Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
Authors:
Preprint
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 (CNN), 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. Several flow SR problems relevant to cardiovascular applications have been studied to demonstrate the proposed method's effectiveness and merit. Both Gaussian and non-Gaussian MRI noises are investigated to illustrate the denoising capability.Keywords
All Related Versions
This publication has 54 references indexed in Scilit:
- Physics-informed multi-LSTM networks for metamodeling of nonlinear structuresComputer Methods in Applied Mechanics and Engineering, 2020
- Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation dataComputer Methods in Applied Mechanics and Engineering, 2020
- Fusing wind-tunnel measurements and CFD data using constrained gappy proper orthogonal decompositionAerospace Science and Technology, 2019
- Prediction of Reynolds stresses in high-Mach-number turbulent boundary layers using physics-informed machine learningTheoretical and Computational Fluid Dynamics, 2018
- Denoising and spatial resolution enhancement of 4D flow MRI using proper orthogonal decomposition and lasso regularizationComputerized Medical Imaging and Graphics, 2018
- Data assimilation of mean velocity from 2D PIV measurements of flow over an idealized airfoilExperiments in Fluids, 2017
- Spatial resolution and velocity field improvement of 4D‐flow MRIMagnetic Resonance in Medicine, 2016
- Aerodynamic database reconstruction via gappy high order singular value decompositionAerospace Science and Technology, 2016
- Robust 4D flow denoising using divergence‐free wavelet transformMagnetic Resonance in Medicine, 2014
- Improved SNR in phase contrast velocimetry with five‐point balanced flow encodingMagnetic Resonance in Medicine, 2010