Multi-task machine learning improves multi-seasonal prediction of the Indian Ocean Dipole

As one of the most predominant interannual variabilities, the Indian Ocean Dipole (IOD) exerts great socio-economic impacts globally, especially on Asia, Africa, and Australia. While enormous efforts have been made since its discovery to improve both climate models and statistical methods for better...

Full description

Saved in:
Bibliographic Details
Published inNature communications Vol. 13; no. 1; pp. 7681 - 9
Main Authors Ling, Fenghua, Luo, Jing-Jia, Li, Yue, Tang, Tao, Bai, Lei, Ouyang, Wanli, Yamagata, Toshio
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 12.12.2022
Nature Publishing Group
Nature Portfolio
Subjects
704/106/35
704/106/829
Africa
Asia
Australia
Climate models
Deep learning
Dipoles
Dynamic models
Economic impact
El Nino
Humanities and Social Sciences
Indian Ocean
Laboratories
Machine Learning
Mathematical models
multidisciplinary
Predictions
Science
Science (multidisciplinary)
Skills
Statistical analysis
Statistical methods
Wind
Indian Ocean
Australia
Asia
Africa
Online AccessGet full text

Cover

More Information
Summary:As one of the most predominant interannual variabilities, the Indian Ocean Dipole (IOD) exerts great socio-economic impacts globally, especially on Asia, Africa, and Australia. While enormous efforts have been made since its discovery to improve both climate models and statistical methods for better prediction, current skills in IOD predictions are mostly limited up to three months ahead. Here, we challenge this long-standing problem using a multi-task deep learning model that we name MTL-NET. Hindcasts of the IOD events during the past four decades indicate that the MTL-NET can predict the IOD well up to 7-month ahead, outperforming most of world-class dynamical models used for comparison in this study. Moreover, the MTL-NET can help assess the importance of different predictors and correctly capture the nonlinear relationships between the IOD and predictors. Given its merits, the MTL-NET is demonstrated to be an efficient model for improved IOD prediction. A multi-task learning model is proposed to improve seasonal-to-annual prediction of the Indian Ocean Dipole (IOD). This model captures the inter-basin interactions between ENSO and IOD and distinctive precursors of positive and negative IOD events.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-022-35412-0