Nonlinear wave evolution with data-driven breaking.

Autor: Eeltink D; Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States. eeltink@mit.edu.; Department of Engineering Science, University of Oxford, Oxford, UK. eeltink@mit.edu., Branger H; Aix-Marseille University, CNRS, Centrale Marseille, IRPHE, Marseille, France., Luneau C; Aix-Marseille University, CNRS, Centrale Marseille, IRPHE, Marseille, France., He Y; Centre for Wind, Waves and Water, School of Civil Engineering, The University of Sydney, Sydney, NSW, Australia., Chabchoub A; Centre for Wind, Waves and Water, School of Civil Engineering, The University of Sydney, Sydney, NSW, Australia.; Disaster Prevention Research Institute, Kyoto University, Kyoto, Japan.; Hakubi Center for Advanced Research, Kyoto University, Kyoto, Japan., Kasparian J; Group of Applied Physics and Institute for Environmental Sciences, University of Geneva, Geneva, Switzerland., van den Bremer TS; Department of Engineering Science, University of Oxford, Oxford, UK.; Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, The Netherlands., Sapsis TP; Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States. sapsis@mit.edu.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2022 Apr 29; Vol. 13 (1), pp. 2343. Date of Electronic Publication: 2022 Apr 29.
DOI: 10.1038/s41467-022-30025-z
Abstrakt: Wave breaking is the main mechanism that dissipates energy input into ocean waves by wind and transferred across the spectrum by nonlinearity. It determines the properties of a sea state and plays a crucial role in ocean-atmosphere interaction, ocean pollution, and rogue waves. Owing to its turbulent nature, wave breaking remains too computationally demanding to solve using direct numerical simulations except in simple, short-duration circumstances. To overcome this challenge, we present a blended machine learning framework in which a physics-based nonlinear evolution model for deep-water, non-breaking waves and a recurrent neural network are combined to predict the evolution of breaking waves. We use wave tank measurements rather than simulations to provide training data and use a long short-term memory neural network to apply a finite-domain correction to the evolution model. Our blended machine learning framework gives excellent predictions of breaking and its effects on wave evolution, including for external data.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz: