NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery
The North Atlantic Oscillation (NAO) is a major climatic phenomenon in the Northern Hemisphere, but the underlying air–sea interaction and physical mechanisms remain elusive. Despite successful short-term forecasts using physics-based numerical models, longer-term forecasts of NAO continue to pose a...
Published in: | Atmosphere |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/atmos14050792 |
id |
ftmdpi:oai:mdpi.com:/2073-4433/14/5/792/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2073-4433/14/5/792/ 2023-08-20T04:08:15+02:00 NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery Bin Mu Xin Jiang Shijin Yuan Yuehan Cui Bo Qin agris 2023-04-26 application/pdf https://doi.org/10.3390/atmos14050792 EN eng Multidisciplinary Digital Publishing Institute Meteorology https://dx.doi.org/10.3390/atmos14050792 https://creativecommons.org/licenses/by/4.0/ Atmosphere; Volume 14; Issue 5; Pages: 792 North Atlantic Oscillation causal discovery air–sea coupling deep learning Text 2023 ftmdpi https://doi.org/10.3390/atmos14050792 2023-08-01T09:51:39Z The North Atlantic Oscillation (NAO) is a major climatic phenomenon in the Northern Hemisphere, but the underlying air–sea interaction and physical mechanisms remain elusive. Despite successful short-term forecasts using physics-based numerical models, longer-term forecasts of NAO continue to pose a challenge. In this study, we employ advanced data-driven causal discovery techniques to explore the causality between multiple ocean–atmosphere processes and NAO. We identify the best NAO predictors based on this causality analysis and develop NAO-MCD, a multivariate air–sea coupled model that incorporates causal discovery to provide 1–6 month lead seasonal forecasts of NAO. Our results demonstrate that the selected predictors are strongly associated with NAO development, enabling accurate forecasts of NAO. NAO-MCD significantly outperforms conventional numerical models and provides reliable seasonal forecasts of NAO, particularly for winter events. Moreover, our model extends the range of accurate forecasts, surpassing state-of-the-art performance at 2- to 6-month lead-time NAO forecasts, substantially outperforming conventional numerical models. Text North Atlantic North Atlantic oscillation MDPI Open Access Publishing Atmosphere 14 5 792 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
North Atlantic Oscillation causal discovery air–sea coupling deep learning |
spellingShingle |
North Atlantic Oscillation causal discovery air–sea coupling deep learning Bin Mu Xin Jiang Shijin Yuan Yuehan Cui Bo Qin NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery |
topic_facet |
North Atlantic Oscillation causal discovery air–sea coupling deep learning |
description |
The North Atlantic Oscillation (NAO) is a major climatic phenomenon in the Northern Hemisphere, but the underlying air–sea interaction and physical mechanisms remain elusive. Despite successful short-term forecasts using physics-based numerical models, longer-term forecasts of NAO continue to pose a challenge. In this study, we employ advanced data-driven causal discovery techniques to explore the causality between multiple ocean–atmosphere processes and NAO. We identify the best NAO predictors based on this causality analysis and develop NAO-MCD, a multivariate air–sea coupled model that incorporates causal discovery to provide 1–6 month lead seasonal forecasts of NAO. Our results demonstrate that the selected predictors are strongly associated with NAO development, enabling accurate forecasts of NAO. NAO-MCD significantly outperforms conventional numerical models and provides reliable seasonal forecasts of NAO, particularly for winter events. Moreover, our model extends the range of accurate forecasts, surpassing state-of-the-art performance at 2- to 6-month lead-time NAO forecasts, substantially outperforming conventional numerical models. |
format |
Text |
author |
Bin Mu Xin Jiang Shijin Yuan Yuehan Cui Bo Qin |
author_facet |
Bin Mu Xin Jiang Shijin Yuan Yuehan Cui Bo Qin |
author_sort |
Bin Mu |
title |
NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery |
title_short |
NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery |
title_full |
NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery |
title_fullStr |
NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery |
title_full_unstemmed |
NAO Seasonal Forecast Using a Multivariate Air–Sea Coupled Deep Learning Model Combined with Causal Discovery |
title_sort |
nao seasonal forecast using a multivariate air–sea coupled deep learning model combined with causal discovery |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://doi.org/10.3390/atmos14050792 |
op_coverage |
agris |
genre |
North Atlantic North Atlantic oscillation |
genre_facet |
North Atlantic North Atlantic oscillation |
op_source |
Atmosphere; Volume 14; Issue 5; Pages: 792 |
op_relation |
Meteorology https://dx.doi.org/10.3390/atmos14050792 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/atmos14050792 |
container_title |
Atmosphere |
container_volume |
14 |
container_issue |
5 |
container_start_page |
792 |
_version_ |
1774720426204725248 |