Search

Machine Learning-Based Prediction of Compressive Strength in Basalt Fiber Reinforced Concrete

Accurate prediction of the mechanical strength of Basalt Fiber Reinforced Concrete (BFRC) is critical for structural design, safety assessment, and the advancement of sustainable infrastructure in civil engineering. Traditional prediction methods often fail to capture the nonlinear relationships between BFRC mix proportions and resulting strength characteristics, leading to unreliable estimations. To address this limitation, this study proposes the Optimized Moment Balanced Machine (OMBM), an advanced machine learning model developed to improve the predictive accuracy of BFRC strength parameters. The model was trained and evaluated using key input features, including cement content, silica fume, fly ash, superplasticizer, water, aggregate composition, and fiber property parameters. The performance of the OMBM was benchmarked against four established machine learning models, such as Least Squares Support Vector Machine (LSSVM), Backpropagation Neural Network (BPNN), K-Nearest Neighbors (KNN), and Linear Regression (LR). Results from ten-fold cross-validation show that OMBM consistently outperforms the comparison models across five evaluation metrics. It achieved the lowest RMSE (2.411), MAE (1.788), and MAPE (4.08%), along with the highest values for correlation coefficient (R = 0.978), and coefficient of determination (R2 = 0.956). Furthermore, the OMBM achieved a Reference Index (RI) score of 1.000, which confirms its position as the leading predictive model within this comparative framework. These results confirm the robustness and reliability of the proposed OMBM model, making it a highly effective tool for accurate strength prediction of BFRC. This approach offers significant potential for the advancement of sustainable infrastructure by enabling more accurate and efficient use of concrete materials.

Interpretable machine learning with Bayesian optimization for bond strength prediction of steel reinforcement in geopolymer concrete

Accurate estimation of bond strength between steel reinforcement and geopolymer concrete is essential for the reliable design of sustainable reinforced concrete structures. However, the highly nonlinear interactions reduce the applicability and accuracy of conventional empirical models. This study proposes a Bayesian-optimized interpretable machine learning framework to predict the ultimate bond strength of reinforced geopolymer concrete using a comprehensive experimental database compiled from published studies. A dataset of 238 samples with 20 influential input variables was assembled to represent material properties, geopolymer chemistry, and specimen geometry. Six advanced machine learning algorithms, including Support Vector Regression (SVR), Random Forest (RF), Extra Trees Regressor (ETR), Gradient Boosting Machine (GBM), XGBoost, and CatBoost, were developed and systematically compared. Hyperparameter tuning was performed using Bayesian optimization to improve model performance. The results indicate that all models achieved strong predictive capability, while the optimized CatBoost model (BO-CatBoost) provided the best performance with testing metrics of R² = 0.950, MAE = 1.173, MAPE = 11.608%, and RMSE = 1.669. A comparative evaluation with existing empirical equations further demonstrated the superior accuracy and lower prediction variability of the proposed model. To enhance model transparency, SHAP-based explainability analysis was conducted to quantify the contribution of each input parameter. The global importance analysis revealed that compressive strength, the embedment length-to-bar diameter ratio, and the cover-to-bar diameter ratio are the most influential factors governing bond strength. Additional mixture-related parameters, including the alkaline solution-to-binder ratio, curing temperature, CaO content in the binder, and the SiO₂/Al₂O₃ ratio, also contribute to the bond mechanism by influencing geopolymerization and matrix densification. The proposed framework provides both high predictive accuracy and interpretable insights, demonstrating the potential of Bayesian-optimized interpretable machine learning to support the design and optimization of sustainable reinforced geopolymer concrete structures.

Bayesian-optimised machine learning for predicting aggressive environment resistance and service life of recycled aggregate geopolymer concrete

Developing reliable computational tools for durability and service-life assessment of concrete structures in aggressive environments is essential for advancing predictive modeling in structural engineering. This study introduces machine learning (ML)–based models for forecasting the sulfate and acid resistance of recycled aggregate geopolymer concrete (RGPC), produced with untreated and surface-treated recycled concrete aggregates (RCAs) through two mixing approaches. Three algorithms, i.e. Gaussian process regression (GPR), LSBoost ensemble, and Neural Network, were trained using nine input parameters related to material composition and exposure conditions, with durability indicators, namely mass loss rate (Kw) and compressive strength retention index (Kf), as outputs. A dataset of 336 experimentally tested RGPC specimens was used, applying Bayesian Optimisation for hyperparameter tuning and 5-fold cross-validation for generalisation. Among the models, the optimized GPR achieved the highest accuracy, confirmed by the lowest objective value. Feature importance analysis highlighted environmental cations, sulfate concentration, RCA replacement level, initial compressive strength, and exposure duration as the most influential factors governing degradation. The proposed Bayesian-optimized ML framework demonstrates a robust and generalizable method for predicting durability and service life of sustainable concretes, providing a valuable tool for simulation-driven design and durability-based performance assessment in mechanics and structural engineering.

Physics-guided ensemble machine learning framework for slope failure prediction

Purpose. This research aims to provide a physics-based ensemble machine learning framework that can reliably predict slope stability and distinguish stable from unstable slopes in static and seismic conditions. Standard analytical and numerical methods have significant processing costs and oversimplified assumptions that limit their usefulness. Methods. The study analyzed 700 slope stability samples, including geotechnical and seismic factors such as slope height, slope angle, cohesion, internal friction angle, and peak ground acceleration. The proposed model now includes physics-based engineering elements, such as tan ϕ, c/H, and PGA/g, to account for geotechnical interactions. A linear meta-learner and Random Forest and Gradient Boosting regressors were used to develop a stacked ensemble framework. We assessed model strength and reliability. Findings. The devised framework showcased exceptional prediction performance with an (R2) of 0.982, a mean absolute error of 0.02 and a root mean square error of nearly 0.03. Cross-validation showed consistent generalization. Random Forests classified slope stability conditions with 97.4% accuracy. The most important parameters for slope stability predictions were the internal friction angle and cohesiveness. Furthermore, the inclusion of carefully crafted physics-based features demonstrably improved robustness, accuracy and consistency. Originality. This work introduces a pioneering, combined framework that fuses the mechanics of geotechnical soil with ensemble machine learning techniques, enhancing both interpretability and the certainty of slope stability predictions. Practical implications. The framework may support rapid, cost-effective, and interpretable preliminary geotechnical risk assessment and design screening. However, its use in slope monitoring or early-warning applications requires further field validation and integration with monitoring data.

Refined analytical frameworks for enhancing friction angle prediction in fiber-reinforced soil through advanced computational methodologies

Traditional analytical and empirical techniques often fail to accurately forecast the friction angle of fiber-reinforced soil (FRS) due to the complex, non-linear dynamics of soil-fiber interactions. To address these limitations, this study employs machine learning (ML) to enhance predictive accuracy. Bagging Regression (BR) and Lasso Regression (LR) are selected for their ability to handle diverse datasets and reduce model complexity, respectively. These models are hybridized with bio-inspired optimizers, specifically Attack Leave Optimizer (ALO) and Chaos Game Optimization (CGO), to develop four frameworks: BRAL (BR + ALO), BRCG (BR + CGO), LRAL (LR + ALO), and LRCG (LR + CGO). The objective is to optimize model parameters for superior precision in estimating the friction angle. Performance is evaluated using R², RMSE, and MAE metrics in training, validation, and testing phases. Results demonstrate that the LRAL model exhibits the highest predictive capability, achieving an R² of 0.995 and the lowest RMSE of 0.634 in the testing phase, significantly outperforming the standalone Bagging model. The developed hybrid models provide a robust tool for FRS shear strength prediction, facilitating more efficient geotechnical design.

Bayesian-Optimized Ensemble Machine Learning for Predicting Settlement of Cohesionless Soil Under Loads

Application of an artificial neural network model for predicting unconfined compressive strength of expansive soils

Machine learning-driven modeling of soil plasticity and strength parameters with interpretability insights

This study proposes advanced stacking ensemble machine learning approaches to predict soil Liquidity Index ( LI ) and Undrained Shear Strength ( Su ). Over 1,550 LI and 950 Su measurements from global research were employed. Individual regressors—Multilayer Perceptron (MLP), Random Forest (RF), and AdaBoost—were evaluated alongside ensemble strategies, including Simple Averaging, Weighted Averaging, and stacking using a Support Vector Regression (SVR) meta-learner. Hyperparameter tuning was performed using both Bayesian Optimization (BO) and Particle Swarm Optimization (PSO). AdaBoost achieved the best results for LI prediction, while RF yielded the highest accuracy for Su . Weighted Averaging ensemble methods produced outstanding predictive performances, achieving R 2 values of 0.9913 (BO) and 0.9961 (PSO) for Su , and 0.9624 (BO) and 0.9338 (PSO) for LI. BO proved superior for LI models, while PSO excelled for Su models. The results highlight the robust potential of ensemble modeling and tailored optimization in the field of geotechnical engineering.

Sovereign Ratings and Risk Pricing, Agency Divergences in the European Union

Using annual EU-27 data for 1995-2024, we examine whether sovereign ratings mainly reflect common macro-fiscal fundamentals or whether agency-specific departures from that benchmark are also priced into sovereign funding conditions. Pooled ordered probits and a machine-learning diagnostic layer for nonlinearities and thresholds for Fitch, Moody’s, and S&P identify a stable set of core rating determinants centred on inflation, debt-to-GDP, current account balance, budget balance rule indicator, output gap, old-age dependency, and revenue capacity, while within-country variation is narrower and concentrated mainly in inflation, debt, and unemployment. The machine-learning analysis confirms that flexible models absorb nearly all systematic variation between fundamentals and ratings, validating the shadow-rating decomposition used in the market-pricing test. ECB-based bond-yield regressions show that both the fundamentals-implied shadow rating and the agency-specific deviation are priced in euro-area Bund spreads: a one-notch more favourable value of either component is associated with about 50 basis points lower spreads. Evidence indicates that this pricing effect strengthens as debt rises and intensifies further once debt exceeds 100% of GDP, while a shorter crisis-period interaction is directionally similar but less precise. Sovereign ratings therefore appear to combine a common fundamentals core with discretionary overlays that markets treat as economically relevant signals.

Behavioral biases and artificial intelligence in banking decision-making: Toward explainable hybrid systems for SME financing

SME credit files arrive incomplete, and the gaps leave room for anchoring, confirmation bias and loss aversion. We compare human, algorithmic and hybrid credit decisions using a benchmark credit dataset alongside a vignette experiment with credit analysts working in Morocco's Souss-Massa region. The modelling arm pairs L2-regularised logistic regression with gradient-boosted trees, adding stratified validation, calibration analysis, SHAP and LIME. In the human arm, matched cases vary the requested amount while everything else is held constant. Analysts were least stable on borderline files, and their decisions moved with the anchor. The boosted model held steadier but leaned harder on indicators that track how thick a file is. AI-first assistance improved consistency and deepened deference to the model; human-first assistance preserved contextual overrides; explanation-gating struck the best balance, though only where SHAP and LIME agreed. We assess distribution through demographic-parity difference, disparate-impact ratio, equal-opportunity difference and false-positive-rate difference. What the results support is a governed hybrid: weak explanations withheld, overrides auditable, human review genuinely available. A regional sample and benchmark data bound how far any of these travels.

Determining Insolvency Regions in Banks: A Stochastic Dynamic Approach Integrating Liquidity and Credit Risk

We develop a continuous-time structural dynamic model to determine the exact insolvency regions of banks arising from the non-linear interaction between liquidity and credit risk. While existing literature predominantly treats these risks in isolation or via reduced-form specifications, we explicitly model the feedback loop where funding shocks and regulatory constraints force balance-sheet adjustments that can lead to endogenous insolvency. By incorporating Basel III regulatory requirements (LCR and NSFR) into a stochastic optimal control framework, we solve for the exact insolvency boundary using the Hamilton-Jacobi-Bellman (HJB) equation. To bridge the gap between theoretical complexity and supervisory practice, we derive and validate a surrogate analytical approximation function that allows for real-time monitoring. Calibrated using granular balance-sheet data from the Iranian banking sector, our model reveals significant non-linear threshold effects: the joint occurrence of liquidity stress and credit portfolio defaults disproportionately accelerates the transition toward insolvency compared to their individual effects. The proposed surrogate function offers supervisors a computationally efficient tool for stress testing and early warning systems. Our findings provide novel insights into financial frictions in emerging markets and offer a rigorous framework for integrated risk management.

AI-Driven Hybrid Probability-of-Default Scoring with Self-Attention and Isotonic Calibration for Payroll-Anchored Retail Borrowers

Payroll-anchored retail borrowers—individuals whose monthly remuneration is routed into an account at the lending institution through a salary-project arrangement—constitute the volume backbone of unsecured consumer lending in Kazakhstan, generating the largest origination flow, the lowest realized default rate, and the majority of the systemic regulatory and capital sensitivities of second-tier banks. Payroll anchoring also changes the lender’s information set, which motivates a study of how that advantage translates into model performance and borrower outcomes. We design and internally validate an explainable hybrid artificial-intelligence framework stratified by client tenure into two production models: a Weight-of-Evidence (WOE) logistic-regression scorecard for new salary-project applicants, and a hybrid scorecard for repeat applicants, in which a stacked ensemble of LightGBM, CatBoost and a multi-head self-attention neural network contributes a single WOE-encoded predictor to a second-stage L2-regularized logistic regression. The hybrid recovers a substantial share of the ensemble’s discriminatory lift while preserving an auditable, monotone scorecard at the point of decision, and isotonic recalibration restores the predicted probabilities of default to the empirical bad-rate scale required for IFRS 9 expected-credit-loss accrual and risk-based pricing. We report discrimination, calibration and stability evidence under a strict anti-leakage protocol and set out the structural preconditions under which the architecture transfers to other emerging-market payroll-anchored portfolios. We are explicit about scope: a true out-of-time validation and a full group-conditional fairness audit are identified as required next steps rather than claimed here. The contribution is a reproducible, interpretable scoring design that exploits payroll visibility while retaining full coefficient interpretability inside the production decision engine.