This paper focuses on enhancing the prediction of vertical soil displacement during deep excavation using Artificial Neural Networks (ANN). Precise prediction of soil movement is essential to ensure the stability of the construction site and surrounding infrastructure. Traditional methods, such as the Finite Element Method (FEM), while accurate, are time-consuming and computationally intensive. In contrast, ANN offers fast and reliable predictions, making it a valuable tool for real-time decision-making. This study integrates FEM-based data to train the ANN model, ensuring the ANN captures complex, non-linear interactions between input variables like depth, pore water pressure, and coordinates. The model is trained and evaluated using performance metrics such as MAE, MSE, RMSE, and R2. With a high correlation coefficient R2 = 0.969238, the ANN model provides predictions with minimal error, demonstrating its effectiveness in replicating real-world measurements. The combined approach of ANN and FEM leverages the strengths of both methods, with FEM offering detailed physical insights and ANN optimizing computational efficiency. The results indicate that ANN-based models can serve as an efficient predictive tool in large-scale construction projects, improving safety by anticipating potential soil displacement issues. Future research will focus on expanding the model's applicability across different soil conditions and enhancing prediction capabilities with other machine learning algorithms.

In evaluating the safety of rock slopes engineering, it is imperative to account for rheological effects. These effects can lead to significant deformations that may adversely impact the overall structural integrity. Consequently, accurate determination of the rheological mechanical parameters of slope rocks is essential. However, the application of rheological parameters obtained from laboratory tests encounters limitations due to the rock's inherent heterogeneity, scale effects, and inevitable sample dispersion. By contrast, on-site monitoring data serve as critical assets for real-time calibration and risk assessment in the evaluation of rheological parameters and prediction of slope deformation. To integrate on-site monitoring data with rheological mechanical mechanisms, this study introduces a probabilistic inverse model for evaluating rock slope rheological parameters, grounded in Bayesian theory, and incorporating a No-U-Turn Sampler (NUTS) based on Markov Chain Monte Carlo (MCMC) sampling algorithm. In terms of methodological efficiency, we compared the NUTS method with the traditional Metropolis-Hastings (M-H) approach, demonstrating the superior efficiency of the former. Additionally, sensitivity analysis of rheological parameters was conducted using the Burgers constitutive model. By combining the NUTS-based MCMC method with this model, the uncertainty of creep parameters was successfully evaluated. Utilizing these updated posterior parameters, up to 3-year deformation forecast for the slope was executed, the findings demonstrate that the deformation on the left bank slope is slight, indicating a state of safety. This study integrates monitoring data with rheological mechanics to establish a physical-data-driven rheological safety assessment mechanism. It offers a scientifically robust and effective approach for the uncertainty evaluation of rheological parameters and deformation prediction, providing significant support for the safety assessment of the left bank slope of the Baihetan hydropower station, China.

Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide. Accurately predicting landslide displacement enables effective early warning and risk management. However, the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models, such as state-of-the-art machine learning (ML) models. To address these challenges, this study proposes a data augmentation framework that uses generative adversarial networks (GANs), a recent advance in generative artificial intelligence (AI), to improve the accuracy of landslide displacement prediction. The framework provides effective data augmentation to enhance limited datasets. A recurrent GAN model, RGAN-LS, is proposed, specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data. A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data. Then, the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory (LSTM) networks and particle swarm optimization-support vector machine (PSO-SVM) models for landslide displacement prediction tasks. Results on two landslides in the Three Gorges Reservoir (TGR) region show a significant improvement in LSTM model prediction performance when trained on augmented data. For instance, in the case of the Baishuihe landslide, the average root mean square error (RMSE) increases by 16.11%, and the mean absolute error (MAE) by 17.59%. More importantly, the model's responsiveness during mutational stages is enhanced for early warning purposes. However, the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM. Further analysis indicates that an optimal synthetic-to-real data ratio (50% on the illustration cases) maximizes the improvements. This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results. By using the powerful generative AI approach, RGAN-LS can generate high-fidelity synthetic landslide data. This is critical for improving the performance of advanced ML models in predicting landslide displacement, particularly when there are limited training data. Additionally, this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas. (c) 2024 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).