Contribution to a conference proceedings/Contribution to a book

FZJ-2026-03291

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Fourier Neural Operators for Rayleigh–Bénard Convection

John, C. M. (Corresponding author)FZJ* ; Lunet, T. ; Götschel, S. ; Herten, A.FZJ* ; Kesselheim, S.FZJ* ; Ruprecht, D.

2026
Springer Nature Switzerland Cham
ISBN: 978-3-032-29923-9 (print), 978-3-032-29924-6 (electronic)

This record in other databases:  

Please use a persistent id in citations: doi:10.1007/978-3-032-29924-6_40

Abstract: We propose an improved Fourier Neural Operator (FNO) for modeling two-dimensional Rayleigh-Bénard convection by predicting 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 maintaining similar accuracy as demonstrated in previous benchmarks. We show that although FNOs generalize to finer meshes, accuracy remains limited by the resolution of the training data.

Note: Won the Best Poster Paper Award

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511) (POF4-511)
2. 5122 - Future Computing & Big Data Systems (POF4-512) (POF4-512)
3. Inno4Scale - Innovative Algorithms for Applications on European Exascale Supercomputers (101118139) (101118139)

Appears in the scientific report 2026

---

Database coverage:
Nationallizenz ; SCOPUS

---