Fourier neural operators for Rayleigh–Bénard convection
Publikationstyp
Conference Paper
Date Issued
2026-06
Sprache
English
First published in
Number in series
l16784 LNCS
Start Page
455
End Page
462
Citation
26th International Conference on Computational Science, ICCS 2026
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
Springer
ISBN of container
978-3-032-29924-6
978-3-032-29923-9
Is Supplemented By
We propose an improved Fourier Neural Operator (FNO) for modeling two-dimensional Rayleigh–Bénard convection by predict-ing time increments instead of full solutions, achieving higher accuracy than a standard FNO baseline. The resulting model is compact (314k parameters, 1.26 MB) and fast (7 ms inference), while maintainingsim-ilaraccuracyasdemonstratedinpreviousbenchmarks.WeshowthatalthoughFNOsgeneralizetofinermeshes,accuracyremainslimitedbytheresolutionofthetrainingdata.
Subjects
Fourier Neural Operator
Ra yleigh–Bénardconvection
DDC Class
510: Mathematics