Machine learning for prediction with missing dynamics

doi:10.1016/j.jcp.2020.109922

Machine learning for prediction with missing dynamics

2021-03-01

48

OA

AI

DOI：10.1016/j.jcp.2020.109922

Original

Save

View PDF

Abstract

En 中文

This article presents a general framework for recovering missing dynamical systems using available data and machine learning techniques. The proposed framework reformulates the prediction problem as a supervised learning problem to approximate a map that takes the memories of the resolved and identifiable unresolved variables to the missing components in the resolved dynamics. We demonstrate the effectiveness of the proposed framework with a strong convergence error bound of the resolved variables up to finite time and numerical tests on prototypical models in various scientific domains. These include the 57-mode barotropic stress models with multiscale interactions that mimic the blocked and unblocked patterns observed in the atmosphere, the nonlinear Schrodinger equation which found many applications in physics such as optics and Bose-Einstein-Condense, the Kuramoto-Sivashinsky equation which spatiotemporal chaotic pattern formation models trapped-ion modes in plasma and phase dynamics in reaction-diffusion systems. While many machine learning techniques can be used to validate the proposed framework, we found that recurrent neural networks outperform kernel regression methods in terms of recovering the trajectory of the resolved components and the equilibrium one-point and two-point statistics. This superb performance suggests that a recurrent neural network is an effective tool for recovering the missing dynamics that involves approximation of highdimensional functions. (c) 2020 Elsevier Inc. All rights reserved.

Keywords:

Closure Modeling

Missing dynamics

Machine learning

Long Short Term Memory

Machine learning for prediction with missing dynamics

Abstract

AI Summary

Journal

Organization