Mohamad Abassi is a postdoctoral researcher at the University of South Florida. He uses deep learning and artificial intelligence to better understanded fluid dynamics, especially in turbulent flows. In this Postdoc Portrait interview, he shares what drew him from practical air experience to computational models.
Applying AI and Machine Learning to Fluid Dynamics
Q | What drew you to fluid dynamics?
I used to be a military pilot in the Tunisian Air Force after I got my bachelor’s degree in aerospace engineering from the French Air Force Academy. With this background, I wanted to deepen my aeronautical and physical knowledge by understanding the complex phenomena that occur around the airplane. With practical air experience, I wanted to use real experimental data in enhancing mathematical models that can make accurate predictions.
Hence, I specialized in computational fluid dynamics (CFD) data assimilation, and I am working on mastering the use of machine learning in fluid dynamics to solve complex CFD problems and to enhance our understanding of fluid dynamics, especially in turbulent flows.
Q | What’s one thing you learned from your research that you didn’t expect?
During my PhD journey, I used to work on making numerical simulations but because one of my tasks consisted of exploiting experimental data, I was asked by my advisor to use a cutting-edge measurement technique: Particle Image Velocimetry. This technique requires hands-on experience in laser and water tunnel operations. That was a surprise to me, but a good one. This way, I have a computational and experimental background.
Q | If your research succeeds, what could it change for science or society?
If my research succeeds, new airplanes will be developed to be more efficient and ecologically friendly.
Responses have been edited for length and clarity.
Are you a researcher who would like to be featured in the “Postdoc Portraits” series? Send in your application here.
