6 papers
Control of chaotic systems by Deep Reinforcement Learning
Michele Alessandro Bucci, Onofrio Semeraro, Alexandre Allauzen +3
Deep Reinforcement Learning (DRL) is applied to control a nonlinear, chaotic system governed by the one-dimensional Kuramoto-Sivashinsky (KS) equation. DRL uses reinforcement learn…
Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
N. Benjamin Erichson, Lionel Mathelin, Zhewei Yao +3
In many applications, it is important to reconstruct a fluid flow field, or some other high-dimensional state, from limited measurements and limited data. In this work, we propose…
Spatio-temporal Proper Orthogonal Decomposition of turbulent channel flow
Srikanth Derebail Muralidhar, Bérengère Podvin, Lionel Mathelin +1
An extension of Proper Orthogonal Decomposition is applied to the wall layer of a turbulent channel flow (Re τ = 590), so that empirical eigenfunctions are defined in both space an…
Diffusion Maps meet Nyström
N. Benjamin Erichson, Lionel Mathelin, Steven L. Brunton +1
Diffusion maps are an emerging data-driven technique for non-linear dimensionality reduction, which are especially useful for the analysis of coherent structures and nonlinear embe…
Observable dictionary learning for high-dimensional statistical inference
Lionel Mathelin, Kévin Kasper, Hisham Abou-Kandil
This paper introduces a method for efficiently inferring a high-dimensional distributed quantity from a few observations. The quantity of interest (QoI) is approximated in a basis…
A statistical learning strategy for closed-loop control of fluid flows
Florimond Guéniat, Lionel Mathelin, M. Yousuff Hussaini
This work discusses a closed-loop control strategy for complex systems utilizing scarce and streaming data. A discrete embedding space is first built using hash functions applied t…