$PINN - a Domain Decomposition Method for Bayesian Physics-Informed Neural Networks

Júlia Vicens-Figueres, Juliette Vanderhaeghen, Federica Bragone, Kateryna Morozovska, Khemraj Shukla

Keywords: physics-informed neural networks, uncertainty quantification, Bayesian Inference, Domain Decomposition, Partial Differential Equations

TL;DR: $PINN is a model that combines a Bayesian PINN with domain decomposition to improve the robustness of uncertainty quantification while enhancing scalability.

Abstract: Physics-Informed Neural Networks (PINNs) are a novel computational approach for solving partial differential equations (PDEs) with noisy and sparse initial and boundary data. Although, efficient quantification of epistemic and aleatoric uncertainties in big multi-scale problems remains challenging. We propose \$ PINN a novel method of computing global uncertainty in PDEs using a Bayesian framework, by combining local Bayesian Physics-Informed Neural Networks (BPINN) with domain decomposition. The solution continuity across subdomains is obtained by imposing the flux continuity across the interface of neighboring subdomains. To demonstrate the effectiveness of $PINN, we conduct a series of computational experiments on PDEs in 1D and 2D spatial domains. Although we have adopted conservative PINNs (cPINNs), the method can be seamlessly extended to other domain decomposition techniques. The results infer that the proposed method recovers the global uncertainty by computing the local uncertainty exactly more efficiently as the uncertainty in each subdomain can be computed concurrently. The robustness of $PINN is verified by adding uncorrelated random noise to the training data up to 15% and testing for different domain sizes.

Journal Opt In: Yes, I want to participate in the IOP focus collection submission

Journal Corresponding Email: [e-mail]

Journal Notes: We have an extended version of the paper.

Submission Number: 147