Abstract
Abstract. The El Niño–Southern Oscillation (ENSO) is an extremely complicated ocean–atmosphere coupling event, the development and decay of which are usually modulated by the energy interactions between multiple physical variables. In this paper, we design a multivariate air–sea coupler (ASC) based on the graph using features of multiple physical variables. On the basis of this coupler, an ENSO deep learning forecast model (named ENSO-ASC) is proposed, whose structure is adapted to the characteristics of the ENSO dynamics, including the encoder and decoder for capturing and restoring the multi-scale spatial–temporal correlations, and two attention weights for grasping the different air–sea coupling strengths on different start calendar months and varied effects of physical variables in ENSO amplitudes. In addition, two datasets modulated to the same resolutions are used to train the model. We firstly tune the model performance to optimal and compare it with the other state-of-the-art ENSO deep learning forecast models. Then, we evaluate the ENSO forecast skill from the contributions of different predictors, the effective lead time with different start calendar months, and the forecast spatial uncertainties, to further analyze the underlying ENSO mechanisms. Finally, we make 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. The correlation skill of the Niño 3.4 index is over 0.78, 0.65, and 0.5 within the lead time of 6, 12, and 18 months respectively. From two heat map analyses, we also discover the common challenges in ENSO predictability, such as the forecasting skills declining faster when making forecasts through June–July–August and the forecast errors being more likely to show up in the western and central tropical Pacific Ocean in longer-term forecasts. ENSO-ASC can simulate ENSO with different strengths, and the forecasted SST and wind patterns reflect an obvious Bjerknes positive feedback mechanism. These results indicate the effectiveness and superiority of our model with the multivariate air–sea coupler in predicting ENSO and analyzing the underlying dynamic mechanisms in a sophisticated way.
Highlights
The El Niño–Southern Oscillation (ENSO) can induce global climate extremes and ecosystem impacts (Zhang et al, 2016), which are the dominant sources of interannual climate changes
We evaluate the ENSO-ASC from three aspects: firstly, we evaluate the model performance from the perspective of model structure, including the input sequence length, the benefits of transfer learning, multivariate air–sea coupler, and the attention weights, and tune the model structure to optimal
The results indicate that using a graph to simulate multivariate interactions is a more reasonable approach, which can learn more ENSO-related dynamical interactions and underlying physical processes than other formalizations
Summary
The El Niño–Southern Oscillation (ENSO) can induce global climate extremes and ecosystem impacts (Zhang et al, 2016), which are the dominant sources of interannual climate changes. The Niño 3 (Niño 4) index is the common indicator for ENSO research to measure the cold tongue (warm pool) variabilities, which is the averaged SST anomalies covering the Niño 3 (Niño 4) region (see Fig. 1). Besides these two indicators, the ONI (oceanic Niño index, 3-month running mean of SST anomalies in the Niño 3.4 region) has become the de facto standard to identify the occurrence of El Niño and La Niña events: if the ONIs of 5 consecutive months are over 0.5 ◦C (below −0.5 ◦C), El Niño (La Niña) occurs. It is worth noting that the model biases of traditional approach have always been a problem for accurate ENSO predictions (Xue et al, 2013)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
