Journal article icon

Journal article

Data-driven discovery of Green’s functions with human-understandable deep learning

Abstract:
There is an opportunity for deep learning to revolutionize science and technology by revealing its findings in a human interpretable manner. We develop a novel data-driven approach for creating a human-machine partnership to accelerate scientific discovery. By collecting physical system responses, under carefully selected excitations, we train rational neural networks to learn Green's functions of hidden partial differential equation. These solutions reveal human-understandable properties and features, such as linear conservation laws, and symmetries, along with shock and singularity locations, boundary effects, and dominant modes. We illustrate this technique on several examples and capture a range of physics, including advection-diffusion, viscous shocks, and Stokes flow in a lid-driven cavity.
Publication status:
Accepted
Peer review status:
Peer reviewed

Actions


Access Document


Publisher copy:
10.1038/s41598-022-08745-5

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Role:
Author, Author


Publisher:
Springer Nature
Journal:
Scientific Reports More from this journal
Volume:
12
Article number:
4824
Publication date:
2021-03-22
Acceptance date:
2022-03-11
DOI:
EISSN:
2045-2322


Language:
English
Keywords:
Pubs id:
1175266
Local pid:
pubs:1175266
Deposit date:
2022-03-22

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP