The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches
Machine learning methods have now become an optional technique in Earth science research, and such data-driven solutions have also made tremendous progress in weather forecasting and climate prediction in recent years. Since climate data are typically time series, the neural network layers, which ca...
Published in: | Computational Intelligence and Neuroscience |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Hindawi Limited
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1155/2022/6141966 https://doaj.org/article/e146efc9430f44b2a3e9b815908a14a4 |
id |
ftdoajarticles:oai:doaj.org/article:e146efc9430f44b2a3e9b815908a14a4 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:e146efc9430f44b2a3e9b815908a14a4 2023-05-15T17:32:33+02:00 The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches Bin Mu Jing Li Shijin Yuan Xiaodan Luo 2022-01-01T00:00:00Z https://doi.org/10.1155/2022/6141966 https://doaj.org/article/e146efc9430f44b2a3e9b815908a14a4 EN eng Hindawi Limited http://dx.doi.org/10.1155/2022/6141966 https://doaj.org/toc/1687-5273 1687-5273 doi:10.1155/2022/6141966 https://doaj.org/article/e146efc9430f44b2a3e9b815908a14a4 Computational Intelligence and Neuroscience, Vol 2022 (2022) Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 article 2022 ftdoajarticles https://doi.org/10.1155/2022/6141966 2022-12-30T23:33:47Z Machine learning methods have now become an optional technique in Earth science research, and such data-driven solutions have also made tremendous progress in weather forecasting and climate prediction in recent years. Since climate data are typically time series, the neural network layers, which can identify the intrinsic connections between the points of the sequence and features in two-dimensional data, perform particularly well for climate prediction. The North Atlantic Oscillation (NAO) is a prominent atmospherical mode in the northern hemisphere, with the frequency change characteristic of sea level pressure (SLP) in the North Atlantic sector. One of the reasons why NAO prediction is still challenging is that NAO is also proven to be influenced by other climate circulations, the most significant of which is the interaction between El Niño-Southern Oscillation (ENSO) and NAO. Therefore, sea surface temperature (SST) in the Pacific Ocean used to characterize ENSO is also one of the factors that contribute to the evolution of NAO and can be used as an input factor to predict the NAO. In this paper, the seasonal lag correlation between ENSO and NAO is explored and analyzed. The interaction has been considered in both short-term forecasting and midterm prediction of the NAO variability. The monthly NAO index (NAOI) fluctuation is predicted using the Niño indices based on the RF-Var model, and the accuracy achieves 68% when the lead time is about three months. In addition, integrating multiple physical variables directly related to the NAO and Pacific SST, the short-term NAO forecasting is conducted using a multi-channel neural network named AccNet with trajectory gated recursive unit (TrajGRU) layer. AccNet has the ability to identify the mechanism of the high-frequency variation in several days, and the NAO variability is indicated by SLP. The loss function of AccNet is set to anomaly correlation coefficient (ACC), which is the indicator that verifies spatial correlation in geoscience. Forecasting extreme ... Article in Journal/Newspaper North Atlantic North Atlantic oscillation Directory of Open Access Journals: DOAJ Articles Pacific Computational Intelligence and Neuroscience 2022 1 22 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 |
spellingShingle |
Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Bin Mu Jing Li Shijin Yuan Xiaodan Luo The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches |
topic_facet |
Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 |
description |
Machine learning methods have now become an optional technique in Earth science research, and such data-driven solutions have also made tremendous progress in weather forecasting and climate prediction in recent years. Since climate data are typically time series, the neural network layers, which can identify the intrinsic connections between the points of the sequence and features in two-dimensional data, perform particularly well for climate prediction. The North Atlantic Oscillation (NAO) is a prominent atmospherical mode in the northern hemisphere, with the frequency change characteristic of sea level pressure (SLP) in the North Atlantic sector. One of the reasons why NAO prediction is still challenging is that NAO is also proven to be influenced by other climate circulations, the most significant of which is the interaction between El Niño-Southern Oscillation (ENSO) and NAO. Therefore, sea surface temperature (SST) in the Pacific Ocean used to characterize ENSO is also one of the factors that contribute to the evolution of NAO and can be used as an input factor to predict the NAO. In this paper, the seasonal lag correlation between ENSO and NAO is explored and analyzed. The interaction has been considered in both short-term forecasting and midterm prediction of the NAO variability. The monthly NAO index (NAOI) fluctuation is predicted using the Niño indices based on the RF-Var model, and the accuracy achieves 68% when the lead time is about three months. In addition, integrating multiple physical variables directly related to the NAO and Pacific SST, the short-term NAO forecasting is conducted using a multi-channel neural network named AccNet with trajectory gated recursive unit (TrajGRU) layer. AccNet has the ability to identify the mechanism of the high-frequency variation in several days, and the NAO variability is indicated by SLP. The loss function of AccNet is set to anomaly correlation coefficient (ACC), which is the indicator that verifies spatial correlation in geoscience. Forecasting extreme ... |
format |
Article in Journal/Newspaper |
author |
Bin Mu Jing Li Shijin Yuan Xiaodan Luo |
author_facet |
Bin Mu Jing Li Shijin Yuan Xiaodan Luo |
author_sort |
Bin Mu |
title |
The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches |
title_short |
The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches |
title_full |
The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches |
title_fullStr |
The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches |
title_full_unstemmed |
The NAO Variability Prediction and Forecasting with Multiple Time Scales Driven by ENSO Using Machine Learning Approaches |
title_sort |
nao variability prediction and forecasting with multiple time scales driven by enso using machine learning approaches |
publisher |
Hindawi Limited |
publishDate |
2022 |
url |
https://doi.org/10.1155/2022/6141966 https://doaj.org/article/e146efc9430f44b2a3e9b815908a14a4 |
geographic |
Pacific |
geographic_facet |
Pacific |
genre |
North Atlantic North Atlantic oscillation |
genre_facet |
North Atlantic North Atlantic oscillation |
op_source |
Computational Intelligence and Neuroscience, Vol 2022 (2022) |
op_relation |
http://dx.doi.org/10.1155/2022/6141966 https://doaj.org/toc/1687-5273 1687-5273 doi:10.1155/2022/6141966 https://doaj.org/article/e146efc9430f44b2a3e9b815908a14a4 |
op_doi |
https://doi.org/10.1155/2022/6141966 |
container_title |
Computational Intelligence and Neuroscience |
container_volume |
2022 |
container_start_page |
1 |
op_container_end_page |
22 |
_version_ |
1766130733743603712 |