A-PINN: Auxiliary physics informed neural networks for forward and inverse problems of nonlinear integro-differential equations

A-PINN: Вспомогательные физически информированные нейронные сети для прямых и обратных задач нелинейных интегро-дифференциальных уравнений
Yi‐Qing Ni, Lei Yuan, Xiangyun Deng, Shuo Hao
2022-04-29

automatic differentiationauxiliary physics-informed neural networksforward and inverse problemsnonlinear Volterra equationsnonlinear integro-differential equations
Physics informed neural networks (PINNs) are a novel deep learning paradigm primed for solving forward and inverse problems of nonlinear partial differential equations (PDEs). By embedding physical information delineated by PDEs in feedforward neural networks, PINNs are trained as surrogate models for approximate solution to the PDEs without need of label data. Due to the excellent capability of neural networks in describing complex relationships, a variety of PINN-based methods have bene developed to solve different kinds of problems such as integer-order PDEs, fractional PDEs, stochastic PDEs and integro-differential equations (IDEs). However, for the state-of-the-art PINN methods in application to IDEs, integral discretization is a key prerequisite in order that IDEs can be transformed into ordinary differential equations (ODEs). However, integral discretization inevitably introduces discretization error and truncation error to the solution. In this study, we propose an auxiliary physics informed neural network (A-PINN) framework for solving forward and inverse problems of nonlinear IDEs. By defining auxiliary output variable(s) to represent the integral(s) in the governing equation and employing automatic differentiation of the auxiliary output to replace integral operator, the proposed A-PINN bypasses the limitation of integral discretization. Distinct from the neural network in the original PINN which only approximates the variables in the governing equation, in the proposed A-PINN framework, a multi-output neural network is constructed to simultaneously calculate the primary outputs and auxiliary outputs which respectively approximate the variables and integrals in the governing equation. Subsequently, the relationship between the primary outputs and auxiliary outputs is constrained by new output conditions in compliance with physical laws. By pursuing the first-order nonlinear Volterra IDE benchmark problem, we validate that the proposed A-PINN can obtain more accurate solution than the conventional PINN. We further demonstrate the good performance of A-PINN in solving the forward problems involving nonlinear Volterra IDE systems, nonlinear 2-dimensional Volterra IDE, and nonlinear Fredholm IDE. Finally, the A-PINN framework is implemented to solve the inverse problem of nonlinear IDEs and the results show that the unknown parameters can be satisfactorily discovered even with heavily noisy data.
1
A multi-output network simultaneously approximates the governing variables and integrals, while additional physics-based output conditions enforce their mathematical relationship.
2
A-PINN represents integrals with auxiliary neural-network outputs and uses automatic differentiation to replace integral operators, avoiding integral discretization.
3
The method eliminates discretization and truncation errors introduced when conventional PINN approaches transform integro-differential equations into ordinary differential equations.
4
The paper introduces A-PINN, an auxiliary physics-informed neural network framework for forward and inverse nonlinear integro-differential equations.
5
Validation on a first-order nonlinear Volterra integro-differential benchmark demonstrates the applicability of A-PINN, although the provided abstract does not report quantitative results.

nonlinear integro-differential equations (IDEs), including their forward and inverse problem formulations

the accuracy and discretization-free solution of forward and inverse IDE problems using auxiliary-output physics-informed neural networks

Publication Details
Publication Date
2022-04-29
Journal
Publisher
ISSN
Cited by
445
Access Type
Author Information
Authors
Yi‐Qing Ni
Lei Yuan
Xiangyun Deng
Shuo Hao
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%