Mixture-of-Experts Learning for Mixture-Response Interpretation and Screening of PE-ECC

Transfer-learned stacked models for assessing mechanical and environmental properties of glass powder UHPC

An informed regression-based knowledge distillation framework for simultaneous prediction of physical and mechanical properties of thermoset epoxy polymers

Epoxy polymers are widely used due to their multifunctional properties, however their complex 3D molecular structure, multi-component nature, and lack of curated datasets have limited the application of machine learning (ML) for these materials.Existing ML studies are largely restricted to simulation data, specific properties, or narrow constituent ranges. To address these limitations, we developed an Informed Regression-based Knowledge Distillation (R-KD) framework for predicting multiple physical (glass transition temperature, density) and mechanical properties (elastic modulus, tensile strength, flexural strength, adhesive strength) of thermoset epoxy polymers. The model was trained on experimental literature data covering diverse monomer classes (9 resins, 37 hardeners). The best-performing single-task regression model per target property serves as teacher model capturing nonlinear feature-property relationships, while a unified neural network student model learns distilled knowledge across all properties simultaneously. By encoding the target property as an input feature, the student model leverages cross-property correlations. Molecular-level descriptors extracted from SMILES representations using RDKit create a physics-informed model. Comparative analysis demonstrates superior or comparable prediction accuracy over multi-task NN baseline model and conventional ML models. Simultaneous multi-property prediction further improves accuracy through information sharing across correlated properties. The proposed framework enables accelerated design of novel epoxy polymers with tailored properties.

Dominant-learner adaptive mixing for concrete compressive strength prediction

Accurate prediction of concrete compressive strength is essential for mixture design, quality control, and the broader use of supplementary cementitious materials in low-carbon construction. Fly ash concrete is particularly challenging to model because its strength development is affected by nonlinear interactions among binder composition, water–binder relationships, admixture dosage, and material characteristics. To address this problem, this study proposes a Dominant Learner with Adaptive Mixing (DLAM) framework for data-driven strength prediction. DLAM uses inner cross-validation to identify the most reliable learner from a pool of machine learning models and introduces a validation-controlled Ridge calibration step to exploit complementary information among candidate predictions. The calibration branch is adopted only when it improves the inner-validation root mean squared error (RMSE), thereby reducing the risk of unnecessary model combination and performance degradation. The framework is evaluated using a leakage-free repeated outer/inner validation protocol on a fly ash concrete dataset and is further examined on an independent public concrete strength dataset. DLAM is compared with individual learners, adaptive model-averaging baselines, and Stacking. The results show that DLAM achieves the lowest mean RMSE among the focused comparators on both datasets, with a clear improvement on the external dataset and a more modest gain on the fly ash dataset. These findings demonstrate that validation-controlled calibration provides a transparent and robust way to enhance machine-learning-based concrete strength prediction, especially when different learners capture complementary aspects of the mixture–strength relationship.

Machine Learning Prediction of Concrete Compressive Strength: Model Comparison, CatBoost Optimization, and SHAP Interpretation

A comparative framework evaluating nine regression algorithms using the UCI Concrete Compressive Strength dataset, jointly integrating correlation-corrected statistical validation, multi-model Bayesian optimization, and domain-informed feature engineering with SHAP interpretation, rarely combined in prior concrete-strength studies.

Data-driven prediction and classification of multi-component alloys using interpretable machine learning

The design of advanced metallic alloys is challenged by complex, nonlinear interactions among multiple alloying elements, making conventional trial-and-error approaches costly and time-intensive. This study presents an integrated, interpretable machine learning framework applied to a dataset of 2,672 multi-component alloy systems, using elemental composition as the sole input. A multi-output Random Forest Regressor simultaneously predicts Ultimate Tensile Strength (UTS) and Liquidus Temperature, achieving a test R² of 0.848 and a 5-fold cross-validation R² of 0.849 ± 0.017, outperforming Linear Regression (R² = 0.512) and Gradient Boosting (R² = 0.787) baselines. A Logistic Regression classifier identifies high-performance alloy compositions defined by simultaneous UTS and liquidus temperature thresholds achieving an overall accuracy of 82% and an AUC of 0.871. Threshold sensitivity analysis confirms classification stability across varying performance criteria. Principal Component Analysis (PCA) and K-Means clustering, applied to the full compositional feature space, reveal three distinct alloy families with systematic differences in mechanical and thermal properties. Critically, interpretability is preserved throughout via SHAP analysis and permutation-based feature importance, identifying Vanadium (V), Iron (Fe), Tungsten (W), and Carbon (C) as the dominant compositional drivers a finding that both confirms and extends established metallurgical understanding. The dataset was verified to contain no missing values across all 31 elemental features. Collectively, the proposed framework provides a scalable and interpretable foundation for accelerated alloy screening, property prediction, and data-driven materials discovery.

Interpretable and Uncertainty-Aware Machine Learning for Shear Strength Prediction of FRCM-Strengthened RC Beams

An interpretable and uncertainty-aware machine-learning framework for estimating the shear capacity of FRCM-strengthened beams enables accurate, transparent, and uncertainty-aware assessment of shear capacity in FRCM-strengthened concrete beams.