On May 19th, TUM-IAS Hans Fischer Fellow Dr. Luca Magri, Imperial College London, Aeronautics Department will give a talk on
"Physics-aware machine learning to predict unpredictable fluids“.
Date: May 19, 2021
Time: 13:00 (until approx.14:00)
Registration: Due to the ongoing pandemic, the TUM-IAS Wednesday Coffee talks are currently held online. To register please send an email to email@example.com.
The ability of fluid mechanics modelling to predict the evolution of a flow is enabled by physical principles and empirical approaches. Physical principles, for example conservation laws, are extrapolative (until the assumptions upon which they hinge break down): they provide predictions on phenomena that have not been observed. Human beings are excellent at extrapolating knowledge because we are excellent at finding physical principles. Empirical modelling provides correlation functions within data. Artificial intelligence and machine learning are excellent at empirical modelling.
In this talk, the complementary capabilities of both approaches will be exploited to achieve adaptive modelling and optimization of nonlinear, unsteady and uncertain flows. The focus of the talk is on computational methodologies for modelling and optimization: (i) data assimilation with a Bayesian approach, (ii) reservoir computing with Bayesian optimization and (iii) auto-encoders (time permitting). The physics is embedded as soft and hard constraints. The flows under investigation are relevant to aerospace propulsion, with a focus on thermoacoustics, and turbulence, with a focus on the Kolmogorov flow.
THE TUM-IAS WEDNESDAY COFFEE TALKS
Due to the ongoing pandemic, the TUM-IAS Wednesday Coffee talks are currently held online. Would you like to receive regular updates on the TUM-IAS Wednesday Coffee Talk and the Zoom link?
Just send a short note to firstname.lastname@example.org!
An overview on upcoming and past TUM-IAS Wednesday Coffee Talks can be found at the TUM-IAS Wednesday Coffee Talk Overview.