Traditionally, the underlying physics of fluid mechanics has been explored by theoretical and computational methods along with experimental measurements. Recently, there has been a resurgence of data-driven and machine learning methods to provide a fourth pillar as a unifying force towards improved understanding and controlling of fluid flow. The focus of this special issue is on the symbiosis of traditional modeling with the data-driven methods for solving fluid problems, e.g., integration of AI/ML techniques with computational and experimental fluid dynamics. The contributions below include recent advances in data-driven techniques for fluid mechanics, and showcase the application of these methods in applied science and engineering.
Topics covered include, but are not limited to:
- Computational and experimental fluid dynamics
- Artificial intelligence
- Machine learning
- Data-driven techniques for fluid mechanics
Rajeev K. Jaiman (University of British Columbia)
Weiwei Zhang (Northwestern Polytechnical University)
Dixia Fan (Queen’s University)
For those interested in submitting, please take note of the following instructions:
- Navigate to the journal’s online submission system. You may need to create an account if you do not already have one.
- During the submission process you will be asked if your manuscript is part of a special topic. Please answer “yes” and select “Artificial Intelligence in Fluid Mechanics” from the subsequent drop-down menu.
Papers that are accepted for publication will publish immediately upon acceptance and will appear online in a virtual collection dedicated to this special topic. Any questions or concerns about the submission process or deadline should be directed to the Physics of Fluids journal manager at firstname.lastname@example.org.