Adel Kassem Farag Gaddafi

Machine learning offers promising tools for predicting the compressive strength of alkali-activated concrete, but high accuracy on literature-compiled datasets does not necessarily translate into reliable predictions for unseen experimental studies. This study investigates the sources and practical limits of this generalisation gap using 963 mixtures with reported 28-day compressive strength from 86 studies. A fixed XGBoost model was evaluated through random, repeated grouped and leave-one-study-out cross-validation, complemented by systematic analyses of missing-value handling, model capacity, hyperparameter selection, performance metrics and predictive uncertainty. Random cross-validation yielded R² = 0.79, whereas leave-one-study-out evaluation produced a pooled R² of 0.28. Missingness indicators alone predicted strength under random validation (R² = 0.20), revealing study-specific reporting signatures, but alternative imputation strategies and feature removal did not resolve the transfer gap. Stronger regularisation and tuning under grouped validation likewise provided little improvement. Negative per-study R² values were concentrated in studies with narrow strength ranges, demonstrating the need to interpret these scores alongside absolute prediction errors. Feature-space novelty was associated with poorer transfer, while restricting predictions to the quarter of mixtures closest to the training distribution increased pooled R² to 0.66. Adaptive conformal intervals achieved 91% mean coverage, with half-widths ranging from approximately 9 MPa for familiar mixtures to 69 MPa for the most novel. These findings point to between-study heterogeneity as a persistent constraint and support using literature-trained models for screening within well-represented composition regions, accompanied by study-aware validation and uncertainty estimates.

Environmental concerns in cement production, driven by carbon dioxide emissions, have intensified. Traditionally, fly ash (FA)-based geopolymer mortars required high-temperature curing, which is impractical. This study explores incorporating 10%, 20%, and 30% ground granulated blast furnace slag (GGBS) into FA-based geopolymers to enable room-temperature curing, enhancing practicality and energy efficiency. Eco-friendly materials, including palm oil clinker (POC) sand and eco-processed pozzolana (EPP), were also utilized. Key assessments covered density, ultrasonic pulse velocity (UPV), compressive strength, X-ray diffraction, and scanning electron microscopy. Results showed 20% and 30% GGBS significantly improved compressive strength by 76% at 7 days and 56% at 28 days. The 30% GGBS mix enhanced density by 6.1% and UPV by 12% at 28 days. Microstructural analysis confirmed the formation of calcium silicate hydrate gel, which densified the matrix. POC sand reduced density but produced lightweight mortars aligning with international standards. Ambient temperature curing reduced costs by ~ $6 per cubic meter. FA-GGBS geopolymer mortars with EPP and POC sand offer sustainable, cost–effective construction alternatives with improved strength and energy savings.