Computational fluid dynamics (CFD) integrated with machine learning (ML) is an emerging and rapidly growing research field. ML's ability to process data and extract patterns enables the extraction of valuable insights from large, fluid datasets. Compared to traditional CFD, ML-enhanced CFD not only significantly reduces simulation costs and improves efficiency but also enhances generalization capabilities, enabling the solution of complex fluid dynamics problems, such as nonlinear and high-dimensional issues. This paper offers a comprehensive overview of ML advancements in theoretical modeling, numerical computation, and experimental validation, structured around the three main areas of CFD research. It also highlights recent fusion applications and algorithms used for training over the past 5 years. Additionally, the future prospects of ML-enabled CFD are explored, along with potential challenges that may arise during its development.
Hu et al. (Fri,) studied this question.