Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
Authors:
Top Cited Papers
- 1 July 2021
- journal article
- conference paper
- Published by AIP Publishing in Physics of Fluids
- Vol. 33 (7) , 073603
Abstract
High-resolution (HR) information of fluid flows, although preferable, is usually less accessible due to limited computational or experimental resources. In many cases, fluid data are generally sparse, incomplete, and possibly noisy. How to enhance spatial resolution and decrease the noise level of flow data is essential and practically useful. Deep learning (DL) techniques have been demonstrated to be effective for super-resolution (SR) tasks, which, however, primarily rely on sufficient HR labels for training. In this work, we present a novel physics-informed DL-based SR solution using convolutional neural networks (CNNs), which is able to produce HR flow fields from low-resolution (LR) inputs in high-dimensional parameter space. By leveraging the conservation laws and boundary conditions of fluid flows, the CNN-SR model is trained without any HR labels. Moreover, the proposed CNN-SR solution unifies the forward SR and inverse data assimilation for the scenarios where the physics is partially known, e.g., unknown boundary conditions. A new network structure is designed to enable not only the parametric SR but also the parametric inference for the first time. Several flow SR problems relevant to cardiovascular applications have been studied to demonstrate the proposed method's effectiveness and merit. A series of different LR scenarios, including LR input with Gaussian noises, non-Gaussian magnetic resonance imaging noises, and downsampled measurements given either well-posed or ill-posed physics, are investigated to illustrate the SR, denoising, and inference capabilities of the proposed method.Keywords
All Related Versions
Funding Information
- National Science Foundation (CMMI-1934300)
This publication has 51 references indexed in Scilit:
- Aerodynamic database reconstruction via gappy high order singular value decompositionAerospace Science and Technology, 2016
- A data-assimilation method for Reynolds-averaged Navier–Stokes-driven mean flow reconstructionJournal of Fluid Mechanics, 2014
- Robust 4D flow denoising using divergence‐free wavelet transformMagnetic Resonance in Medicine, 2014
- On dynamic mode decomposition: Theory and applicationsJournal of Computational Dynamics, 2014
- Dynamic mode decomposition of numerical and experimental dataJournal of Fluid Mechanics, 2010
- Improved SNR in phase contrast velocimetry with five‐point balanced flow encodingMagnetic Resonance in Medicine, 2010
- Bayesian inverse problems for functions and applications to fluid mechanicsInverse Problems, 2009
- A Reconstruction Method for the Flow Past an Open CavityJournal of Fluids Engineering, 2005
- Gappy data and reconstruction procedures for flow past a cylinderJournal of Fluid Mechanics, 2004
- Numerical study of the turbulent flow past an airfoil with trailing edge separationAIAA Journal, 1983