Monte Carlo PINNs: deep learning approach for forward and inverse problems involving high dimensional fractional partial differential equations

TL;DR

This paper presents Monte Carlo PINNs, a novel deep learning method that efficiently solves high-dimensional fractional PDEs by combining neural network surrogates with stochastic fractional derivative approximations.

Contribution

It introduces MC-PINNs, a sampling-based extension of PINNs, which reduces computational cost and enables solving high-dimensional fractional PDEs more effectively.

Findings

MC-PINNs outperform existing methods in high-dimensional fractional PDEs

The approach effectively handles parametric and random inputs in fractional PDEs

Numerical examples demonstrate the method's flexibility and efficiency

Abstract

We introduce a sampling based machine learning approach, Monte Carlo physics informed neural networks (MC-PINNs), for solving forward and inverse fractional partial differential equations (FPDEs). As a generalization of physics informed neural networks (PINNs), our method relies on deep neural network surrogates in addition to a stochastic approximation strategy for computing the fractional derivatives of the DNN outputs. A key ingredient in our MC-PINNs is to construct an unbiased estimation of the physical soft constraints in the loss function. Our directly sampling approach can yield less overall computational cost compared to fPINNs proposed in \cite{pang2019fpinns} and thus provide an opportunity for solving high dimensional fractional PDEs. We validate the performance of MC-PINNs method via several examples that include high dimensional integral fractional Laplacian equations, parametric identification of time-space fractional PDEs, and fractional diffusion equation with random inputs. The results show that MC-PINNs is flexible and promising to tackle high-dimensional FPDEs.