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

2022/10/28 by Kelshaw, Daniel, Magri, Luca
#FOS: Computer and information sciences #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2210.16215

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.

Related

• Uncovering solutions from data corrupted by systematic errors: A physics-constrained convolutional neural network approach
• Physics-Informed CNNs for Super-Resolution of Sparse Observations on Dynamical Systems
• Super-resolving sparse observations in partial differential equations: A physics-constrained convolutional neural network approach
• Physics-informed deep-learning applications to experimental fluid mechanics
• Super Resolution for Turbulent Flows in 2D: Stabilized Physics Informed Neural Networks