Machine learning prediction of the Madden-Julian oscillation

Abstract The socioeconomic impact of weather extremes draws the attention of researchers to the development of novel methodologies to make more accurate weather predictions. The Madden–Julian oscillation (MJO) is the dominant mode of variability in the tropical atmosphere on sub-seasonal time scales...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Riccardo Silini, Marcelo Barreiro, Cristina Masoller
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Environmental sciences GE1-350 Meteorology. Climatology QC851-999
Acceso en línea:	https://doaj.org/article/fececcd91ff74ab4ac7e491179b51cad
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fececcd91ff74ab4ac7e491179b51cad
record_format	dspace
spelling	oai:doaj.org-article:fececcd91ff74ab4ac7e491179b51cad2021-11-28T12:24:48ZMachine learning prediction of the Madden-Julian oscillation10.1038/s41612-021-00214-62397-3722https://doaj.org/article/fececcd91ff74ab4ac7e491179b51cad2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41612-021-00214-6https://doaj.org/toc/2397-3722Abstract The socioeconomic impact of weather extremes draws the attention of researchers to the development of novel methodologies to make more accurate weather predictions. The Madden–Julian oscillation (MJO) is the dominant mode of variability in the tropical atmosphere on sub-seasonal time scales, and can promote or enhance extreme events in both, the tropics and the extratropics. Forecasting extreme events on the sub-seasonal time scale (from 10 days to about 3 months) is very challenging due to a poor understanding of the phenomena that can increase predictability on this time scale. Here we show that two artificial neural networks (ANNs), a feed-forward neural network and a recurrent neural network, allow a very competitive MJO prediction. While our average prediction skill is about 26–27 days (which competes with that obtained with most computationally demanding state-of-the-art climate models), for some initial phases and seasons the ANNs have a prediction skill of 60 days or longer. Furthermore, we show that the ANNs have a good ability to predict the MJO phase, but the amplitude is underestimated.Riccardo SiliniMarcelo BarreiroCristina MasollerNature PortfolioarticleEnvironmental sciencesGE1-350Meteorology. ClimatologyQC851-999ENnpj Climate and Atmospheric Science, Vol 4, Iss 1, Pp 1-7 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Environmental sciences GE1-350 Meteorology. Climatology QC851-999
spellingShingle	Environmental sciences GE1-350 Meteorology. Climatology QC851-999 Riccardo Silini Marcelo Barreiro Cristina Masoller Machine learning prediction of the Madden-Julian oscillation
description	Abstract The socioeconomic impact of weather extremes draws the attention of researchers to the development of novel methodologies to make more accurate weather predictions. The Madden–Julian oscillation (MJO) is the dominant mode of variability in the tropical atmosphere on sub-seasonal time scales, and can promote or enhance extreme events in both, the tropics and the extratropics. Forecasting extreme events on the sub-seasonal time scale (from 10 days to about 3 months) is very challenging due to a poor understanding of the phenomena that can increase predictability on this time scale. Here we show that two artificial neural networks (ANNs), a feed-forward neural network and a recurrent neural network, allow a very competitive MJO prediction. While our average prediction skill is about 26–27 days (which competes with that obtained with most computationally demanding state-of-the-art climate models), for some initial phases and seasons the ANNs have a prediction skill of 60 days or longer. Furthermore, we show that the ANNs have a good ability to predict the MJO phase, but the amplitude is underestimated.
format	article
author	Riccardo Silini Marcelo Barreiro Cristina Masoller
author_facet	Riccardo Silini Marcelo Barreiro Cristina Masoller
author_sort	Riccardo Silini
title	Machine learning prediction of the Madden-Julian oscillation
title_short	Machine learning prediction of the Madden-Julian oscillation
title_full	Machine learning prediction of the Madden-Julian oscillation
title_fullStr	Machine learning prediction of the Madden-Julian oscillation
title_full_unstemmed	Machine learning prediction of the Madden-Julian oscillation
title_sort	machine learning prediction of the madden-julian oscillation
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/fececcd91ff74ab4ac7e491179b51cad
work_keys_str_mv	AT riccardosilini machinelearningpredictionofthemaddenjulianoscillation AT marcelobarreiro machinelearningpredictionofthemaddenjulianoscillation AT cristinamasoller machinelearningpredictionofthemaddenjulianoscillation
_version_	1718407993059442688

Machine learning prediction of the Madden-Julian oscillation

Ejemplares similares