State estimation in minimal turbulent channel flow: A comparative study of 4DVar and PINN

Du, Yifan; Wang, Mengze; Zaki, Tamer A.

doi:10.1016/j.ijheatfluidflow.2022.109073

Cited by 24 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While unsupervised learning used for GANs and semisupervised learning assisted with physics-inspired loss functions introduced in the present survey can mitigate this issue, existing techniques still require learning the relationship between coarse data and high-resolution vortical flows from either unpaired or paired training data for successful reconstruction. Since the majority of real-world problems do not have access to ground truth and only sparse and noisy measurements are available, one can consider the use of data assimilation [177][178][179] to improve super-resolution reconstruction by incorporating the latest observations with a short-range real-time forecast.…”

Section: Applications To Real-world Problemsmentioning

confidence: 99%

Super-resolution analysis via machine learning: a survey for fluid flows

Fukami

Fukagata

Taira

2023

Theor. Comput. Fluid Dyn.

View full text Add to dashboard Cite

This paper surveys machine-learning-based super-resolution reconstruction for vortical flows. Super resolution aims to find the high-resolution flow fields from low-resolution data and is generally an approach used in image reconstruction. In addition to surveying a variety of recent super-resolution applications, we provide case studies of super-resolution analysis for an example of two-dimensional decaying isotropic turbulence. We demonstrate that physics-inspired model designs enable successful reconstruction of vortical flows from spatially limited measurements. We also discuss the challenges and outlooks of machine-learning-based super-resolution analysis for fluid flow applications. The insights gained from this study can be leveraged for super-resolution analysis of numerical and experimental flow data. Graphical abstract

show abstract

Section: Applications To Real-world Problemsmentioning

confidence: 99%

Super-resolution analysis via machine learning: a survey for fluid flows

Fukami

Fukagata

Taira

2023

Theor. Comput. Fluid Dyn.

View full text Add to dashboard Cite

show abstract

“…The most important benefit of using PINNs is their flexibility. PINNs can deal with any boundary condition or no boundary condition, they do not need to deal with the complex grid designs required to incorporate the kinematics of the immersed body, they are less sensitive to the spatio-temporal resolution and noise, and they can patch the results in regions where velocity field data are not available ( Cai et al, 2021 ; Jin et al, 2021 ; Di Leoni et al, 2022 preprint; Molnar and Grauer, 2022 ; Du et al, 2023 ; Molnar et al, 2023 ; Zhou et al, 2023 ).…”

Section: Introductionmentioning

confidence: 99%

Reconstructing the pressure field around swimming fish using a physics-informed neural network

Calicchia

Mittal

Seo

et al. 2023

Journal of Experimental Biology

View full text Add to dashboard Cite

Fish detect predators, flow conditions, environments, and each other through pressure signals. Lateral line ablation is often performed to understand the role of pressure sensing. In this study, the authors propose a non-invasive method for reconstructing the instantaneous pressure field sensed by a fish's lateral line system from 2D particle image velocimetry (PIV) measurements. The method uses a physics-informed neural network (PINN) to predict an optimized solution for the pressure field near and on the fish's body that satisfy both the Navier-Stokes equations and the constraints put forward by the PIV measurements. The method was validated using a direct numerical simulation of a swimming mackerel, Scomber scombrus, and was applied to experimental data of a turning zebrafish, Danio rerio. The results demonstrate that this method is relatively insensitive to the spatio-temporal resolution of the PIV measurements and accurately reconstructs the pressure on the fish's body.

show abstract

“…Eivazi and Vinuesa [30] used PINNs to reconstruct turbulent flows from noisy datasets. Du et al [31] also compared PINNs with four-dimensional adjoint-variational data assimilation in reconstructing turbulent channel flows from sparse data. Linqi et al [32] then used PINNs in an enhanced super-resolution GAN to reconstruct turbulent channel flows from sparse data generated from upsampling via tri-linear interpolation.…”

Section: Introductionmentioning

confidence: 99%

Physics-Informed Super-Resolution of Turbulent Channel Flows via Three-Dimensional Generative Adversarial Networks

Ward

2023

Fluids

View full text Add to dashboard Cite

For a few decades, machine learning has been extensively utilized for turbulence research. The goal of this work is to investigate the reconstruction of turbulence from minimal or lower-resolution datasets as inputs using reduced-order models. This work seeks to effectively reconstruct high-resolution 3D turbulent flow fields using unsupervised physics-informed deep learning. The first objective of this study is to reconstruct turbulent channel flow fields and verify these with respect to the statistics. The second objective is to compare the turbulent flow structures generated from a GAN with a DNS. The proposed deep learning algorithm effectively replicated the first- and second-order statistics of turbulent channel flows of Reτ= 180 within a 2% and 5% error, respectively. Additionally, by incorporating physics-based corrections to the loss functions, the proposed algorithm was also able to reconstruct λ2 structures. The results suggest that the proposed algorithm can be useful for reconstructing a range of 3D turbulent flows given computational and experimental efforts.

show abstract

State estimation in minimal turbulent channel flow: A comparative study of 4DVar and PINN

Cited by 24 publications

References 41 publications

Super-resolution analysis via machine learning: a survey for fluid flows

Super-resolution analysis via machine learning: a survey for fluid flows

Reconstructing the pressure field around swimming fish using a physics-informed neural network

Physics-Informed Super-Resolution of Turbulent Channel Flows via Three-Dimensional Generative Adversarial Networks

Contact Info

Product

Resources

About