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 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 non-linear relationships between the IOD and predictors. Given its merits, the MTLNET is demonstrated to be an efficient model for improved IOD prediction.

Automated summary

This study challenges the long-standing problem of IOD prediction and proposes a multi-task deep learning model called MTL-NET. The model outperforms world-class dynamical models in predicting IOD and correctly captures the non-linear relationships between IOD and predictors.