Mapping the AI landscape in buildings energy research: Temporal dynamics and global disparities using topic modeling

In increasing global efforts to enhance energy efficiency in buildings, this study employs an innovative topic modeling approach to explore the landscape of artificial intelligence and machine learning applications in building energy use. The study addresses three primary research questions: (1) What are the salient topics in AI applications for building energy use? (2) How have these topics evolved? (3) What are the differences in topics between OECD and non-OECD countries in the application of AI to building energy use? By analyzing a comprehensive dataset of scholarly articles, our findings identify key themes and trends within the field, tracking their progression and transformation over time. The findings reveal a 29 % annual growth in research, with predictive modeling, building optimization, and smart energy management emerging as the most prevalent AI-driven applications. While OECD countries focus on automation and sensor-based energy management, non-OECD nations emphasize retrofitting and urban sustainability as primary strategies for efficiency gains. These differences reflect global disparities in technological adoption and policy priorities. This study advances the understanding of the dynamic landscape of AI applications in building energy management and rationalization, identifying gaps and opportunities for future research and policy development to bridge regional divides and enhance global energy efficiency strategies.