Integrating life cycle assessment with GIS and AI for the building sector: a comprehensive review

• Systematic review of GIS and AI integration within building LCA. • Propose an innovative GIS–AI-enhanced LCA framework for the building sector. • Identify key barriers: data heterogeneity, low transferability, poor adaptability. • Reveal shift in LCA toward dynamic, data-driven and spatially explicit approaches. • Offer methodological and practical guidance for GIS–AI–enhanced low-carbon LCA. The building sector plays an important role in global decarbonization efforts, with emerging net-zero policies reshaping life cycle–based carbon reduction strategies. While Life Cycle Assessment (LCA) offers a standardized framework for evaluating environmental impacts, traditional approaches often face data limitations and manual processes. Advances in Geographic Information Systems (GIS) and Artificial Intelligence (AI) now offer data-driven capabilities that make LCA more spatially explicit, automated, and efficient. This review systematically explores the integration of GIS and AI in building LCA by conducting both bibliometric and life cycle–oriented analyses of 153 highly relevant publications and 67 recent case studies. This study summarizes GIS and AI methods in building LCA, explores their application scenarios, and proposes an innovative GIS–AI-enhanced LCA framework for the building sector. Core tasks, GIS–AI synergistic roles, technical barriers, and future directions are clarified across four application quadrants. Results indicate a rapid increase in GIS- and AI-advanced LCA research, with a dominant focus on operational carbon, bottom-up modeling, and analyses at the building and city scales. However, practical implementation remains limited due to three persistent challenges: (1) data heterogeneity and multi-scale integration difficulties, (2) limited model generalizability and spatiotemporal adaptability, and (3) implementation barriers. To address these challenges, we highlight future research priorities including standardized data infrastructures, dynamic and transferable GIS–AI models, and context-aware, life cycle–based optimization strategies. The proposed framework provides a theoretical foundation for advancing GIS–AI-enabled LCA and supporting scalable, adaptive decarbonization strategies in the building sector.