Physics-Constrained Generative Adversarial Networks for 3D Turbulence
December 01, 2022 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Dima Tretiak, Arvind T. Mohan, Daniel Livescu
arXiv ID
2212.00217
Category
physics.comp-ph
Cross-listed
cs.LG
Citations
2
Venue
arXiv.org
Last Checked
3 months ago
Abstract
Generative Adversarial Networks (GANs) have received wide acclaim among the machine learning (ML) community for their ability to generate realistic 2D images. ML is being applied more often to complex problems beyond those of computer vision. However, current frameworks often serve as black boxes and lack physics embeddings, leading to poor ability in enforcing constraints and unreliable models. In this work, we develop physics embeddings that can be stringently imposed, referred to as hard constraints, in the neural network architecture. We demonstrate their capability for 3D turbulence by embedding them in GANs, particularly to enforce the mass conservation constraint in incompressible fluid turbulence. In doing so, we also explore and contrast the effects of other methods of imposing physics constraints within the GANs framework, especially penalty-based physics constraints popular in literature. By using physics-informed diagnostics and statistics, we evaluate the strengths and weaknesses of our approach and demonstrate its feasibility.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β physics.comp-ph
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
R.I.P.
π»
Ghosted
Heterogeneous Parallelization and Acceleration of Molecular Dynamics Simulations in GROMACS
R.I.P.
π»
Ghosted
By-passing the Kohn-Sham equations with machine learning
R.I.P.
π»
Ghosted
Machine Learning of coarse-grained Molecular Dynamics Force Fields
R.I.P.
π»
Ghosted
Towards Physics-informed Deep Learning for Turbulent Flow Prediction
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted