INTEGRATING ARTIFICIAL INTELLIGENCE INTO LIFE CYCLE ASSESSMENT IN THE BUILDING INDUSTRY: A BIBLIOMETRIC AND CRITICAL REVIEW

Increasing environmental impacts of buildings necessitate robust sustainability assessment tools, positioning Life Cycle Assessment (LCA) as a central methodology for evaluating environmental performance. Artificial Intelligence (AI) offers strategic potential to enhance the accuracy, efficiency, and automation of LCA processes. This study critically reviews AI-integrated LCA research in the construction sector. A bibliometric analysis of 883 publications from Web of Science and Scopus was conducted, alongside a systematic review of 18 articles explicitly integrating AI into LCA workflows. Findings show Machine Learning (ML) and Artificial Neural Networks (ANN) are predominantly used to predict energy consumption and carbon emissions. However, AI-LCA integration remains fragmented due to unstructured data, lack of standardized protocols, low interoperability, and restricted access to high-quality datasets. Current literature primarily focuses on operational energy use, largely neglecting embodied impacts and broader sustainability indicators. Future research should prioritize AI frameworks incorporating standardized data schemas, real-time monitoring, and case-based validation. Integrating AI into LCA offers transformative potential for data-driven, transparent, and adaptable sustainability strategies in construction.