A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction

Abstract

Machine learning models are gaining increasing popularity in the domain of fluid dynamics for their potential to accelerate the production of high-fidelity computational fluid dynamics data. However, many recently proposed machine learning models for high-fidelity data reconstruction require low-fidelity data for model training. Such requirement restrains the application performance of these models, since their data reconstruction accuracy would drop significantly if the low-fidelity input data used in model test has a large deviation from the training data. To overcome this restraint, we propose a diffusion model which only uses high-fidelity data at training. With different configurations, our model is able to reconstruct high-fidelity data from either a regular low-fidelity sample or a sparsely measured sample, and is also able to gain an accuracy increase by using physics-informed conditioning information from a known partial differential equation when that is available. Experimental results demonstrate that our model can produce accurate reconstruction results for 2d turbulent flows based on different input sources without retraining.

Cited by in corpus (18)

• Synthetic Lagrangian Turbulence by Generative Diffusion Models
• Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey
• Conditional score-based diffusion models for solving inverse problems in mechanics
• Generative Learning of the Solution of Parametric Partial Differential Equations Using Guided Diffusion Models and Virtual Observations
• Turbulence Scaling from Deep Learning Diffusion Generative Models
• Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Diffusion-Based Surrogate Modeling and Multi-Fidelity Calibration
• Neural Network Complexity of Chaos and Turbulence
• What Artificial Intelligence can do for High-Performance Computing systems?
• Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion Framework
• STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
• Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems
• Physics-informed Shadowgraph Network: An End-to-end Density Field Reconstruction Method
• Predicting the Dynamics of Complex System via Multiscale Diffusion Autoencoder
• Vector Field Synthesis with Sparse Streamlines Using Diffusion Model
• Generative Reconstruction of Spatiotemporal Wall-Pressure in Turbulent Boundary Layers via Patchwise Latent Diffusion
• Flow Gym: A framework for the development, benchmarking, training, and deployment of flow-field quantification methods