Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability
Abstract We use neural networks and large climate model ensembles to explore predictability of internal variability in sea surface temperature (SST) anomalies on interannual (1–3 years) and decadal (1–5 and 3–7 years) timescales. We find that neural networks can skillfully predict SST anomalies at t...
Published in: | Geophysical Research Letters |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1029/2023GL108099 https://doaj.org/article/80757044f02545b2b306cf448bc1c1ff |
id |
ftdoajarticles:oai:doaj.org/article:80757044f02545b2b306cf448bc1c1ff |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:80757044f02545b2b306cf448bc1c1ff 2024-09-09T19:57:11+00:00 Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability Frances V. Davenport Elizabeth A. Barnes Emily M. Gordon 2024-06-01T00:00:00Z https://doi.org/10.1029/2023GL108099 https://doaj.org/article/80757044f02545b2b306cf448bc1c1ff EN eng Wiley https://doi.org/10.1029/2023GL108099 https://doaj.org/toc/0094-8276 https://doaj.org/toc/1944-8007 1944-8007 0094-8276 doi:10.1029/2023GL108099 https://doaj.org/article/80757044f02545b2b306cf448bc1c1ff Geophysical Research Letters, Vol 51, Iss 11, Pp n/a-n/a (2024) climate prediction neural networks decadal prediction machine learning Geophysics. Cosmic physics QC801-809 article 2024 ftdoajarticles https://doi.org/10.1029/2023GL108099 2024-08-05T17:48:59Z Abstract We use neural networks and large climate model ensembles to explore predictability of internal variability in sea surface temperature (SST) anomalies on interannual (1–3 years) and decadal (1–5 and 3–7 years) timescales. We find that neural networks can skillfully predict SST anomalies at these lead times, especially in the North Atlantic, North Pacific, Tropical Pacific, Tropical Atlantic and Southern Ocean. The spatial patterns of SST predictability vary across the nine climate models studied. The neural networks identify “windows of opportunity” where future SST anomalies can be predicted with more certainty. Neural networks trained on climate models also make skillful SST predictions in reconstructed observations, although the skill varies depending on which climate model the network was trained. Our results highlight that neural networks can identify predictable internal variability within existing climate data sets and show important differences in how well patterns of SST predictability in climate models translate to the real world. Article in Journal/Newspaper North Atlantic Southern Ocean Directory of Open Access Journals: DOAJ Articles Southern Ocean Pacific Geophysical Research Letters 51 11 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
climate prediction neural networks decadal prediction machine learning Geophysics. Cosmic physics QC801-809 |
spellingShingle |
climate prediction neural networks decadal prediction machine learning Geophysics. Cosmic physics QC801-809 Frances V. Davenport Elizabeth A. Barnes Emily M. Gordon Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability |
topic_facet |
climate prediction neural networks decadal prediction machine learning Geophysics. Cosmic physics QC801-809 |
description |
Abstract We use neural networks and large climate model ensembles to explore predictability of internal variability in sea surface temperature (SST) anomalies on interannual (1–3 years) and decadal (1–5 and 3–7 years) timescales. We find that neural networks can skillfully predict SST anomalies at these lead times, especially in the North Atlantic, North Pacific, Tropical Pacific, Tropical Atlantic and Southern Ocean. The spatial patterns of SST predictability vary across the nine climate models studied. The neural networks identify “windows of opportunity” where future SST anomalies can be predicted with more certainty. Neural networks trained on climate models also make skillful SST predictions in reconstructed observations, although the skill varies depending on which climate model the network was trained. Our results highlight that neural networks can identify predictable internal variability within existing climate data sets and show important differences in how well patterns of SST predictability in climate models translate to the real world. |
format |
Article in Journal/Newspaper |
author |
Frances V. Davenport Elizabeth A. Barnes Emily M. Gordon |
author_facet |
Frances V. Davenport Elizabeth A. Barnes Emily M. Gordon |
author_sort |
Frances V. Davenport |
title |
Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability |
title_short |
Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability |
title_full |
Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability |
title_fullStr |
Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability |
title_full_unstemmed |
Combining Neural Networks and CMIP6 Simulations to Learn Windows of Opportunity for Skillful Prediction of Multiyear Sea Surface Temperature Variability |
title_sort |
combining neural networks and cmip6 simulations to learn windows of opportunity for skillful prediction of multiyear sea surface temperature variability |
publisher |
Wiley |
publishDate |
2024 |
url |
https://doi.org/10.1029/2023GL108099 https://doaj.org/article/80757044f02545b2b306cf448bc1c1ff |
geographic |
Southern Ocean Pacific |
geographic_facet |
Southern Ocean Pacific |
genre |
North Atlantic Southern Ocean |
genre_facet |
North Atlantic Southern Ocean |
op_source |
Geophysical Research Letters, Vol 51, Iss 11, Pp n/a-n/a (2024) |
op_relation |
https://doi.org/10.1029/2023GL108099 https://doaj.org/toc/0094-8276 https://doaj.org/toc/1944-8007 1944-8007 0094-8276 doi:10.1029/2023GL108099 https://doaj.org/article/80757044f02545b2b306cf448bc1c1ff |
op_doi |
https://doi.org/10.1029/2023GL108099 |
container_title |
Geophysical Research Letters |
container_volume |
51 |
container_issue |
11 |
_version_ |
1809928075167662080 |