English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. The El Niño–Southern Oscillation (ENSO) is an extremely complicated ocean–atmospherecoupling event, the development and decay of which are usually modulated bythe energy interactions between multiple physical variables. In this paper,we design a multivariate air–sea coupler (ASC) based on the graph usingfeatures of multiple physical variables. On the basis of this coupler, anENSO deep learning forecast model (named ENSO-ASC) is proposed, whosestructure is adapted to the characteristics of the ENSO dynamics, includingthe encoder and decoder for capturing and restoring the multi-scale spatial–temporalcorrelations, and two attention weights for grasping the different air–seacoupling strengths on different start calendar months and varied effects ofphysical variables in ENSO amplitudes. In addition, two datasets modulatedto the same resolutions are used to train the model. We firstly tune themodel performance to optimal and compare it with the other state-of-the-artENSO deep learning forecast models. Then, we evaluate the ENSO forecastskill from the contributions of different predictors, the effective leadtime with different start calendar months, and the forecast spatialuncertainties, to further analyze the underlying ENSO mechanisms. Finally, wemake ENSO predictions over the validation period from 2014 to 2020.Experiment results demonstrate that ENSO-ASC outperforms the other models.Sea surface temperature (SST) and zonal wind are two crucial predictors. Thecorrelation skill of the Niño 3.4 index is over 0.78, 0.65, and 0.5 within the leadtime of 6, 12, and 18 months respectively. From two heat map analyses, we also discover thecommon challenges in ENSO predictability, such as the forecasting skillsdeclining faster when making forecasts through June–July–August and theforecast errors being more likely to show up in the western and central tropicalPacific Ocean in longer-term forecasts. ENSO-ASC can simulate ENSO withdifferent strengths, and the forecasted SST and wind patterns reflect anobvious Bjerknes positive feedback mechanism. These results indicate theeffectiveness and superiority of our model with the multivariate air–seacoupler in predicting ENSO and analyzing the underlyingdynamic mechanisms in a sophisticated way.

ENSO-ASC 1.0.0: ENSO deep learning forecast model with a multivariate air–sea coupler