Abstract
The construction industry is a major contributor to global environmental impacts, particularly through the production and use of cement-based materials. In response to this challenge, this study provides a comprehensive synthesis of recent advances in the integration of Life-Cycle Assessment (LCA) and Artificial Neural Networks (ANNs) for optimizing cementitious composites containing Supplementary Cementitious Materials (SCMs). A total of 14 case studies specifically addressing this topic were identified, reviewed, and analyzed, spanning various binder compositions, ANN architectures, and LCA frameworks. The findings highlight how hybrid ANN-LCA systems can accurately predict mechanical performance while minimizing environmental burdens, supporting the formulation of low-carbon, high-performance cementitious composites. The diverse SCMs explored, including fly ash, slag, silica fume, waste glass powder, and rice husk ash, demonstrate significant potential for reducing CO(2) emissions, energy consumption, and raw material depletion. Furthermore, the systematic comparative matrix developed in this work offers a valuable reference for researchers and practitioners aiming to implement intelligent, eco-efficient mix designs. Overall, this study contributes to advancing digital sustainability tools and reinforces the viability of ANN-LCA integration as a scalable decision-support framework for green construction practices.