TL;DR
The proposed framework combined a curated database, neural network-based curve prediction, and hyperparameter optimization, providing a robust approach for evaluating the soil arching effect, providing a robust approach for evaluating the soil arching effect.
The proposed AFELA–machine learning framework provides a computationally efficient, reliable, and interpretable approach for tunnel stability assessment in sloping rock mass conditions.
Ground settlement induced by shield tunnel boring machine (TBM) excavation is a major geotechnical concern in urban tunneling because it may affect the safety of adjacent structures and underground infrastructure. In this study, machine learning models were developed to predict the maximum settlement induced by shield TBM excavation using a three-dimensional numerical analysis database comprising 320 simulation cases generated from combinations of tunnel diameter (D), ground elastic modulus (E), face pressure (FP), and backfill pressure (BP). Random forest (RF) and extreme gradient boosting (XGBoost) models were developed and compared with an existing regression-based settlement prediction equation. Predictive performance and generalization capability were evaluated using random split and GroupKFold validation techniques. Under random split validation, RF achieved the highest predictive performance, with a coefficient of determination of 0.997 and a root mean square error of 0.438 mm, followed by XGBoost. Both machine learning models outperformed the existing settlement prediction equation. However, model performance decreased substantially under GroupKFold validation, indicating limited generalization capability under unseen D–E grouped conditions. The results demonstrate that the developed machine learning models provide accurate predictions within the range of tunnel–ground conditions represented by the adopted numerical analysis database. The findings highlight the importance of evaluating both predictive performance and generalization capability, particularly when machine learning models developed from numerical analysis databases are applied beyond the conditions represented in the training database.
The significance of rock brittleness is well‐recognized in the fields of geotechnical engineering and energy exploration. To enhance the predictive precision of rock brittleness, this paper proposes a Stacking integrated algorithm. This algorithm synergistically combines various meta models and foundational models, utilizing a suite of nine algorithm modes: Gaussian Process Regression, Support Vector Machine, Backpropagation Neural network, Extreme Learning Machine network, Decision Tree, Random Forest, Extreme Gradient Boosting, Lasso Regression, and Ridge Regression. Furthermore, Tuna and Bayesian optimization algorithms are utilized to refine the model's performance. Additionally, a new diversity index, k, based on the ratio of correlation coefficients, has been introduced to facilitate the optimal selection of base models for the Stacking integrated algorithm. The predictive accuracy of the Stacking integrated model, as determined by the proposed diversity index k, surpasses that of the finest individual base model and outperforms other sets of five integrated base models with an equivalent number of components. This underscores the efficacy of the diversity index k in guiding the selection of appropriate base models for the stacking process. The most effective model for predicting rock brittleness incorporates the Extreme Learning Machine network, Decision Tree, Random Forest and Extreme Gradient Boosting. This ensemble model demonstrates superior accuracy over the single best model, the Decision Tree, by reducing the average brittleness prediction error rate by 0.3745 and elevating the determination coefficient ( R 2 ) value from 0.9118 to 0.9629.When compared with the Particle Swarm Optimization model, this composite model achieves an increase of 0.1498 in R 2 .
Accurate prediction of tunnel water inflow in water-rich fault zones is important for groundwater control design and construction risk prevention. In this study, a per-linear-meter tunnel water inflow database containing 425 valid samples was established through orthogonal numerical simulations based on a three-dimensional steady-state seepage model with a grouting ring. The input variables included four hydraulic and grouting parameters and two excavation-position descriptors, namely the excavation-position distance and excavation-position category, thereby reflecting both the water-blocking effect of grouting reinforcement and the spatial variation in water inflow as the excavation face approached the fault zone. Considering that the samples were generated from 25 orthogonal simulation cases at different excavation positions, grouped validation was adopted to reduce information leakage at the simulation-case level. Four baseline machine learning models, including SVM, RF, XGBoost, and CatBoost, were evaluated using ten repeated grouped hold-out validations. CatBoost achieved the best overall baseline generalization performance, with an average test R2 of 0.6209 ± 0.0405, MAE of 0.1084 ± 0.0079, and RMSE of 0.1555 ± 0.0085. CatBoost was therefore selected for further hyperparameter optimization. Subsequently, random search, Bayesian optimization, the Osprey Optimization Algorithm, and the Grey Wolf Optimizer were compared under the same search space and computational budget. Hyperparameter optimization was conducted only within the training set using grouped cross-validation, and the independent grouped test set was used only for final evaluation. The results showed that the unoptimized CatBoost model achieved the best overall balance between prediction accuracy, stability, and computational efficiency. Although RS-CatBoost slightly improved MAE and MAPE among the optimized models, none of the optimization strategies consistently outperformed the unoptimized CatBoost baseline, indicating that the choice of hyperparameter optimization algorithm played a secondary role under the current dataset and grouped-validation framework. The proposed framework is intended as a preliminary modeling reference under controlled numerical simulation conditions, and its practical engineering reliability requires further validation using field monitoring data or independent benchmark cases.