CFD IMPACT Conference 2019
We are pleased to announce that the CFD IMPACT 2019 Conference will be held on Monday, July 1, 2019 in the Dan Kahn Auditorium at the Technion. In this year’s conference we hope to repeat and build on last year’s successful conference, and highlight, among other topics, machine learning, high-order numerical methods, and advanced turbulence modeling. This year's Keynote Speaker will be Prof. George Karniadakis, Division of Applied Mathematics, Brown University & Department of Mechanical Engineering, MIT whose talk will be entitled "Physics-Informed Learning Machines for Physical Systems".
Conference topics include High-fidelity numerical methods in CFD, High-performance computing in CFD, High Reynolds number turbulence in CFD, High-complexity in CFD, Industrial applications of CFD.
Professor George Karniadikis
Division of Applied Mathematics
Brown University & Department of Mechanical Engineering, MIT
Karniadikis received his S.M and Ph.D. from Massachusetts Institute of Technology. He was appointed Lecturer in the Department of Mechanical Engineering at MIT in 1987 and subsequently he joined the Center for Turbulence Research at Stanford / Nasa Ames. He joined Princeton University as Assistant professor in the Department of Mechanical and Aerospace Engineering and as Associate Faculty in the Program of Applied and Computational Mathematics. He was a visiting Professor at Caltech in 1993 in the Aeronautics Department and joined Brown University as Associate Professor of Applied Mathematics in the Center for Fluid Mechanics in 1994. After becoming a full professor in 1996, he continues to be a Visiting Professor and Senior Lecturer of Ocean/Mechanical Engineering at MIT. He is a Fellow of the Society for Industrial and Applied Mathematics (SIAM, 2010-), Fellow of the American Physical Society (APS, 2004-), Fellow of the American Society of MechanicalEngineers (ASME, 2003-), and Associate Fellow of the American Institute of Aeronautics and Astronautics (AIAA, 2006-). He received Alexander von Humboldt award in 2017, the Ralf E Kleinman award from SIAM (2015), the J. Tinsley Oden Medal (2013), and the CFD award (2007) by the US Association in Computational Mechanics. His h-index is 87 and has been cited over 38,000 times.
Physics-Informed Learning Machines for Physical Systems
In this talk, we will present a new approach to develop a data-driven, learning-based framework for predicting outcomes of physical systems and for discovering hidden physics from noisy data.
A key concept is the seamless fusion and integration of data of variable fidelity into the predictive models. First we will present a Bayesian approach on neural networks (NNs). Unlike other approaches that rely on big data, here we "learn" from small data by exploiting the information provided by the physical conservation laws, which are used to obtain informative priors or regularize the neural networks. We will also make connections between DPR and NNs and discuss the new powerful concept of meta-learning.
This works is supported by the DARPA EQUiPS program on Uncertainty Quantification and AFOSR.