El Ni\~no Modoki thus far can be mostly predicted more than 10 years ahead of time

TL;DR

This study demonstrates that El Niño Modoki events can be largely predicted over a decade in advance by analyzing long-term solar activity data and applying information flow-based causal deep learning techniques.

Contribution

The paper introduces a novel approach using information flow causality and deep learning to predict El Niño Modoki events more than 10 years ahead, based on solar activity data.

Findings

El Niño Modoki can be predicted over 10 years in advance.

Information flow from solar activity influences El Niño Modoki predictability.

Causal deep learning accurately reproduces events 12 years ahead.

Abstract

The 2014-2015 "Monster"/"Super" El Ni\~no failed to be predicted one year earlier due to the growing importance of a new type of El Ni\~no, El Ni\~no Modoki, which reportedly has much lower forecast skill with the classical models. In this study, we show that, so far as of today, this new El Ni\~no actually can be mostly predicted at a lead time of more than 10 years. This is achieved through tracing the predictability source with an information flow-based causality analysis, which is rigorously established from first principles in the past decade. We show that the information flowing from the solar activity 45 years ago to the sea surface temperature results in a causal structure resembling the El Ni\~no Modoki mode. Based on this, a multidimensional system is constructed out of the sunspot number series with time delays of 22-50 years. The first 25 principal components are then taken as the predictors to fulfill the prediction, which through information flow-based causal deep learning reproduces rather accurately the events 12 years in advance.