Physics-informed neural networks for high-speed flows

Zhiping Mao; Ameya D. Jagtap; George Em Karniadakis

doi:10.1016/j.cma.2019.112789

Keywords

Euler equationsConservation lawRiemann problemAerodynamicsInverse problemPosition (finance)Artificial neural networkMathematical analysisEuler's formulaApplied mathematicsPhysicsRiemann hypothesisMathematicsComputer scienceMechanicsArtificial intelligence

Affiliated Institutions

Brown University US

Related Publications

Turbulence Approximation for Inhomogeneous Flows: Part I. The Clipping Approximation

J. C. André , G. De Moor , P. Lacarrère +1 more

A modification of the quasi-normal theory is proposed for the study of inhomogeneous turbulent flows. In this approximation realizability conditions for third-order correlations...

1976 Journal of the Atmospheric Sciences 73 citations

Application of the Piecewise Parabolic Method (PPM) to Meteorological Modeling

Richard L. Carpenter , Kelvin K. Droegemeier , Paul R. Woodward +1 more

The Piecewise Parabolic Method (PPM), a numerical technique developed in astrophysics for modeling fluid flows with strong shocks and discontinuities is adapted for treating sha...

1990 Monthly Weather Review 193 citations

Modern Compressible Flow: With Historical Perspective

John Anderson

1 Compressible Flow - Some History and Introductory Thoughts 2 Integral Forms of the Conservation Equations for Inviscid Flows 3 One-Dimensional Flow 4 Oblique Shock and Expansi...

2020 1595 citations

Study of rarefied shear flow by the discrete velocity method

James E. Broadwell

The application of a simple discrete velocity model to low Mach number Couette and Rayleigh flow is investigated. In the model, the molecular velocities are restricted to a fini...

1964 Journal of Fluid Mechanics 276 citations

Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations

Maziar Raissi , Alireza Yazdani , George Em Karniadakis

Machine-learning fluid flow Quantifying fluid flow is relevant to disciplines ranging from geophysics to medicine. Flow can be experimentally visualized using, for example, smok...

2020 Science 1697 citations

Publication Info

Year: 2019
Type: article
Volume: 360
Pages: 112789-112789
Citations: 1041
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Physics-informed neural networks for high-speed flows

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1041

OpenAlex

Cite This

APA Style

                            
                                    Zhiping Mao, 
                                
                                    Ameya D. Jagtap, 
                                
                                    George Em Karniadakis
                                
                            (2019). 
                            Physics-informed neural networks for high-speed flows. 
                            Computer Methods in Applied Mechanics and Engineering
                            , 360
                            
                            , 112789-112789.
                            https://doi.org/10.1016/j.cma.2019.112789

Identifiers

DOI: 10.1016/j.cma.2019.112789