rainfall-induced slope stability and failure probability based on GA-LSTM-MCAlexandria Engineering Journal, 2026
- A new intelligent combined prediction system for rainfall-induced instability of circular failure slopesEnvironmental Earth Sciences, 2025
- Time series prediction of the slope stability under rainfall conditions based on LSTM and CNNNatural Hazards, 2025
- Considering antecedent rainfall to improve susceptibility assessment of rainfall-earthquake-triggered landslides on unsaturated slopesEnvironmental Earth Sciences, 2024
- Rainfall-induced landslide prediction models, part ii: deterministic physical and phenomenologically modelsBulletin of Engineering Geology and the Environment, 2024
- Deep-learning-based landslide early warning method for loose deposits slope coupled with groundwater and rainfall monitoringComputers and Geotechnics, 2023
- Establishing a shallow-landslide prediction method by using machine-learning techniques based on the physics-based calculation of soil slope stabilityLandslides, 2023
- Mitigation of spatial nonstationarity with vision transformersComputers & Geosciences, 2023
- Estimation of daily bicycle traffic using machine and deep learning techniquesTransportation, 2022
- Uncertainty of rainfall-induced landslides considering spatial variability of parametersComputers and Geotechnics, 2017