Towards Physics-informed Deep Learning for Turbulent Flow Prediction

Wang, Rui; Kashinath, Karthik; Mustafa, Mustafa; Albert, Adrian; Yu, Rose

doi:10.1145/3394486.3403198

Cited by 180 publications

(113 citation statements)

References 13 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…While potentially more accurate than traditional turbulence models, these new models have not achieved reduced computational expense. Another major thrust uses "pure" ML, aiming to replace the entire Navier-Stokes simulation with approximations based on deep neural networks (25)(26)(27)(28)(29)(30). A pure ML approach can be extremely efficient, avoiding the severe time-step constraints required for stability with traditional approaches.…”

Section: Forced Turbulencementioning

confidence: 99%

Machine learning–accelerated computational fluid dynamics

Kochkov

Smith

Alieva

et al. 2021

Proc. Natl. Acad. Sci. U.S.A.

447

229

View full text Add to dashboard Cite

Numerical simulation of fluids plays an essential role in modeling many physical phenomena, such as weather, climate, aerodynamics, and plasma physics. Fluids are well described by the Navier–Stokes equations, but solving these equations at scale remains daunting, limited by the computational cost of resolving the smallest spatiotemporal features. This leads to unfavorable trade-offs between accuracy and tractability. Here we use end-to-end deep learning to improve approximations inside computational fluid dynamics for modeling two-dimensional turbulent flows. For both direct numerical simulation of turbulence and large-eddy simulation, our results are as accurate as baseline solvers with 8 to 10× finer resolution in each spatial dimension, resulting in 40- to 80-fold computational speedups. Our method remains stable during long simulations and generalizes to forcing functions and Reynolds numbers outside of the flows where it is trained, in contrast to black-box machine-learning approaches. Our approach exemplifies how scientific computing can leverage machine learning and hardware accelerators to improve simulations without sacrificing accuracy or generalization.

show abstract

Section: Forced Turbulencementioning

confidence: 99%

Machine learning–accelerated computational fluid dynamics

Kochkov

Smith

Alieva

et al. 2021

Proc. Natl. Acad. Sci. U.S.A.

447

229

View full text Add to dashboard Cite

show abstract

“…The hybrid RANS-LES coupling approach combines the computational efficiency of RANS with the more accurate resolving power of LES to provide a technique that is less expensive and more tractable than pure LES [124]. Here, we review TurbulentFlowNet (TFNet), proposed by Wang et al [105], which applies scale separation and builds upon the structure of existing turbulence models.…”

Section: Physics-informed Machine Learning: Case Studies In Emulation Downscaling and Forecastingmentioning

confidence: 99%

Physics-informed machine learning: case studies for weather and climate modelling

Kashinath

Mustafa

Albert

et al. 2021

Phil. Trans. R. Soc. A.

231

132

View full text Add to dashboard Cite

Machine learning (ML) provides novel and powerful ways of accurately and efficiently recognizing complex patterns, emulating nonlinear dynamics, and predicting the spatio-temporal evolution of weather and climate processes. Off-the-shelf ML models, however, do not necessarily obey the fundamental governing laws of physical systems, nor do they generalize well to scenarios on which they have not been trained. We survey systematic approaches to incorporating physics and domain knowledge into ML models and distill these approaches into broad categories. Through 10 case studies, we show how these approaches have been used successfully for emulating, downscaling, and forecasting weather and climate processes. The accomplishments of these studies include greater physical consistency, reduced training time, improved data efficiency, and better generalization. Finally, we synthesize the lessons learned and identify scientific, diagnostic, computational, and resource challenges for developing truly robust and reliable physics-informed ML models for weather and climate processes. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

show abstract

“…In the area of fluid dynamics, for turbulent flow predictions, Wang et al [33] developed a physics-informed deep learning framework. They introduced the use of trainable spectral filters coupled with Reynolds-averaged Navier-Stokes (RANS) and Large Eddy Simulation (LES) models followed by a convolutional architecture in order to predict turbulent flows.…”

Section: Related Workmentioning

confidence: 99%

MESHFREEFLOWNET: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

Jiang

Esmaeilzadeh

Azizzadenesheli

et al. 2020

SC20: International Conference for High Performance Computing, Networking, Storage and Analysis

Self Cite

View full text Add to dashboard Cite

We propose MeshfreeFlowNet, a novel deep learningbased super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs. While being computationally efficient, Mesh-freeFlowNet accurately recovers the fine-scale quantities of interest. MeshfreeFlowNet allows for: (i) the output to be sampled at all spatio-temporal resolutions, (ii) a set of Partial Differential Equation (PDE) constraints to be imposed, and (iii) training on fixed-size inputs on arbitrarily sized spatio-temporal domains owing to its fully convolutional encoder.We empirically study the performance of Mesh-freeFlowNet on the task of super-resolution of turbulent flows in the Rayleigh-Bénard convection problem. Across a diverse set of evaluation metrics, we show that Mesh-freeFlowNet significantly outperforms existing baselines. Furthermore, we provide a large scale implementation of MeshfreeFlowNet and show that it efficiently scales across large clusters, achieving 96.80% scaling efficiency on up to 128 GPUs and a training time of less than 4 minutes.We provide an open-source implementation of our method that supports arbitrary combinations of PDE constraints 1 . * Denotes equal contribution.

show abstract

Towards Physics-informed Deep Learning for Turbulent Flow Prediction

Cited by 180 publications

References 13 publications

Machine learning–accelerated computational fluid dynamics

Machine learning–accelerated computational fluid dynamics

Physics-informed machine learning: case studies for weather and climate modelling

MESHFREEFLOWNET: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

Contact Info

Product

Resources

About