Low-dimensional Flow Models from high-dimensional Flow data with Machine Learning and First Principles

Deng Nan (1, 2) , Luc R. Pastur (1) , Bernd R. Noack (3, 4)

1 IMSIA - UMR 9219 - Institut des Sciences de la mécanique et Applications industrielles
2 LISN - Laboratoire Interdisciplinaire des Sciences du Numérique
3 HIT - Harbin Institute of Technology
4 Institut für Strömungsmechanik und Technische Akustik

Reduced-order modelling and system identification can help us figure out the elementary degrees of freedom and the underlying mechanisms from the high-dimensional and nonlinear dynamics of fluid flow. Machine learning has brought new opportunities to these two processes and is revolutionising traditional methods. We show a framework to obtain a sparse humaninterpretable model from complex high-dimensional data using machine learning and first principles.

Domaines: Mécanique des fluides [physics.class-ph]; Science non linéaire [physics]; Dynamique des Fluides [physics.flu-dyn]

Deng Nan, Luc R. Pastur, Bernd R. Noack. Low-dimensional Flow Models from high-dimensional Flow data with Machine Learning and First Principles. ERCIM News 122: Solving Engineering Problems with Machine Learning., 2020. ⟨hal-03195632⟩