UCS Prediction of Carbonate Rocks using Deep Feedforward Neural Networks with Aquila Algorithm Model

Machine-learning modeling of pore pressure variation in geological CO2 storage reservoir

Bayesian-Optimized Machine Learning Framework with SHAP Interpretation for Rockburst Intensity Prediction in Deep Underground Engineering

As mineral resource development moves deeper into the earth, mine dynamic disasters, represented by rockbursts, occur frequently. Due to the combined effects of in situ rock stress state and geostress conditions, it is difficult to obtain reliable prediction results using traditional empirical criteria or single-index prediction methods. To address these issues, this paper constructs a rockburst sample database based on the existing literature, including maximum tangential stress, uniaxial compressive strength, uniaxial tensile strength, elastic energy index, stress coefficient, and brittleness coefficient. Secondly, six typical machine learning algorithms are selected for rockburst level classification research. Then, to address the problem of imbalanced sample distribution, the SMOTE oversampling method is introduced to balance the data, and Bayesian optimization and cross-validation are combined to optimize the model hyperparameters. The results show that optimized XGBoost models exhibit high accuracy and stability in rockburst level discrimination, and accuracy reached 0.7664, recall was 0.7664, macro-P was 0.7664, and macro-F1 was 0.7662. Furthermore, taking the BO-XGBoost model as an example, the SHAP method is introduced to analyze the interpretability of the model’s prediction results. The results show that the elastic energy index and stress-related indices are the main controlling factors affecting the intensity of rockburst; they accounted for 25.75% and 22.68%, respectively. Based on the above research results, this paper further explores the ideas for rockburst safety management and prevention from the aspects of energy control, stress regulation, and optimization of rock mass structural characteristics, providing theoretical basis and technical support for the scientific formulation of rockburst risk identification, level prediction, and safety prevention and control measures in deep underground engineering.

Machine learning analyses of low salinity effect due to surface-charge alteration in carbonate porous media

Accurate prediction of rock–brine zeta potential is critical for understanding wettability alteration and optimizing low-salinity water flooding (LSWF) in carbonate reservoirs. Although numerous experimental studies have investigated this phenomenon, the complex interactions among brine chemistry, rock mineralogy, fluid properties, and operational conditions remain inadequately quantified. This study systematically evaluated these relationships using nine machine learning models: Multiple Linear Regression (MLR), Regression Tree (RT), Random Forest (RF), Support Vector Machine (SVM), Gaussian Process Regression (GPR), Adaptive Neuro-Fuzzy Inference System (ANFIS), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) network, and Deep Neural Network (DNN). A dataset of approximately 900 experimental zeta potential measurements was used for model training and validation. Hyperparameters were optimized to maximize predictive accuracy and generalization, with performance assessed using root mean square error (RMSE) and efficiency factor (EF). The RBF network achieved the highest predictive accuracy (overall RMSE = 2.89 mV; EF = 0.96) and demonstrated robust generalization across varying training dataset proportions. DNN and RF also performed strongly, whereas linear (MLR) and fuzzy-based (ANFIS) models showed limited capacity to capture nonlinear electrochemical interactions. Sensitivity analysis indicated that brine ionic composition, particularly Na⁺, Ca²⁺, SO₄²⁻, Sr²⁺, and HCO₃⁻ concentrations, had the greatest influence on zeta potential. The proposed RBF-based predictive framework offers a reliable and efficient tool for estimating surface charge under diverse reservoir conditions, thereby improving mechanistic understanding of wettability alteration during LSWF.

Performance and Limitations of Machine Learning Models for Groundwater Level Prediction Using Hydro-Climatic Variables

Accurate groundwater level (GWL) prediction is essential for sustainable groundwater management and resource planning. However, it is challenging in heterogeneous hydrogeological settings for physics-based models, particularly under limited subsurface characterisation. Machine learning (ML) techniques can capture complex spatio-temporal groundwater dynamics, complementing conventional modelling approaches. This study systematically evaluates the performance and limitations of ML models for GWL prediction in sandstone and mudstone formations, with emphasis on the influence of local hydrogeological conditions. Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and Random Forest (RF), along with their wavelet-enhanced counterparts, were applied to monthly hydro-climatic data from 11 observation wells in the Lower Otter Catchment, UK, covering 2011–2023. The final four years were reserved for validation. Time-series predictors were used because time-invariant and sparsely available geological parameters provide limited explanatory power for local-scale GWL dynamics. Their influence is implicitly reflected in observed GWL responses. Model performance was assessed using statistical criteria, including the coefficient of determination (R 2 ). Additionally, a new metric, the Data Difference and Trend Index (DDTI), was introduced to measure the proportion of simulated values matching observed trends within a predefined threshold (e.g. 0.5 m). Model performance was site-specific, with validation R 2 ranging from < 0.1 to > 0.9. This indicates the dominant influence of local hydrogeological conditions, with lower accuracy observed in partially confined, non-recharge-dominated, and river-disconnected wells. A 2-month time lag produced optimal model performance, reflecting the catchment’s characteristic response time to infiltration processes. Individual models occasionally outperformed ensemble averages, which showed fewer outliers. Wavelet transforms did not consistently enhance performance. Model efficacy varied seasonally, with validation R 2 markedly lower in summer (e.g. < 0.1) and higher in autumn (e.g. > 0.9). This emphasises key limitations of ML-based GWL prediction, including reduced reliability near lithological boundaries and strong sensitivity to hydro-climatic conditions, constraining model transferability. Overall, the findings highlight the value of moving beyond performance benchmarking to explicitly identify hydro-climatic and hydrogeological conditions under which ML models lose reliability, informing groundwater modelling and sustainable water management. Graphical Abstract This study evaluates the performance and limitations of machine learning (ML) models for predicting groundwater levels (GWL) in sandstone and mudstone formations using hydro-climatic variables across 11 observation wells in the Lower River Otter Water Body, UK. Four ML models, i.e. Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and Random Forest (RF), along with their wavelet-enhanced versions, were applied to monthly hydro-climatic data from 2011 to 2023, with the last four years reserved for validation. Model performance was assessed using the coefficient of determination (R 2 ), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency (NSE), and a novel Data Difference and Trend Index (DDTI), which quantifies the proportion of simulated data following observed trends within a defined threshold. Results indicate that predictive accuracy is highly site-specific, with local hydrogeological conditions strongly influencing outcomes. No model consistently captured GWL near interior boundaries where sandstone is confined by mudstone, and neither wavelet transforms nor model ensembles reliably improved performance. Seasonal variability also affected model efficacy, with the highest accuracy in autumn and the lowest in summer. Overall, the workflow highlights the limitations of ML for GWL prediction and provides insights for future hydrogeological modelling.

An Insight Into Rock Brittleness Prediction Based on Stacking Integrated Algorithm

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 .

Refined simulation of groundwater level dynamics based on a machine learning stacking framework

Accurate and rapid prediction of groundwater levels (GWL) is essential for effective groundwater management. Machine learning models are efficient tools for GWL prediction, but individual models often suffer from limited generalization due to inherent randomness. This study proposed a stacking-based GWL prediction framework suitable for arid regions in Northwest China. Feature variables affecting GWL were selected using variable importance in projection (VIP). Then, three machine learning models—artificial neural networks (ANN), random forests (RF), and Light Gradient Boosting Machine (LightGBM)—were developed, and their outputs were integrated using a support vector regression (SVR)-based stacking method to enhance the accuracy of GWL prediction. The results show that the factors of influencing GWL changes vary significantly across different regions, and selecting the most contributive feature variables is beneficial for model construction. Among the individual models, the RF model demonstrated higher accuracy and more stable performance, outperforming the ANN and LightGBM models. However, individual models exhibited poor generalization during validation. In contrast, the stacking model maintained high performance, demonstrating superior generalization. Compared to the best-performing individual model (RF) in validation period, the Nash–Sutcliffe efficiency ( NSE ) and Kling–Gupta efficiency ( KGE ) of stacking model improved by 0.11–0.66 and 0.05–0.41, the correlation coefficient ( R 2 ) increased by 0.05–0.3, and root mean square error ( RMSE ) reduced by 0.01–0.1 m. In the stacking simulation, RF had the highest average contribution (80.2%), followed by ANN (13.9%) and LightGBM (5.9%). This study provides a stacking simulation framework based on machine learning methods for precise groundwater level simulation, which can serve as a reference for groundwater level simulation in other regions.