Prediction method for rock shear strength parameters based on data-driven and interpretability analysis

The technology known as cemented paste backfill (CPB) has gained considerable popularity worldwide. Yield stress (YS) is a significant factor considered in the assessment of CPB’s flowability or transportability. The minimal shear stress necessary to start the flow is known as Yield stress (YS), and it serves as an excellent measure of the strength of the particle-particle interaction. The traditional evaluation and measurement of YS performed by experimental tests are time-consuming and costly, which induces delays in construction projects. Moreover, the YS of CPB depends on numerous factors such as cement/tailing ratio, solid content and oxide content of tailing. Therefore, in order to simplify YS estimation and evaluation, the Artificial Intelligence (AI) approaches including eight Machine Learning techniques such as the Extreme Gradient Boosting algorithm, Gradient Boosting algorithm, Random Forest algorithm, Decision Trees, K-Nearest Neighbor, Support Vector Machine, Multivariate Adaptive Regression Splines and Gaussian Process are used to build the soft-computing model in predicting the YS of CPB. The performance of these models is evaluated by three metrics coefficient of determination (R2), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The 3 best models were found to predict the Yield Stress of CPB (Gradient Boosting (GB), Extreme Gradient Boosting (XGB) and Random Forest (RF), respectively) with the 3 metrics of the three models, respectively, GB {R2 = 0.9811, RMSE = 0.1327 MPa, MAE = 0.0896 MPa}, XGB {R2 = 0.9034, RMSE = 0.3004 MPa, MAE = 0.1696 MPa} and RF {R2 = 0.8534, RMSE = 0.3700 MPa, MAE = 0.1786 MPa}, for the testing dataset. Based on the best performance model including GB, XG and RF, the other AI techniques such as SHapley Additive exPlanations (SHAP), Permutation Importance, and Individual Conditional Expectation (ICE) are also used for evaluating the factor effect on the YS of CPB. The results of this investigation can help the engineers to accelerate the mixed design of CPB.

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

An experimental investigation to predict the compressive strength of lightweight Ceramsite aggregate UHPC using boosting and bagging techniques

To identify factors affecting and key environmental factors of the Oncomelania hupensis snail density in the Yangtze River Delta region using machine learning methods. Administrative village-level O. hupensis snail survey data in the Yangtze River Delta (including Shanghai Municipality, Jiangsu Province, Zhejiang Province and Anhui Province) from 2011 to 2021 were retrieved from the Information Management System for Parasitic Disease Control of Chinese Center for Disease Control and Prevention. Environmental factor data were captured from the Google Earth Engine platform, including elevation, slope, terrain, normalized difference vegetation index (NDVI), vegetation type, soil type, total petroleum hydrocarbon (TPH), ammonium nitrogen, inorganic nitrogen, dissolved oxygen, pH of water, chemical oxygen demand (COD) and inorganic phosphorus, and climatic factor data in the study region were retrieved from the Copernicus Climate Data Store, including annual precipitation, aridity index and annual mean temperature (AMT). O. hupensis snail survey data in the Yangtze River Delta region from 2011 to 2021 were randomly divided into a training set (70%) and a test set (30%), and five machine learning models were selected for machine learning model construction and comparative analysis of the O. hupensis snail density using the software R 4.3.0, including random forest (RF), eXtreme gradient boosting (XGBoost), support vector machine (SVM), gradient boosting machine (GBM) and neural network (NN). The XGBoost model was employed to construct a predictive model for the O. hupensis snail density, and the impact of each environmental factor on O. hupensis snail distribution was quantified. The SHapley Additive exPlanations (SHAPs) values were calculated to estimate the average contribution of each variable to the model prediction, and the core environmental factors affecting the O. hupensis snail population density were screened. Among the five machine learning models, the XGBoost model exhibited the optimal comprehensive performance, with the coefficient of determination (R2) of 0.855, mean squared error (MSE) of 0.188, root mean squared error (RMSE) of 0.434 and mean absolute error (MAE) of 0.155, respectively. Analysis of factors affecting the O. hupensis snail density with the XGBoost model showed that among the 16 environmental factors, the top four high-impact factors ranked by SHAPs values included annual precipitation, elevation, aridity index and NDVI, with cumulative SHAPs contributions of 75%, which was higher than that of other environmental factors. If NDVI was higher than 0.6, the O. hupensis snail density increased with NDVI and peaked if NDVI was 0.8 (1.60 snails/0.1 m2). The O. hupensis snail density increased with elevation if the elevation ranged from 14 to 40 m, and slowly rose if the annual precipitation ranged from 900 to 1 300 mm, and then increased rapidly to the peak (1.52 snails/0.1 m2) if the annual precipitation ranged from 1 300 to 1 500 mm. In addition, the O. hupensis snail density increased rapidly to the maximum (1.60 snails/0.1 m2) if the aridity index ranged from 0.8 to 1.1, and decreased gradually if the aridity index exceeded 1.1. The XGBoost model shows excellent performance in prediction of the O. hupensis snail density and identification of key environmental factors in the Yangtze River Delta region. Annual precipitation, elevation, aridity index and NDVI are key environmental factors affecting the distribution and density of O. hupensis snails in the Yangtze River Delta region.

Use of claims data to predict the inpatient length of stay among U.S. stroke patients

To accurately predict the impact of nitrogen reduction strategies on greenhouse gas emissions in agricultural systems and support informed decision-making for a green, low-carbon transition, this study proposes a multi-model ensemble prediction framework using integrated machine learning techniques. To address the limitations of traditional emission assessment methods—such as their inability to handle high-dimensional data, nonlinear interactions, and regional heterogeneity—three models are employed: eXtreme Gradient Boosting (XGBoost), Random Forest, and Light Gradient Boosting Machine (LightGBM). These models are combined using a Stacking ensemble approach to enhance predictive accuracy and robustness. Comprehensive performance evaluations and variable importance analyses were conducted. The proposed framework achieved an R² of 0.901 and a Root Mean Square Error (RMSE) of 0.301 on the N₂O Global dataset, significantly outperforming benchmark models such as Natural Gradient Boosting (NGBoost) (R²: 0.829; RMSE: 0.382) and Categorical Boosting (CatBoost) (R²: 0.864; RMSE: 0.341). It also demonstrated strong adaptability on the Rothamsted and DayCent datasets. SHapley Additive exPlanations (SHAP) analysis identified nitrogen application rate, rainfall frequency, and soil type as the most influential factors affecting emissions. Scenario simulations showed that a 20% reduction in nitrogen application could decrease emissions to 3.124 kg N₂O-N/ha/year. When combined with optimized management practices—such as cover cropping and improved tillage scheduling—emissions were further reduced to 2.487 kg N₂O-N/ha/year. Accordingly, the proposed method provides a practical exploration for enhancing the applicability and interpretability of models. It offers valuable insights for agricultural environmental modeling and emission reduction policy support, demonstrating both theoretical significance and practical relevance.

Modeling of necking area reduction of carbon steel in hydrogen environment using machine learning approach

Compressive strength prediction of sustainable concrete incorporating rice husk ash (RHA) using hybrid machine learning algorithms and parametric analyses

The accurate prediction of the residual strength of defective pipelines is a critical prerequisite for ensuring the safe operation of oil and gas pipelines, and it holds significant implications for the pipeline’s remaining service life and preventive maintenance. Traditional machine learning algorithms often fail to comprehensively account for the correlative factors influencing the residual strength of defective pipelines, exhibit limited capability in extracting nonlinear features from data, and suffer from insufficient predictive accuracy. Furthermore, the predictive models typically lack interpretability. To address these issues, this study proposes a hybrid prediction model for the residual strength of defective pipelines based on Bayesian optimization (BO) and eXtreme Gradient Boosting (XGBoost). This approach resolves the issues of excessive iterations and high computational costs associated with conventional hyperparameter optimization methods, significantly enhancing the model’s predictive performance. The model’s prediction performance is evaluated using mainstream metrics such as the Mean Absolute Percentage Error (MAPE), Coefficient of Determination (R2), Root Mean Square Error (RMSE), robustness analysis, overfitting analysis, and grey relational analysis. To enhance the interpretability of the model’s predictions, reveal the significance of features, and confirm prior domain knowledge, Shapley additive explanations (SHAP) are employed to conduct the relevant research. The results indicate that, compared with Random Forest, LightGBM, Support Vector Machine, gradient boosting regression tree, and Multi-Layer Perceptron, the BO-XGBoost model exhibits the best prediction performance, with MAPE, R2, and RMSE values of 5.5%, 0.971, and 1.263, respectively. Meanwhile, the proposed model demonstrates the highest robustness, the least tendency for overfitting, and the most significant grey relation degree value. SHAP analysis reveals that the factors influencing the residual strength of defective pipelines, ranked in descending order of importance, are defect depth (d), wall thickness (t), yield strength (σy), external diameter (D), defect length (L), tensile strength (σu), and defect width (w). The development of this model contributes to improving the integrity management of oil and gas pipelines and provides decision support for the intelligent management of defective pipelines in oil and gas fields.

The mechanical characteristics of rocks, specifically uniaxial compressive strength (UCS) and elastic modulus (E), serve as crucial factors in ensuring the integrity and stability of relevant projects in mining and civil engineering. This study proposes a novel hybrid PSO (particle swarm optimization) with tree-based models, such as gradient boosting regressor (GBR), light gradient boosting machine (LightGBM), random forest (RF), and extreme gradient boosting (XGBoost) for predicting UCS and E of rock samples from Block IX of the Thar Coalfield in Pakistan. A total of 122 datasets were divided into training and testing sets, with an 80:20 ratio, respectively, to develop the predictive models. Key performance metrics, including the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), were employed to assess the model’s predictive performance. The results indicate that the PSO-XGBoost model demonstrated the highest accuracy in predicting UCS and E, outperforming the other models, which exhibited inferior predictive performance. Furthermore, this study utilized the SHAP (Shapley Additive exPlanations) machine learning method to enhance our understanding of how each input feature variable influences the output values of UCS and E. In conclusion, the proposed framework offers significant advantages in evaluating the strength and deformation of rocks at Thar Coalfield, with promising applications in the field of mining and rock engineering.

Accurate prediction of thrust and torque is essential for optimizing the performance, energy efficiency, and control of brushless direct current (BLDC) motors in unmanned aerial vehicles (UAVs). Traditional physics-based models often struggle to capture the nonlinear relationships between motor input parameters and aerodynamic outputs, prompting the exploration of data-driven approaches. This study evaluates the predictive capabilities of six ensemble learning algorithms, including Bootstrap Aggregating (Bagging), Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Stacked Generalization (Stacking), in modeling thrust and torque. Experimental data were obtained using a Tyto Robotics thrust stand designed for precise static performance testing of electric propulsion systems. Among the models, CatBoost exhibited the highest accuracy in thrust prediction with a coefficient of determination of 0.9873, a root mean square error (RMSE) of 7.0506, a mean absolute error (MAE) of 6.0610, and a mean absolute percentage error (MAPE) of 2.10%. In torque prediction, AdaBoost demonstrated superior performance, achieving an R 2 of 0.9713, RMSE of 0.0018, MAE of 0.0013, and MAPE of 2.60%, effectively capturing complex electromechanical dynamics. In contrast, XGBoost underperformed in thrust prediction due to hyperparameter sensitivity, while Stacking showed limited generalization in torque estimation. Bagging and GBM delivered moderate and consistent results across both outputs. The findings underscore the potential of CatBoost and AdaBoost for robust predictive modeling of UAV propulsion systems, contributing to enhanced control and system design in autonomous flight applications.

In recent years, diabetes has become a global public health problem, and it is reported that the migrant Indians have more prevalence rate of Type-II diabetes. Also, the type-II diabetes in Indians are increased to a large extent due to modern lifestyle, food habits etc. In this work, an ElectroGastroGram (EGG) based non-invasive assessment for early prediction of type-II diabetes is proposed. Furthermore, the EGG signals are acquired from normal individuals and people with an age group between 50 and 65 who are suffering from Type-II diabetes using three electrode EGG acquisition devices. Also, the Explainable Artificial Intelligence (XAI) especially SHapley Additive exPlanations (SHAP) and Meta-Heuristics based feature selection methods are utilized to determine the prominent EGG signal features. A framework is devised using Meta-Heuristic based Hybrid Extreme Gradient (MH-XGB) Boost Classifier for an efficient classification of normal EGG signals and diabetic EGG signals. The proposed MH-XGB classifier is compared with the benchmark models namely Random Forest (RF) classifier and conventional Extreme Gradient Boosting (XGBoost) classifier by using performance metrics. Results demonstrate that the proposed MH-XGB classifier exhibits accuracy, sensitivity, specificity of 95.8%, 100%, and 92.3% respectively which is superior to other benchmark models. Additionally, it is demonstrated that the AUC, F1 Score and False Positive Rate (FPR) of the proposed MH-XGB classifier is 0.9545, 0.96 and 0.077 respectively. The proposed method is highly useful for early prediction of real-time societal disease (diabetes—Type-II) in an effective manner.

The purpose of this article is to address the persistent challenge of reliable power demand forecasting in modern energy systems, where dynamic fluctuations and noisy signals often reduce model accuracy and credibility. Traditional forecasting methods, although widely applied, struggle to adapt to stochastic variations, limiting their usefulness for grid stability and long-term planning. This study proposed a Hybrid Power Demand Forecasting Model with Uncertainty Estimation under Input Perturbations (HPDEF-MUIP). The model combined three machine learning algorithms, Extreme Gradient Boosting, Categorical Boosting, and RandomForest, into a hybridised model designed to enhance robustness. Data preprocessing included Empirical Mode Decomposition for signal refinement, Kalman Filtering for noise reduction, and normalisation for balanced scaling. To simulate and evaluate resilience against noisy environments, adversarial perturbation strategies such as the Fast Gradient Sign Method were introduced. The model was trained and validated on a large smart meter dataset spanning 2022–2025, using ten-fold cross-validation and hyperparameter optimisation with Genetic Algorithms. Performance was assessed through standard accuracy metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), the coefficient of determination and Mean Absolute Percentage Error (MAPE). Findings showed that HPDEF-MUIP achieved an R² of 0.9539 and a MAPE of (3.12%), significantly outperforming baseline models. Under perturbed conditions, adversarial training reduced error variance by (17%), confirming improved resilience. The study concludes that hybrid model learning with uncertainty estimation offers a reliable and interpretable tool for supporting smart grid operations, demand-response planning, and sustainable energy management.

Nighttime high-power aircraft engine run-ups represent a critical operational activity with potential implications for airport management and environmental assessment; yet, their quantitative prediction remains limited in existing literature. The objective of this study is to develop and evaluate a data-driven machine learning framework capable of accurately predicting nighttime high-power engine run-up characteristics using historical operational data. A supervised learning methodology is adopted using an open-access dataset comprising approximately 860 nighttime run-up records. The proposed framework includes data preprocessing, temporal feature engineering (month, season, and quarter), exploratory data analysis, correlation assessment, and comparative model development using Linear Regression, Random Forest, Gradient Boosting, Extreme Gradient Boosting (XGBoost), and an Artificial Neural Network (multilayer perceptron). Model performance is evaluated using coefficient of determination (R²), root mean square error (RMSE), mean absolute error, and mean absolute percentage error, supported by predicted-versus-actual comparisons and learning-curve analysis. The results demonstrate that ensemble-based models outperform linear and neural network approaches, with XGBoost achieving the highest predictive accuracy on the testing dataset (R² ≈ 0.90, RMSE ≈ 2.15). Learning curves further indicate stable validation performance with increasing training data size. The proposed machine learning framework provides a structured and data-driven approach for predicting nighttime high-power aircraft engine run-up activity within the analyzed operational dataset, offering a valuable analytical tool for data-driven assessment of airport ground operations.

This study examines the wear characteristics of A356-Al 2 O 3 -B 4 C composites produced via stir casting, incorporating three reinforcement compositions (5, 10, and 15 wt.% Al 2 O 3 with a constant 5 wt.% B 4 C). We used seven different machine learning algorithms to predict wear rates based on experimental tribological data: Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Gradient Boosting (GB), Light GBM, and AdaBoost. The Random Forest model was better at making predictions, with a R 2 of 0.83, a mean absolute error (MAE) of 0.0012 m 3 /Nm, a mean absolute percentage error (MAPE) of 1.3%, and a root mean squared error (RMSE) of 0.0094 m 3 /Nm, which means it was 83% accurate. Experimental wear rates ranged from 4.3 × 10 −14 to 3.43 × 10 −13 m 3 /Nm across varying sliding distances (1500–6000 m), loads (10–20 N), and velocities (1.45–2.66 m/s). Systematic k-fold cross-validation and grid search hyperparameter Optimisation to make sure the model worked well. The results show that machine learning, especially ensemble tree-based methods, can accurately predict how well composite materials will wear, which speeds up the process of optimizing material design and cuts down on the cost of experiments. This study shows that combining artificial intelligence with traditional tribological characterization can improve the ability to predict how composite materials will behave in the future. It also sheds light on the relative importance of tribological operating parameters.