A Machine Learning‐Based Approach to Quantify ENSO Sources of Predictability

Abstract A machine learning method is used to identify sources of long‐term ENSO predictability in the ocean (sea surface temperature (SST) and heat content) and the atmosphere (near‐surface zonal wind (U10)). Tropical SST represents the primary source of predictability skill. While U10 does not inc...

Full description

Saved in:
Bibliographic Details
Main Authors: Ioana Colfescu, Hannah Christensen, David John Gagne
Format: Article
Language:English
Published: Wiley 2024-07-01
Series:Geophysical Research Letters
Subjects:
Online Access:https://doi.org/10.1029/2023GL105194
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849716800986546176
author Ioana Colfescu
Hannah Christensen
David John Gagne
author_facet Ioana Colfescu
Hannah Christensen
David John Gagne
author_sort Ioana Colfescu
collection DOAJ
description Abstract A machine learning method is used to identify sources of long‐term ENSO predictability in the ocean (sea surface temperature (SST) and heat content) and the atmosphere (near‐surface zonal wind (U10)). Tropical SST represents the primary source of predictability skill. While U10 does not increase the skill when associated with SST, our analysis suggests U10 alone has apredictive skill comparable to that of SST between 11 and 21 months in advance, from late fall up to late spring. The long‐lead signal originates from coupled wind‐SST interactions across the Indian Ocean (IO) and propagates across the Pacific via an atmospheric bridge mechanism. A linear correlation analysis supports this mechanism, suggesting a precursor link between anomalies in SST in the western and wind in the eastern IO. Our results have important implications for ENSO predictions beyond 1 year ahead and identify the key role of U10 over the IO.
format Article
id doaj-art-116a62a7c8ef465096ea77a64479ae75
institution DOAJ
issn 0094-8276
1944-8007
language English
publishDate 2024-07-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-116a62a7c8ef465096ea77a64479ae752025-08-20T03:12:51ZengWileyGeophysical Research Letters0094-82761944-80072024-07-015113n/an/a10.1029/2023GL105194A Machine Learning‐Based Approach to Quantify ENSO Sources of PredictabilityIoana Colfescu0Hannah Christensen1David John Gagne2National Centre for Atmospheric Science (NCAS) University of Leeds Leeds UKDepartment of Atmospheric, Oceanic and Planetary Physics University of Oxford Oxford UKNational Center for Atmospheric Research Boulder CO USAAbstract A machine learning method is used to identify sources of long‐term ENSO predictability in the ocean (sea surface temperature (SST) and heat content) and the atmosphere (near‐surface zonal wind (U10)). Tropical SST represents the primary source of predictability skill. While U10 does not increase the skill when associated with SST, our analysis suggests U10 alone has apredictive skill comparable to that of SST between 11 and 21 months in advance, from late fall up to late spring. The long‐lead signal originates from coupled wind‐SST interactions across the Indian Ocean (IO) and propagates across the Pacific via an atmospheric bridge mechanism. A linear correlation analysis supports this mechanism, suggesting a precursor link between anomalies in SST in the western and wind in the eastern IO. Our results have important implications for ENSO predictions beyond 1 year ahead and identify the key role of U10 over the IO.https://doi.org/10.1029/2023GL105194machine learningENSOpredictionpredictive skillclimateclimate models
spellingShingle Ioana Colfescu
Hannah Christensen
David John Gagne
A Machine Learning‐Based Approach to Quantify ENSO Sources of Predictability
Geophysical Research Letters
machine learning
ENSO
prediction
predictive skill
climate
climate models
title A Machine Learning‐Based Approach to Quantify ENSO Sources of Predictability
title_full A Machine Learning‐Based Approach to Quantify ENSO Sources of Predictability
title_fullStr A Machine Learning‐Based Approach to Quantify ENSO Sources of Predictability
title_full_unstemmed A Machine Learning‐Based Approach to Quantify ENSO Sources of Predictability
title_short A Machine Learning‐Based Approach to Quantify ENSO Sources of Predictability
title_sort machine learning based approach to quantify enso sources of predictability
topic machine learning
ENSO
prediction
predictive skill
climate
climate models
url https://doi.org/10.1029/2023GL105194
work_keys_str_mv AT ioanacolfescu amachinelearningbasedapproachtoquantifyensosourcesofpredictability
AT hannahchristensen amachinelearningbasedapproachtoquantifyensosourcesofpredictability
AT davidjohngagne amachinelearningbasedapproachtoquantifyensosourcesofpredictability
AT ioanacolfescu machinelearningbasedapproachtoquantifyensosourcesofpredictability
AT hannahchristensen machinelearningbasedapproachtoquantifyensosourcesofpredictability
AT davidjohngagne machinelearningbasedapproachtoquantifyensosourcesofpredictability