NeuralPDE: Automating Physics-Informed Neural Networks (PINNs) with Error Approximations
arXiv:2107.09443
Abstract
Physics-informed neural networks (PINNs) are an increasingly powerful way to solve partial differential equations, generate digital twins, and create neural surrogates of physical models. In this manuscript we detail the inner workings of NeuralPDE.jl and show how a formulation structured around numerical quadrature gives rise to new loss functions which allow for adaptivity towards bounded error tolerances. We describe the various ways one can use the tool, detailing mathematical techniques like using extended loss functions for parameter estimation and operator discovery, to help potential users adopt these PINN-based techniques into their workflow. We showcase how NeuralPDE uses a purely symbolic formulation so that all of the underlying training code is generated from an abstract formulation, and show how to make use of GPUs and solve systems of PDEs. Afterwards we give a detailed performance analysis which showcases the trade-off between training techniques on a large set of PDEs. We end by focusing on a complex multiphysics example, the Doyle-Fuller-Newman (DFN) Model, and showcase how this PDE can be formulated and solved with NeuralPDE. Together this manuscript is meant to be a detailed and approachable technical report to help potential users of the technique quickly get a sense of the real-world performance trade-offs and use cases of the PINN techniques.
74 pages, 20+ figures, 20+ tables
References in corpus (5)
- Solving high-dimensional partial differential equations using deep learning
- Cuba - a library for multidimensional numerical integration
- Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
- Understanding and mitigating gradient pathologies in physics-informed neural networks
- A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
Cited by in corpus (3)
- Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
- Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)
- Adjoint-based Particle Forcing Reconstruction and Uncertainty Quantification