New El Niño events can be predicted 18 months out

MADRID (EUROPA PRESS) – A new tool developed at the University of Hawaii will allow forecasting El Niño-Southern Oscillation (ENSO) climate events up to 18 months in advance.

The findings, which combine knowledge of ocean and atmospheric physics with predictive accuracy, were published in Nature.

The El Niño-Southern Oscillation is a climate pattern that consists of the oscillation of meteorological parameters in the equatorial Pacific every few years. It is one of the most important sources of annual climate variability worldwide.

“We have developed a new conceptual model, the so-called extended nonlinear recharge oscillator (XRO) model, which significantly improves the prediction capability of ENSO events more than a year in advance, better than global climate models and comparable to artificial intelligence forecasts. [IA] “We are more skilled,” Sen Zhao, lead author of the study and an assistant researcher in the Department of Atmospheric Sciences at SOEST (School of Ocean and Earth Science and Technology), said in a statement. “Our model effectively incorporates the fundamental physics of ENSO and the interactions of ENSO with other climate patterns in the global oceans that vary from season to season.”

Scientists have been working for decades to improve ENSO predictions given its global environmental and socioeconomic impacts. Traditional operational forecast models have struggled to successfully predict ENSO with lead times greater than one year.

LOW CONFIDENCE IN AI MODELS

Recent advances in AI have pushed these boundaries, achieving accurate predictions up to 16 to 18 months in advance. However, the “black box” nature of AI models has prevented attribution of this accuracy to specific physical processes. Failing to account for the source of predictability in AI models results in low confidence that these predictions will be successful for future events as the Earth continues to warm.

“Unlike the ‘black box’ nature of AI models, our XRO model provides a transparent view of the mechanisms of the equatorial Pacific and its interactions with other climate patterns outside the tropical Pacific,” said Fei-Fei Jin, corresponding author and professor of atmospheric sciences at SOEST. “For the first time, we can robustly quantify its impact on ENSO predictability, thereby deepening our understanding of ENSO physics and its sources of predictability.”

“Our findings also identify shortcomings in the latest generation of climate models that lead to their failure to accurately predict ENSO,” said Malte Stuecker, an adjunct professor of oceanography at SOEST and co-author of the study. “To improve ENSO predictions, climate models must correctly capture the key physics of ENSO and, in addition, several composite aspects of other climate patterns in the global oceans.”

“Different sources of predictability lead to different evolutions of ENSO events,” said Philip Thompson, an associate professor of oceanography at SOEST and co-author of the study. “We can now provide skillful, long-term predictions of this ‘ENSO diversity,’ which is critical as different types of ENSO have very different impacts on global climate and individual communities.”