Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit Model
The prediction of sea surface temperature anomalies (SSTA) is vital to the study of marine ecosystems and global climate. The SSTA can be accurately forecasted one step ahead by numerical and statistical methods. However, multistep-ahead forecasting for SSTA is greatly challenging since the nonlinea...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9866103/ |
_version_ | 1811270130343084032 |
---|---|
author | Xiaoyin Liu Ning Li Jun Guo Zhongyong Fan Xiaoping Lu Weifeng Liu Baodi Liu |
author_facet | Xiaoyin Liu Ning Li Jun Guo Zhongyong Fan Xiaoping Lu Weifeng Liu Baodi Liu |
author_sort | Xiaoyin Liu |
collection | DOAJ |
description | The prediction of sea surface temperature anomalies (SSTA) is vital to the study of marine ecosystems and global climate. The SSTA can be accurately forecasted one step ahead by numerical and statistical methods. However, multistep-ahead forecasting for SSTA is greatly challenging since the nonlinearity and nonstationarity of SSTA and the lag problem of prediction. Therefore, in this article, a multistep-ahead SSTA forecasting method based on the hybrid empirical mode decomposition (EMD) and gated recurrent unit (GRU) model is proposed considering that EMD has the advantage of reducing data complexity and GRU is good at long-term prediction of data. First, the EMD algorithm is applied to obtain several intrinsic modal mode functions that are more stationary than the original data. Then, GRU is used for multistep forecasting, in which three multistep forecasting strategies (recursive, direct, and multioutput) are compared. The proposed hybrid model is validated by multistep forecasting for monthly average SSTA at the Niño3.4 region. The experimental results show that using reconstruction error as part of the prediction effectively improves the prediction accuracy of the EEMD-GRU model and outperforms other EMD algorithms combined with GRU. Compared with traditional models, the EEMD-GRU model can better predict future multimonth trends of SSTA and effectively alleviate the problem of prediction lag of the traditional model. Finally, this model is applied to the Niño3.4 regional SSTA prediction, and the results show that this model can provide a reference for ocean research. |
first_indexed | 2024-04-12T21:55:10Z |
format | Article |
id | doaj.art-a4bd238a44404b44a9867bbc9ca3a661 |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-12T21:55:10Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-a4bd238a44404b44a9867bbc9ca3a6612022-12-22T03:15:21ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01157525753810.1109/JSTARS.2022.32012289866103Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit ModelXiaoyin Liu0https://orcid.org/0000-0001-7407-2216Ning Li1Jun Guo2Zhongyong Fan3Xiaoping Lu4Weifeng Liu5https://orcid.org/0000-0002-5388-9080Baodi Liu6https://orcid.org/0000-0002-1408-5514College of Science, China University of Petroleum (East China), Qingdao, ChinaCollege of Science, China University of Petroleum (East China), Qingdao, ChinaCollege of Science, China University of Petroleum (East China), Qingdao, ChinaCollege of Science, China University of Petroleum (East China), Qingdao, ChinaCOSMO Industrial Intelligence Institute, Qingdao, ChinaCollege of Control Science and Engineering, China University of Petroleum (East China), Qingdao, ChinaCollege of Control Science and Engineering, China University of Petroleum (East China), Qingdao, ChinaThe prediction of sea surface temperature anomalies (SSTA) is vital to the study of marine ecosystems and global climate. The SSTA can be accurately forecasted one step ahead by numerical and statistical methods. However, multistep-ahead forecasting for SSTA is greatly challenging since the nonlinearity and nonstationarity of SSTA and the lag problem of prediction. Therefore, in this article, a multistep-ahead SSTA forecasting method based on the hybrid empirical mode decomposition (EMD) and gated recurrent unit (GRU) model is proposed considering that EMD has the advantage of reducing data complexity and GRU is good at long-term prediction of data. First, the EMD algorithm is applied to obtain several intrinsic modal mode functions that are more stationary than the original data. Then, GRU is used for multistep forecasting, in which three multistep forecasting strategies (recursive, direct, and multioutput) are compared. The proposed hybrid model is validated by multistep forecasting for monthly average SSTA at the Niño3.4 region. The experimental results show that using reconstruction error as part of the prediction effectively improves the prediction accuracy of the EEMD-GRU model and outperforms other EMD algorithms combined with GRU. Compared with traditional models, the EEMD-GRU model can better predict future multimonth trends of SSTA and effectively alleviate the problem of prediction lag of the traditional model. Finally, this model is applied to the Niño3.4 regional SSTA prediction, and the results show that this model can provide a reference for ocean research.https://ieeexplore.ieee.org/document/9866103/Empirical mode decompositiongated recurrent unit neural networkmultistep-ahead predictionprediction lagssea surface temperature anomalies |
spellingShingle | Xiaoyin Liu Ning Li Jun Guo Zhongyong Fan Xiaoping Lu Weifeng Liu Baodi Liu Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit Model IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Empirical mode decomposition gated recurrent unit neural network multistep-ahead prediction prediction lags sea surface temperature anomalies |
title | Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit Model |
title_full | Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit Model |
title_fullStr | Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit Model |
title_full_unstemmed | Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit Model |
title_short | Multistep-Ahead Prediction of Ocean SSTA Based on Hybrid Empirical Mode Decomposition and Gated Recurrent Unit Model |
title_sort | multistep ahead prediction of ocean ssta based on hybrid empirical mode decomposition and gated recurrent unit model |
topic | Empirical mode decomposition gated recurrent unit neural network multistep-ahead prediction prediction lags sea surface temperature anomalies |
url | https://ieeexplore.ieee.org/document/9866103/ |
work_keys_str_mv | AT xiaoyinliu multistepaheadpredictionofoceansstabasedonhybridempiricalmodedecompositionandgatedrecurrentunitmodel AT ningli multistepaheadpredictionofoceansstabasedonhybridempiricalmodedecompositionandgatedrecurrentunitmodel AT junguo multistepaheadpredictionofoceansstabasedonhybridempiricalmodedecompositionandgatedrecurrentunitmodel AT zhongyongfan multistepaheadpredictionofoceansstabasedonhybridempiricalmodedecompositionandgatedrecurrentunitmodel AT xiaopinglu multistepaheadpredictionofoceansstabasedonhybridempiricalmodedecompositionandgatedrecurrentunitmodel AT weifengliu multistepaheadpredictionofoceansstabasedonhybridempiricalmodedecompositionandgatedrecurrentunitmodel AT baodiliu multistepaheadpredictionofoceansstabasedonhybridempiricalmodedecompositionandgatedrecurrentunitmodel |