Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition

The Pacific Decadal Oscillation (PDO), as the dominant mode of decadal sea surface temperature variability in the North Pacific, exhibits both interannual and decadal fluctuations that significantly influence global climate. The complexity associated with PDO changes poses challenges for accurate pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Hang Yu, Junbo Lei, Pengfei Lin, Tao Zhang, Hailong Liu, Huilin Lai, Lindong Lai, Bowen Zhao, Bo Wu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/15/2537
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239699435028480
author Hang Yu
Junbo Lei
Pengfei Lin
Tao Zhang
Hailong Liu
Huilin Lai
Lindong Lai
Bowen Zhao
Bo Wu
author_facet Hang Yu
Junbo Lei
Pengfei Lin
Tao Zhang
Hailong Liu
Huilin Lai
Lindong Lai
Bowen Zhao
Bo Wu
author_sort Hang Yu
collection DOAJ
description The Pacific Decadal Oscillation (PDO), as the dominant mode of decadal sea surface temperature variability in the North Pacific, exhibits both interannual and decadal fluctuations that significantly influence global climate. The complexity associated with PDO changes poses challenges for accurate predictions. This study develops a BiLSTM-WOA-MMD (BWM) model, which integrates a bidirectional long short-term memory network with a whale optimization algorithm (WOA) and multiple modal decomposition (MMD), to forecast PDO at both interannual and decadal time scales. The model successfully predicts monthly/annual average PDO index of up to 15 months/5 years in advance, achieving a correlation coefficient of 0.56/0.55. By utilizing the WOA to effectively optimize hyperparameters, the model enhances the PDO prediction skill compared to existing deep learning PDO prediction models, improving the correlation coefficient from 0.47 to 0.68 at a 6-month lead time. The combination of MMD and WOA further minimizes prediction errors and extends the forecasting effective time to 15 months by capturing essential modes. The BWM model can be employed for future PDO prediction and the predicted PDO will remain in its cool phase in the next year both using the PDO index from NECI and derived from near-time satellite data. This proposed model offers an effective way to advance the prediction skill of climate variability on multiple time scales by utilizing all kinds of data available including satellite data, and provides a large-scale background to monitor marine heatwaves.
format Article
id doaj-art-dd92d7fef8cd430684b1a01c9d5b7706
institution Kabale University
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-dd92d7fef8cd430684b1a01c9d5b77062025-08-20T04:00:51ZengMDPI AGRemote Sensing2072-42922025-07-011715253710.3390/rs17152537Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal DecompositionHang Yu0Junbo Lei1Pengfei Lin2Tao Zhang3Hailong Liu4Huilin Lai5Lindong Lai6Bowen Zhao7Bo Wu8State Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics (IAP), Beijing 100029, ChinaFujian Key Laboratory of Analytical Mathematics and Applications (FJKLAMA) Center for Applied Mathematics, School of Mathematics and Statistics, Fujian Normal University, Fuzhou 350117, ChinaState Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics (IAP), Beijing 100029, ChinaState Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics (IAP), Beijing 100029, ChinaLaoshan Laboratory, Qingdao 266237, ChinaFujian Key Laboratory of Analytical Mathematics and Applications (FJKLAMA) Center for Applied Mathematics, School of Mathematics and Statistics, Fujian Normal University, Fuzhou 350117, ChinaCenter for Philippine Studies, International College of Chinese Studies, Fujian Normal University, Fuzhou 350117, ChinaShanghai Typhoon Institute, China Meteorological Administration, Shanghai 200030, ChinaState Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics (IAP), Beijing 100029, ChinaThe Pacific Decadal Oscillation (PDO), as the dominant mode of decadal sea surface temperature variability in the North Pacific, exhibits both interannual and decadal fluctuations that significantly influence global climate. The complexity associated with PDO changes poses challenges for accurate predictions. This study develops a BiLSTM-WOA-MMD (BWM) model, which integrates a bidirectional long short-term memory network with a whale optimization algorithm (WOA) and multiple modal decomposition (MMD), to forecast PDO at both interannual and decadal time scales. The model successfully predicts monthly/annual average PDO index of up to 15 months/5 years in advance, achieving a correlation coefficient of 0.56/0.55. By utilizing the WOA to effectively optimize hyperparameters, the model enhances the PDO prediction skill compared to existing deep learning PDO prediction models, improving the correlation coefficient from 0.47 to 0.68 at a 6-month lead time. The combination of MMD and WOA further minimizes prediction errors and extends the forecasting effective time to 15 months by capturing essential modes. The BWM model can be employed for future PDO prediction and the predicted PDO will remain in its cool phase in the next year both using the PDO index from NECI and derived from near-time satellite data. This proposed model offers an effective way to advance the prediction skill of climate variability on multiple time scales by utilizing all kinds of data available including satellite data, and provides a large-scale background to monitor marine heatwaves.https://www.mdpi.com/2072-4292/17/15/2537Pacific Decadal Oscillationinterannual-decadal variabilityprediction skilloptimizing algorithmhyperparameter
spellingShingle Hang Yu
Junbo Lei
Pengfei Lin
Tao Zhang
Hailong Liu
Huilin Lai
Lindong Lai
Bowen Zhao
Bo Wu
Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition
Remote Sensing
Pacific Decadal Oscillation
interannual-decadal variability
prediction skill
optimizing algorithm
hyperparameter
title Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition
title_full Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition
title_fullStr Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition
title_full_unstemmed Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition
title_short Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition
title_sort improved pacific decadal oscillation prediction by an optimizing model combined bidirectional long short term memory and multiple modal decomposition
topic Pacific Decadal Oscillation
interannual-decadal variability
prediction skill
optimizing algorithm
hyperparameter
url https://www.mdpi.com/2072-4292/17/15/2537
work_keys_str_mv AT hangyu improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT junbolei improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT pengfeilin improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT taozhang improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT hailongliu improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT huilinlai improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT lindonglai improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT bowenzhao improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition
AT bowu improvedpacificdecadaloscillationpredictionbyanoptimizingmodelcombinedbidirectionallongshorttermmemoryandmultiplemodaldecomposition