Deep learning identification of SST teleconnections driving early-winter North Atlantic climate

Seasonal predictability over the North Atlantic-European (NAE) sector is strongly modulated by the background climate state, particularly in early winter. In this season, different El Niño-Southern Oscillation (ENSO) teleconnections have been reported before and after the 1990s. However, these studies rely on linear analysis, and the reasons for this lack of stationarity and its implications for seasonal forecasting have not yet been fully assessed. Here, we evaluate the non-stationarity of early-winter ENSO teleconnections over the NAE using a non-linear framework, the Neural Network forecast application (NN4CAST). The NN4CAST model predicts November-December mean sea-level pressure anomalies from October sea surface temperature (SST) anomalies. The neural network achieves skill comparable to the ECMWF seasonal forecasting system (SEAS5), and even exceeds it in certain regions like the NAE, despite relying only on October SST predictors. The model skilfully predicts the dominant NAE atmospheric variability modes, with a predictability that is strongly period-dependent. In particular, significant skill is found over the North Atlantic Oscillation centres of action during 1970–1995, especially for the Iceland region, whereas for the East Atlantic pattern, the improvement comes in recent decades (1996–2019). This teleconnection shift is mainly associated with Pacific SST anomalies, with recent decades marked by an intensified Southeast Asian Rossby wave source and a southward displacement of the North Atlantic jet stream. Our results demonstrate that explainable artificial intelligence can identify state-dependent SST precursors of NAE predictability, bridging data-driven and mechanistic understanding of climate teleconnections.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-14
DOI
https://doi.org/10.1038/s41598-026-78245-3
Primary Topic
Climate variability and models
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Deep learning identification of SST teleconnections driving early-winter North Atlantic climate

Belén Rodríguez‐Fonseca, Magdalena Balmaseda, Irene Polo, Marta Martín‐Rey et al.
4 links
Scientific Reports
Climate variability and models
article

Deep learning identification of SST teleconnections driving early-winter North Atlantic climate

Belén Rodríguez‐Fonseca, Magdalena Balmaseda, Irene Polo, Marta Martín‐Rey, Víctor Galván Fraile
article en

Abstract

Seasonal predictability over the North Atlantic-European (NAE) sector is strongly modulated by the background climate state, particularly in early winter. In this season, different El Niño-Southern Oscillation (ENSO) teleconnections have been reported before and after the 1990s. However, these studies rely on linear analysis, and the reasons for this lack of stationarity and its implications for seasonal forecasting have not yet been fully assessed. Here, we evaluate the non-stationarity of early-winter ENSO teleconnections over the NAE using a non-linear framework, the Neural Network forecast application (NN4CAST). The NN4CAST model predicts November-December mean sea-level pressure anomalies from October sea surface temperature (SST) anomalies. The neural network achieves skill comparable to the ECMWF seasonal forecasting system (SEAS5), and even exceeds it in certain regions like the NAE, despite relying only on October SST predictors. The model skilfully predicts the dominant NAE atmospheric variability modes, with a predictability that is strongly period-dependent. In particular, significant skill is found over the North Atlantic Oscillation centres of action during 1970–1995, especially for the Iceland region, whereas for the East Atlantic pattern, the improvement comes in recent decades (1996–2019). This teleconnection shift is mainly associated with Pacific SST anomalies, with recent decades marked by an intensified Southeast Asian Rossby wave source and a southward displacement of the North Atlantic jet stream. Our results demonstrate that explainable artificial intelligence can identify state-dependent SST precursors of NAE predictability, bridging data-driven and mechanistic understanding of climate teleconnections.

Scientific Reports
Universidad Complutense de Madrid (ES), Consejo Superior de Investigaciones Científicas (ES), European Centre for Medium-Range Weather Forecasts (GB), Instituto de Geociencias (ES), University of Reading (GB)
Climate action
Climate variability and models
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon