Multiple studies have investigated the use of steel, synthetic fibers, and natural fibers to reduce plastic shrinkage cracks in concrete, which are mostly caused by water evaporation from the surface of the material. This review used original published research articles from the Web of Science and Scopus database to evaluate the performance and relationship between the fiber volume, aspect ratio, compressive strength, and plastic shrinkage cracking. This review also discussed the most widely used technique for evaluating plastic shrinkage cracking, the ASTM C 1579, with two bottom restraints and a central stress riser to induce cracking, and its modified version with additional reinforcement for further restraining the ASTM C 1579 mold. Longer fibers function better than shorter fibers because of their larger surface area, which allows them to bridge fissures. It was also observed that crack initiation time is delayed when fibers are added to concrete. In addition, as the volume proportion of the fibers increased, the plastic shrinkage cracks decreased, but the compressive strength declined. Furthermore, the volume fraction of the fibers had a greater effect on reducing cracking than the aspect ratio. It was also concluded that a fiber volume inclusion below 1% is best.

Biochar-modified concrete has emerged as a promising material to mitigate carbon emissions. However, limited availability of published experimental datasets (PED), necessitates predictive models. In this study, PED were collected from Web of Science database. Synthetic datasets (SDs) were generated using a large language model (LLM) based on the descriptive statistics of PED training data. Subsequently, SDs were augmented with PED to investigate their influence on predictive modelling. Baseline models were developed using linear and nonlinear regressors, and extreme gradient boosting (XGBoost) with Optuna-based hyperparameter optimization was adopted for reliability and augmentation analysis. Exploratory data analysis revealed the inability of SDs to capture multivariate structure of PED. For PED-only models, test R² of 0.911 identified XGBoost as the best-performing model. Despite high training and validation scores, reliability models showed average R² performance of 0.513 on PED test set. Additionally, augmented models failed to outperform PED-only models, despite outperforming reliability models. Effect of augmentation size also revealed that small to moderate SD additions outperformed larger SD additions, although evaluation procedure has an effect on ranking. These findings suggests that LLM-generated SDs can be used for preliminary exploration and controlled augmentation, but should not be used in replacing experimental data without rigorous validation.

The cement industry plays a crucial role in global CO2 emissions. As demand for cement continues to rise, innovative solutions are required to mitigate its