Machine Learning and Explainable Artificial Intelligence for Predicting Unconfined Compressive Strength in Carbonated Stabilized Soils

Comparative and Interpretable Machine Learning for Fly Ash Geopolymer Strength: Prediction, Validation and Optimization

An interpretable machine learning framework integrating Extreme Gradient Boosting with Shapley Additive Explanations to predict the 28-day compressive strength of fly ash-based geopolymer concrete (FA-GPC) is developed and experimentally validates.

Novel Interpretable Machine Learning Models for Predicting Compressive Strength of Nano-Silica Concrete

This study provides a robust, interpretable, and generalizable ML framework for optimizing nano-silica concrete mix design and highlights the strong potential of ML, particularly ensemble models combined with explainable AI techniques, to improve prediction reliability, reduce trial-and-error experimentation, and support more cost-efficient and sustainable concrete design.

Flowability prediction and artificial intelligence analysis of SCC based on machine learning

Six machine learning algorithms were employed to construct artificial intelligence models for the precise prediction of self-compacting concrete (SCC) flow properties, and the extreme gradient boosting (XGB) model was identified as exhibiting superior predictive accuracy and generalization performance.

Optimization and predictive measurement of compressive strength of iron ore slag modified concrete using data-driven supervised machine learning algorithms.

This study develops an integrated machine learning-experimental framework to predict the compressive strength (CS) of concrete incorporating ternary industrial wastes glass powder, marble powder, and iron ore slag. For this purpose, a dataset comprising 366 mix ratios and corresponding CS values was compiled from various sources for analysis. Advanced machine learning (ML) algorithms, including extreme gradient boosting (XGB), gradient boosting, and random forest (RF), were employed alongside hybrid techniques such as XGB-GBR and XGB-RF to evaluate the influence of these materials on strength. Based on the outcomes of the analysis, the hybrid XGB-GBR model demonstrates the highest balanced performance for both training (R2 = 0.911) and testing (R2 = 0.869) data sets. For validating the ML modeling and developing an interactive graphical user interface (GUI), experimental evaluation of CS and scanning electron microscopy was conducted. Additionally, feature importance modeling and optimization identified curing age and coarse aggregate as the most influential factors that would impact the model prediction. The contribution of this research lies in the combined modeling and experimental evaluation of a ternary waste concrete system, along with the development of a GUI. This deployable GUI will enhance the industrial applicability of ML-based concrete optimization by reducing material costs, minimizing trial batching, and supporting sustainable mix design practices.

Machine learning and response surface modeling for predicting strength loss of alkali-activated materials exposed to aggressive environment

Innovative sustainable concrete with waste glass materials: an explainable machine learning for compressive strength prediction

Sustainable concrete incorporating waste glass materials has emerged as a promising solution to reduce environmental impacts associated with cement production and natural aggregate depletion. Accurate prediction of compressive strength (CS) is essential for optimizing such mixtures and ensuring structural reliability. In this study, five machine learning models: Random Forest (RF), K-Nearest-Neighbors (KNN), Adaptive-Boosting (AdaBoost), Light Gradient Boosting Machine (LightGBM), and Extreme-Gradient-Boosting (XGBoost) were developed and optimized using Grid Search to predict the CS of concrete containing glass powder (GP) and glass sand (GS). A dataset of 270 experimental samples was utilized, incorporating eight input parameters, including curing duration, cement content, GP, GS, water, density, sand, and basalt. Among the models, LightGBM demonstrated superior predictive performance during testing, achieving a determination coefficient (R² = 0.964) and Root-Mean-Square-Error (RMSE = 2.05 MPa), followed by XGBoost (R² = 0.955) and RF (R² = 0.953). In contrast, KNN and AdaBoost exhibited comparatively lower performance. SHAP and Partial Dependence Plot (PDP) analyses identified curing duration and cement content as the most influential parameters, while water and GP exhibited negative effects on CS. To enhance practical applicability, the LightGBM model was deployed through a user-friendly GUI, enabling rapid and reliable prediction of CS and providing an accurate, interpretable, and practical decision-support tool for sustainable concrete mixture design.