Physics-Informed Convolutional Neural Networks for Corruption Removal on Dynamical Systems
This addresses a fundamental problem in the physical sciences for researchers dealing with inaccurate measurements, though it appears incremental as it builds on existing physics-informed neural network approaches.
The paper tackled the problem of removing stationary corruption from measurements on dynamical systems, proposing physics-informed convolutional neural networks and demonstrating robustness to corruption modality and magnitude for 2D incompressible Navier-Stokes equations in chaotic-turbulent flow.
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.