Enforcing imprecise constraints on generative adversarial networks for emulating physical systems
From MaRDI portal
Publication:5163887
Abstract: Generative adversarial networks (GANs) were initially proposed to generate images by learning from a large number of samples. Recently, GANs have been used to emulate complex physical systems such as turbulent flows. However, a critical question must be answered before GANs can be considered trusted emulators for physical systems: do GANs-generated samples conform to the various physical constraints? These include both deterministic constraints (e.g., conservation laws) and statistical constraints (e.g., energy spectrum of turbulent flows). The latter have been studied in a companion paper (Wu et al., Enforcing statistical constraints in generative adversarial networks for modeling chaotic dynamical systems. Journal of Computational Physics. 406, 109209, 2020). In the present work, we enforce deterministic yet imprecise constraints on GANs by incorporating them into the loss function of the generator. We evaluate the performance of physics-constrained GANs on two representative tasks with geometrical constraints (generating points on circles) and differential constraints (generating divergence-free flow velocity fields), respectively. In both cases, the constrained GANs produced samples that conform to the underlying constraints rather accurately, even though the constraints are only enforced up to a specified interval. More importantly, the imposed constraints significantly accelerate the convergence and improve the robustness in the training, indicating that they serve as a physics-based regularization. These improvements are noteworthy, as the convergence and robustness are two well-known obstacles in the training of GANs.
Recommendations
- Enforcing constraints for interpolation and extrapolation in generative adversarial networks
- Learning generative neural networks with physics knowledge
- Some theoretical properties of GANs
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- Physics-informed generative adversarial networks for stochastic differential equations
Cites work
- A comparison study of deep Galerkin method and deep Ritz method for elliptic problems with different boundary conditions
- A consistent dual-mesh framework for hybrid LES/RANS modeling
- Constraint-aware neural networks for Riemann problems
- Deep learning
- Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification
- DGM: a deep learning algorithm for solving partial differential equations
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Enforcing constraints for interpolation and extrapolation in generative adversarial networks
- scientific article; zbMATH DE number 2189140 (Why is no real title available?)
- Inflow turbulence generation methods
- MgNet: a unified framework of multigrid and convolutional neural network
- PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network
- Physics-informed generative adversarial networks for stochastic differential equations
- Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Stochastic seismic waveform inversion using generative adversarial networks as a geological prior
- Turbulent Flows
Cited in
(4)- Solution of physics-based Bayesian inverse problems with deep generative priors
- Learning generative neural networks with physics knowledge
- Enforcing constraints for interpolation and extrapolation in generative adversarial networks
- Physics-guided training of GAN to improve accuracy in airfoil design synthesis
Describes a project that uses
Uses Software
This page was built for publication: Enforcing imprecise constraints on generative adversarial networks for emulating physical systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5163887)
