# Multi-Modal Data-Driven Bayesian-Optimized CNN-LSTM Model for Slope Displacement Prediction

## TL;DR

A new model combining CNN and LSTM with Bayesian optimization improves slope displacement predictions using multi-modal data like rainfall and earth pressure.

## Contribution

A novel Bayesian-optimized CNN-LSTM model that fuses multi-modal data for enhanced slope displacement prediction accuracy and stability.

## Key findings

- The model achieved an average R2 of 0.971 with MAE of 0.444 mm and RMSE of 0.618 mm.
- Compared to other models, it reduced MAE and RMSE by up to 32.3% and 29.5%, respectively.
- Extrapolation prediction accuracy improved by 30.2% in MAE and 24.6% in RMSE using rainfall and earth pressure data.

## Abstract

What are the main findings?
A multimodal data-driven Bayesian optimized CNN-LSTM prediction model was constructed, which significantly improved the accuracy and stability of slope displacement time series prediction.The study verified that fusing multimodal data such as rainfall and earth pressure can effectively enhance the model’s ability to represent external influencing factors, thereby improving prediction stability.

A multimodal data-driven Bayesian optimized CNN-LSTM prediction model was constructed, which significantly improved the accuracy and stability of slope displacement time series prediction.

The study verified that fusing multimodal data such as rainfall and earth pressure can effectively enhance the model’s ability to represent external influencing factors, thereby improving prediction stability.

What are the implications of the main findings?
This provides a high-precision intelligent prediction method for slope safety monitoring and geological disaster early warning, supporting reliable extrapolation prediction in the case of missing or abnormal GNSS data.The constructed framework provides a technical approach that can be referenced for similar engineering time series prediction tasks.

This provides a high-precision intelligent prediction method for slope safety monitoring and geological disaster early warning, supporting reliable extrapolation prediction in the case of missing or abnormal GNSS data.

The constructed framework provides a technical approach that can be referenced for similar engineering time series prediction tasks.

Accurate prediction of slope displacement is an important prerequisite for building an effective geological hazard early warning system for disaster prevention and reduction. However, the inherent nonlinearity and time-varying characteristics of slope displacement evolution greatly affect the prediction accuracy. To improve the slope displacement prediction accuracy, a multi-modal data-driven Bayesian-optimized Convolutional Neural Network and Long Short-Term Memory (Bayes-CNN-LSTM) model was constructed. The performance of the model was evaluated using multi-modal monitoring data from the GuShan mine slope. Experimental results showed that the Bayes-CNN-LSTM model achieved an average coefficient of determination (R2) of 0.971, with a mean absolute error (MAE) of 0.444 mm and a root mean square error (RMSE) of 0.618 mm. Compared with the CNN-LSTM, LSTM, CNN, SVM, TCN, and Transformer models, the MAE of the constructed model was decreased by 25.1%, 31.3%, 32.3%, 24.1%, 24.7%, and 17.7%, respectively, and the RMSE decreased by 20.1%, 26.9%, 29.5%, 18.0%, 20.7%, and 12.4%, respectively. Furthermore, the proper integration of multi-modal data can effectively improve the prediction accuracy when extrapolating slope displacement. Based on rainfall and earth pressure data, the average MAE and RMSE of extrapolation (24-h) prediction using the constructed model were decreased by 30.2% and 24.6%, respectively. The model effectively improves the accuracy of slope displacement prediction and enhances the practicality of the slope safety monitoring system, providing valuable reference for slope safety monitoring.