Related Experiment Video
Updated: May 26, 2026
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
Multi-Modal Data-Driven Bayesian-Optimized CNN-LSTM Model for Slope Displacement Prediction
Xingwang Zhao1,2,3, Xinlong Wan1,3, Jian Chen1,3
1Key Laboratory of Aviation-Aerospace-Ground Cooperative Monitoring and Early Warning of Coal Mining-Induced Disasters of Anhui Higher Education Institutes, Anhui University of Science and Technology, Huainan 232001, China.
Sensors (Basel, Switzerland)
|March 14, 2026
Summary
A new Bayesian-optimized Convolutional Neural Network and Long Short-Term Memory (Bayes-CNN-LSTM) model improves slope displacement prediction accuracy. This advanced model enhances geological hazard early warning systems for disaster prevention.
Area of Science:
- Geotechnical Engineering
- Artificial Intelligence
- Disaster Prevention
Background:
- Accurate slope displacement prediction is crucial for geological hazard early warning systems.
- Nonlinearity and time-varying characteristics of slope displacement challenge prediction accuracy.
Purpose of the Study:
- To develop an advanced model for improving slope displacement prediction accuracy.
- To enhance the reliability of geological hazard early warning systems.
Main Methods:
- A multi-modal data-driven Bayesian-optimized Convolutional Neural Network and Long Short-Term Memory (Bayes-CNN-LSTM) model was constructed.
- The model's performance was evaluated using multi-modal monitoring data from the GuShan mine slope.
- Comparative analysis was performed against various established models (CNN-LSTM, LSTM, CNN, SVM, TCN, Transformer).
Main Results:
- The Bayes-CNN-LSTM model achieved high accuracy with R2 of 0.971, MAE of 0.444 mm, and RMSE of 0.618 mm.
- The model demonstrated significant reductions in Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) compared to other models.
- Integration of multi-modal data, including rainfall and earth pressure, improved extrapolation prediction accuracy by 30.2% (MAE) and 24.6% (RMSE) for 24-h forecasts.
Conclusions:
- The Bayes-CNN-LSTM model significantly enhances slope displacement prediction accuracy.
- The model improves the practicality and effectiveness of slope safety monitoring systems.
- This approach offers a valuable reference for advancing slope safety monitoring and disaster risk reduction.