Speaker
Giulio Ortali
(SISSA)
Description
In this work we define a Subgrid Closure model that, employed in a Large Eddy Simulation approach, exhibits correct scaling laws in high order Structure Functions, encompassing intermittent effects and energy cascade dynamics. Due to the massive amount of data needed to reach converged statistics of high order statistical moments, we consider the setting of Shell Models of Turbulence. Our method employs a custom-made Deep Learning architecture comprising a Runge-Kutta integration scheme for the large scales of turbulence, augmented with a Recurrent Artificial Neural Network.
Primary authors
Giulio Ortali
(SISSA)
Dr
Alessandro Corbetta
(Eindhoven University of Technology)
Gianluigi Rozza
(Full professor)
Prof.
Federico Toschi
(Eindhoven University of Technology)
