A Review of Artificial Intelligence in Boiling Heat Transfer: Predictive Modeling, Dynamic Characterization, and Methodological Advances

Boiling heat transfer remains a cornerstone of efficient thermal management, with far-reaching implications for energy systems and industrial processes. Advances in this field not only deepen fundamental scientific understanding but also enable transformative improvements in energy efficiency, equipment performance, and operational safety. Contemporary research in this area focuses on accurate parameter prediction, intelligent image analysis, and quantitative characterization of bubble dynamics, collectively advancing both mechanistic insight and engineering optimization. In this context, artificial intelligence (AI), encompassing machine learning and deep learning techniques, has emerged as a powerful paradigm, offering significant advantages in predictive accuracy, data-driven analysis, and experimental efficiency. This paper provides a systematic review of AI applications in boiling heat transfer research. First, conventional approaches are critically assessed, highlighting the growing relevance and advantages of AI-based methodologies. Next, key machine learning algorithms are introduced and classified according to their roles and capabilities. Subsequently, recent advances in AI-driven prediction of heat transfer parameters, automated analysis of bubble dynamics, and the development of novel research methodologies are comprehensively examined. Finally, current achievements are synthesized, and future research directions are outlined, with particular emphasis on the integration of AI into real-time control and edge-computing frameworks for industrial thermal management.