Learning closure relations using differentiable programming: An example in radiation transport
Journal of Quantitative Spectroscopy and Radiative Transfer · 2024-05 · 318 · 108941
DOI: 10.1016/j.jqsrt.2024.108941 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Quantitative Spectroscopy and Radiative Transfer, 2024-05. Verfasst von A.J. Crilly und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The continuous flow or ‘transport’ of a macroscopic system of particles is a high dimensional problem and therefore often solved using reduced order models. This necessarily introduces unknown closure relations into these models. In this work, we present a machine learning approach to finding accurate closure relations utilising differentiable programming. As a case study, we consider the transport of photons and use a literature radiation transport test problem as a training dataset. We present novel ML closures for a number of reduced order models which out-perform their literature counterparts in both trained and unseen problems.
Zitieren
APA
Crilly, A., Duhig, B., & Bouziani, N. (2024). Learning closure relations using differentiable programming: An example in radiation transport. Journal of Quantitative Spectroscopy and Radiative Transfer, 318, 108941. https://doi.org/10.1016/j.jqsrt.2024.108941
Vancouver
Crilly A, Duhig B, Bouziani N. Learning closure relations using differentiable programming: An example in radiation transport. Journal of Quantitative Spectroscopy and Radiative Transfer. 2024;318:108941. doi:10.1016/j.jqsrt.2024.108941
BibTeX
@article{Crilly2024,
author = {Crilly, A.J. and Duhig, B. and Bouziani, N.},
title = {Learning closure relations using differentiable programming: An example in radiation transport},
journal = {Journal of Quantitative Spectroscopy and Radiative Transfer},
year = {2024},
volume = {318},
pages = {108941},
doi = {10.1016/j.jqsrt.2024.108941}
}
EUVIMED