Physics-Informed Convolutional Neural Networks for Corruption Removal on Dynamical Systems

TL;DR

This paper introduces physics-informed convolutional neural networks designed to effectively remove corruption from data in dynamical systems, enabling accurate physical solutions even with partial and noisy observations.

Contribution

It presents a novel physics-informed CNN framework for stationary corruption removal in dynamical systems, demonstrated on turbulent fluid flow data.

Findings

Robustness to different corruption modalities and magnitudes

Successful extraction of physical solutions from corrupted data

Applicable to complex 2D turbulent flow simulations

Abstract

Measurements on dynamical systems, experimental or otherwise, are often subjected to inaccuracies capable of introducing corruption; removal of which is a problem of fundamental importance in the physical sciences. In this work we propose physics-informed convolutional neural networks for stationary corruption removal, providing the means to extract physical solutions from data, given access to partial ground-truth observations at collocation points. We showcase the methodology for 2D incompressible Navier-Stokes equations in the chaotic-turbulent flow regime, demonstrating robustness to modality and magnitude of corruption.