A machine learning model for reconstructing skin-friction drag over ocean surface waves

Simple item page
Author(s)Yousefi, Kianoosh
Author(s)Hora, Gurpreet Singh
Author(s)Yang, Hongshuo
Author(s)Veron, Fabrice
Author(s)Giometto, Marco G.
Date Accessioned2024-03-28T18:08:42Z
Date Available2024-03-28T18:08:42Z
Publication Date2024-03-25
DescriptionThis article was originally published in Journal of Fluid Mechanics. The version of record is available at: https://doi.org/10.1017/jfm.2024.81. © The Author(s), 2024. Published by Cambridge University Press.
AbstractIn order to improve the predictive abilities of weather and climate models, it is essential to understand the behaviour of wind stress at the ocean surface. Wind stress is contingent on small-scale interfacial dynamics typically not directly resolved in numerical models. Although skin friction contributes considerably to the total stress up to moderate wind speeds, it is notoriously challenging to measure and predict using physics-based approaches. This work proposes a supervised machine learning (ML) model that estimates the spatial distribution of the skin-friction drag over wind waves using solely wave elevation and wave age, which are relatively easy to acquire. The input–output pairs are high-resolution wave profiles and their corresponding surface viscous stresses collected from laboratory experiments. The ML model is built upon a convolutional neural network architecture that incorporates the Mish nonlinearity as its activation function. Results show that the model can accurately predict the overall distribution of viscous stresses; it captures the peak of viscous stress at/near the crest and its dramatic drop to almost null just past the crest in cases of intermittent airflow separation. The predicted area-aggregate skin friction is also in excellent agreement with the corresponding measurements. The proposed method offers a practical pathway for estimating both local and area-aggregate skin friction and can be easily integrated into existing numerical models for the study of air–sea interactions.
SponsorThis research is supported by the National Science Foundation (NSF) under grant number 2030859 to the Computing Research Association (CRA) for the Computing Innovation Fellows Project. This research was also partially funded by the National Institute of Standards and Technology under grant number 70NANB22H057. H.Y. acknowledges support from the Columbia University Summer at SEAS Program. This work used the Anvil supercomputer at Purdue University through allocation ATM180022 from the Advanced Cyberinfrastructure Coordination Ecosystem: Services and Support (ACCESS) program, which is supported by NSF grants 2138259, 2138286, 2138307, 2137603 and 2138296.
CitationYousefi, Kianoosh, Gurpreet Singh Hora, Hongshuo Yang, Fabrice Veron, and Marco G. Giometto. “A Machine Learning Model for Reconstructing Skin-Friction Drag over Ocean Surface Waves.” Journal of Fluid Mechanics 983 (March 25, 2024): A9. https://doi.org/10.1017/jfm.2024.81.
ISSN1469-7645
URLhttps://udspace.udel.edu/handle/19716/34232
Languageen_US
PublisherJournal of Fluid Mechanics
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
Keywordsmachine learning
Keywordssurface gravity waves
Keywordswind-wave interactions
TitleA machine learning model for reconstructing skin-friction drag over ocean surface waves
TypeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A machine learning model for reconstructing skin-friction drag over ocean surface waves.pdf
Size:
5.42 MB
Format:
Adobe Portable Document Format
Description:
Main article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.22 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Open Access Publications