Physics-informed neural networks for data-driven simulation: advantages, limitations, and opportunities
File(s)
Accepted version
Author(s)
de la Mata, Felix Fernandez
Gijon, Alfonso
Molina-Solana, Miguel
Gomez-Romero, Juan
Type
Journal Article
Abstract
The last decade has seen a rise in the number and variety of techniques available for data-driven simulation of physical phenomena. One of the most promising approaches is Physics-Informed Neural Networks (PINNs), which can combine both data, obtained from sensors or numerical solvers, and physics knowledge, expressed as partial differential equations. In this work, we investigated the suitability of PINNs to replace current available numerical methods for physics simulations. Although the PINN approach is general and independent of the complexity of the underlying physics equations, a selection of typical heat transfer and fluid dynamics problems was proposed and multiple PINNs were comprehensibly trained and tested to solve them. When PINNs were used as learned simulators, the outcome of our experiments was not entirely satisfactory as not enough accuracy was achieved even though optimal configurations and long training times were used. The main cause for this limitation was found to be the lack of adequate activation functions and specialized architectures, since they proved to have a notable impact on the final accuracy of each model. In turn, PINN architectures showed an accurate behavior when used for parameter inference of partial differential equations from data.
Date Issued
2023-01-15
Date Acceptance
2022-12-01
Citation
Physica A: Statistical Mechanics and its Applications, 2023, 610
ISSN
0378-4371
Publisher
Elsevier
Journal / Book Title
Physica A: Statistical Mechanics and its Applications
Volume
610
Copyright Statement
Copyright © 2022 Elsevier B.V. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Subjects
Data-driven simulations
Deep learning
Learned simulators
Physical Sciences
Physics
Physics, Multidisciplinary
Physics-Informed Neural Networks
Science & Technology
Publication Status
Published
Article Number
128415
Date Publish Online
2022-12-16