Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations

TL;DR

This paper introduces physics-informed GANs (PI-GANs) that incorporate physical laws via stochastic differential equations to solve forward, inverse, and mixed stochastic problems efficiently, even in high dimensions.

Contribution

The paper presents a novel class of PI-GANs that embed SDEs into the architecture, enabling unified solutions to stochastic problems with limited data and demonstrating high-dimensional capabilities.

Findings

PI-GANs accurately approximate stochastic processes from sparse data.

Overfitting occurs in both generator and discriminator, affecting training.

PI-GANs effectively solve high-dimensional SDEs up to 30 dimensions.

Abstract

We developed a new class of physics-informed generative adversarial networks (PI-GANs) to solve in a unified manner forward, inverse and mixed stochastic problems based on a limited number of scattered measurements. Unlike standard GANs relying only on data for training, here we encoded into the architecture of GANs the governing physical laws in the form of stochastic differential equations (SDEs) using automatic differentiation. In particular, we applied Wasserstein GANs with gradient penalty (WGAN-GP) for its enhanced stability compared to vanilla GANs. We first tested WGAN-GP in approximating Gaussian processes of different correlation lengths based on data realizations collected from simultaneous reads at sparsely placed sensors. We obtained good approximation of the generated stochastic processes to the target ones even for a mismatch between the input noise dimensionality and the effective dimensionality of the target stochastic processes. We also studied the overfitting issue for both the discriminator and generator, and we found that overfitting occurs also in the generator in addition to the discriminator as previously reported. Subsequently, we considered the solution of elliptic SDEs requiring approximations of three stochastic processes, namely the solution, the forcing, and the diffusion coefficient. We used three generators for the PI-GANs, two of them were feed forward deep neural networks (DNNs) while the other one was the neural network induced by the SDE. Depending on the data, we employed one or multiple feed forward DNNs as the discriminators in PI-GANs. Here, we have demonstrated the accuracy and effectiveness of PI-GANs in solving SDEs for up to 30 dimensions, but in principle, PI-GANs could tackle very high dimensional problems given more sensor data with low-polynomial growth in computational cost.