Computer Science - Learning; Physics - Atmospheric and Oceanic Physics; Deep Learning; Fourier Neural Operators; Parameterizations; PyQG
Abstract :
[en] In climate simulations, small-scale processes shape ocean dynamics but remain
computationally expensive to resolve directly. For this reason, their
contributions are commonly approximated using empirical parameterizations,
which lead to significant errors in long-term projections. In this work, we
develop parameterizations based on Fourier Neural Operators, showcasing their
accuracy and generalizability in comparison to other approaches. Finally, we
discuss the potential and limitations of neural networks operating in the
frequency domain, paving the way for future investigation.
Research Center/Unit :
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège
Disciplines :
Electrical & electronics engineering
Author, co-author :
Mangeleer, Victor ; Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Big Data
Louppe, Gilles ; Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Big Data
Language :
English
Title :
Robust Ocean Subgrid-Scale Parameterizations Using Fourier Neural Operators
Publication date :
01 November 2023
Event name :
Machine Learning and the Physical Sciences, NeurIPS 2023
