Analyzing El Niño–Southern Oscillation Predictability Using Long‐Short‐Term‐Memory Models

Abstract

El Niño–Southern Oscillation (ENSO) can have global impacts, affecting daily temperature and precipitation, and extreme weather, such as hurricanes and tornadoes. Because of its importance, scientists strive to understand the processes that govern ENSO and develop models to predict its evolution and changes in variability. Here long‐short‐term‐memory models (LSTMs) were compared to linear regression models (LR) to explore the benefits of simple, deep neural networks in predicting ENSO, in addition to quantifying the relative importance of the sources of ENSO's predictability. The models use central Pacific sea surface temperatures (SST), equatorial Pacific warm water volumes, and western Pacific zonal winds as predictors, individually and in combinations, on monthly and daily resolutions, from 1‐ to 11‐month leads. By using these predictors, many characteristic time scales are encompassed—from days‐to‐weeks in the atmosphere, to months‐to‐seasons in the coupled system, and interseasonal‐to‐interannual in the subsurface ocean. Results show, with monthly input, predictions from LSTM were like predictions from LR. However, with daily SST at longer leads, LSTM exhibited some advantage over LR in terms of the correlation coefficient. This suggests that daily SST may contain some nonlinear element that improves LSTM predictability compared to LR. In addition, this suggests that more information, such as gridded data and additional variables, would likely improve predictability using LSTM, but results would be more difficult to interpret. Overall, LSTM may be appealing because once the computationally expensive training of LSTM is complete, the predictions employing the trained model can be relatively cheap to perform thereafter.

Deep Learning Data-Intelligence Model Based on Adjusted Forecasting Window Scale: Application in Daily Streamflow Simulation

“…In 2019, Huang et al published a study in which LSTM was combined with the E1 Nino-Southern Oscillation index. In comparison with the linear regression model, LSTM used the nonlinear evolution of the data better and demonstrated its statistical advantage in long leads [47].…”

A study of the effects of westerly wind bursts on ENSO based on CESM

“…Although some climate models see WWBs as stochastic processes that do not depend on the ENSO cycle (Kessler et al 1995;Moore and Kleeman 1999), many studies based on observations have found that the occurrence of WWBs is highly related to the ocean state (Harrison and Vecchi 1997;Vecchi and Harrison 2000;Batstone and Hendon 2005;Eisenman et al 2005;Tziperman and Yu 2007). Indeed, WWBs preferentially occur prior to and during the development of El Niño events and tend to migrate eastward with the expansion of the Western Pacific warm pool (McPhaden 1999;Yu et al 2003;Huang et al 2019). A widely accepted hypothesis is that the occurrence of WWBs is semi-stochastic, that is, WWBs should be partially modulated by the background SST and partially determined by stochastic processes (Gebbie et al 2007).…”

Reconstructing Ocean Heat Content for Revisiting Global Ocean Warming from Remote Sensing Perspectives

“…However, LSTM uses gating algorithms, i.e., an input gate, forget gate, and output gate, which can resolve the vanishing and exploding gradient problem of RNN by controlling long-distance dependence and selectively forgetting data to prevent information overload. To date, LSTM has achieved remarkable results in translation, recognition, video, and marine applications (e.g., predicting El Niño changes) [49].…”