Deep neural networks for active wave breaking classification

Abstract Wave breaking is an important process for energy dissipation in the open ocean and coastal seas. It drives beach morphodynamics, controls air-sea interactions, determines when ship and offshore structure operations can occur safely, and influences on the retrieval of ocean properties from s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Caio Eadi Stringari, Pedro Veras Guimarães, Jean-François Filipot, Fabien Leckler, Rui Duarte
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c794f5a8c357497da7d41ffed41a0f97
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c794f5a8c357497da7d41ffed41a0f97
record_format	dspace
spelling	oai:doaj.org-article:c794f5a8c357497da7d41ffed41a0f972021-12-02T14:27:02ZDeep neural networks for active wave breaking classification10.1038/s41598-021-83188-y2045-2322https://doaj.org/article/c794f5a8c357497da7d41ffed41a0f972021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83188-yhttps://doaj.org/toc/2045-2322Abstract Wave breaking is an important process for energy dissipation in the open ocean and coastal seas. It drives beach morphodynamics, controls air-sea interactions, determines when ship and offshore structure operations can occur safely, and influences on the retrieval of ocean properties from satellites. Still, wave breaking lacks a proper physical understanding mainly due to scarce observational field data. Consequently, new methods and data are required to improve our current understanding of this process. In this paper we present a novel machine learning method to detect active wave breaking, that is, waves that are actively generating visible bubble entrainment in video imagery data. The present method is based on classical machine learning and deep learning techniques and is made freely available to the community alongside this publication. The results indicate that our best performing model had a balanced classification accuracy score of $$\approx$$ ≈ 90% when classifying active wave breaking in the test dataset. An example of a direct application of the method includes a statistical description of geometrical and kinematic properties of breaking waves. We expect that the present method and the associated dataset will be crucial for future research related to wave breaking in several areas of research, which include but are not limited to: improving operational forecast models, developing risk assessment and coastal management tools, and refining the retrieval of remotely sensed ocean properties.Caio Eadi StringariPedro Veras GuimarãesJean-François FilipotFabien LecklerRui DuarteNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Caio Eadi Stringari Pedro Veras Guimarães Jean-François Filipot Fabien Leckler Rui Duarte Deep neural networks for active wave breaking classification
description	Abstract Wave breaking is an important process for energy dissipation in the open ocean and coastal seas. It drives beach morphodynamics, controls air-sea interactions, determines when ship and offshore structure operations can occur safely, and influences on the retrieval of ocean properties from satellites. Still, wave breaking lacks a proper physical understanding mainly due to scarce observational field data. Consequently, new methods and data are required to improve our current understanding of this process. In this paper we present a novel machine learning method to detect active wave breaking, that is, waves that are actively generating visible bubble entrainment in video imagery data. The present method is based on classical machine learning and deep learning techniques and is made freely available to the community alongside this publication. The results indicate that our best performing model had a balanced classification accuracy score of $$\approx$$ ≈ 90% when classifying active wave breaking in the test dataset. An example of a direct application of the method includes a statistical description of geometrical and kinematic properties of breaking waves. We expect that the present method and the associated dataset will be crucial for future research related to wave breaking in several areas of research, which include but are not limited to: improving operational forecast models, developing risk assessment and coastal management tools, and refining the retrieval of remotely sensed ocean properties.
format	article
author	Caio Eadi Stringari Pedro Veras Guimarães Jean-François Filipot Fabien Leckler Rui Duarte
author_facet	Caio Eadi Stringari Pedro Veras Guimarães Jean-François Filipot Fabien Leckler Rui Duarte
author_sort	Caio Eadi Stringari
title	Deep neural networks for active wave breaking classification
title_short	Deep neural networks for active wave breaking classification
title_full	Deep neural networks for active wave breaking classification
title_fullStr	Deep neural networks for active wave breaking classification
title_full_unstemmed	Deep neural networks for active wave breaking classification
title_sort	deep neural networks for active wave breaking classification
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/c794f5a8c357497da7d41ffed41a0f97
work_keys_str_mv	AT caioeadistringari deepneuralnetworksforactivewavebreakingclassification AT pedroverasguimaraes deepneuralnetworksforactivewavebreakingclassification AT jeanfrancoisfilipot deepneuralnetworksforactivewavebreakingclassification AT fabienleckler deepneuralnetworksforactivewavebreakingclassification AT ruiduarte deepneuralnetworksforactivewavebreakingclassification
_version_	1718391337572630528

Deep neural networks for active wave breaking classification

Ejemplares similares