Explained predictions of strong eastern Pacific El Niño events using deep learning.

Global and regional impacts of El Niño-Southern Oscillation (ENSO) are sensitive to the details of the pattern of anomalous ocean warming and cooling, such as the contrasts between the eastern and central Pacific. However, skillful prediction of such ENSO diversity remains a challenge even a few months in advance. Here, we present an experimental forecast with a deep learning model (IGP-UHM AI model v1.0) for the E (eastern Pacific) and C (central Pacific) ENSO diversity indices, specialized on the onset of strong eastern Pacific El Niño events by including a classification output. We find that higher ENSO nonlinearity is associated with better skill, with potential implications for ENSO predictability in a warming climate. When initialized in May 2023, our model predicts the persistence of El Niño conditions in the eastern Pacific into 2024, but with decreasing strength, similar to 2015-2016 but much weaker than 1997-1998. In contrast to the more typical El Niño development in 1997 and 2015, in addition to the ongoing eastern Pacific warming, an eXplainable Artificial Intelligence analysis for 2023 identifies weak warm surface, increased sea level and westerly wind anomalies in the western Pacific as precursors, countered by warm surface and southerly wind anomalies in the northern Atlantic.

Holocene hydroclimatic variability in the tropical Pacific explained by changing ENSO diversity.

Understanding El Niño-Southern Oscillation (ENSO) response to past climate forcings is hindered by conflicting paleoclimate evidence. Records from the eastern Pacific show an intensification of ENSO variability from early to late Holocene, while records from the central Pacific show highly variable ENSO throughout the Holocene without an obvious relation to insolation forcing, which is the main climate driver during this interval. Here, we show via climate model simulations that conflicting Holocene records can be reconciled by considering changes in the relative frequency of the three preferred spatial patterns in which El Niño events occur (Eastern Pacific, Central Pacific, and Coastal) and in the strength of their hydroclimatic impacts. The relationship between ENSO diversity and variance is not only crucial for interpreting paleo-ENSO records and understanding ENSO response to external forcings but can also be used across climate model simulations to help evaluate the realism of ENSO projections in a changing climate.

ITCZ shift and extratropical teleconnections drive ENSO response to volcanic eruptions.

The mechanisms through which volcanic eruptions affect the El Niño-Southern Oscillation (ENSO) state are still controversial. Previous studies have invoked direct radiative forcing, an ocean dynamical thermostat (ODT) mechanism, and shifts of the Intertropical Convergence Zone (ITCZ), among others, to explain the ENSO response to tropical eruptions. Here, these mechanisms are tested using ensemble simulations with an Earth system model in which volcanic aerosols from a Tambora-like eruption are confined either in the Northern or the Southern Hemisphere. We show that the primary drivers of the ENSO response are the shifts of the ITCZ together with extratropical circulation changes, which affect the tropics; the ODT mechanism does not operate in our simulations. Our study highlights the importance of initial conditions in the ENSO response to tropical volcanic eruptions and provides explanations for the predominance of posteruption El Niño events and for the occasional posteruption La Niña in observations and reconstructions.