Forecasting El Niño and La Niña Using Spatially and Temporally Structured Predictors and a Convolutional Neural Network

Abstract

El Niño-Southern Oscillation (ENSO) is characterized by large-scale fluctuations of sea surface temperature in the central and eastern tropical Pacific accompanied by changes in the atmospheric circulation. ENSO events are of two main types: El Niño and La Niña. Oceanic Niño index (ONI) determines the five consecutive 3-month running mean of sea surface temperature (SST) anomalies, in the Niño 3.4 region (5°S-5°N, 170°W-120°W). El Niño is a phenomenon in the equatorial Pacific Ocean characterized by a value of greater than 0.5°C for ONI. La Niña is a phenomenon in the equatorial Pacific Ocean characterized by a value of less than-0.5°C for ONI. The lingering of either of these two phenomena could induce severe droughts, while either of them following the other could cause massive floods. In both cases, deaths and substantial pecuniary loss is unavoidable, making their forecast of great significance. This study takes over the challenge of forecasting these two phenomena with one year lead time which has proven difficult in the literature. This research's contribution is restructuring ENSO events' predictors, including SST, sea level pressure, surface wind speed, and wind stress in a spatially and temporally meaningful way and designing a convolutional neural network (CNN) that takes advantage of this structure to forecast ENSO events of different types (i.e. Central Pacific and Eastern Pacific) in the next year. Not only a high precision in forecasts was achieved, but also it was shown that the proposed model has the potential to achieve higher recalls if a larger number of samples from the positive class would become available.

Non-linear modes of global sea surface temperature variability and their relationships with global precipitation and temperature

“…By regressing the time series of figure 3(a) onto global SST, La Niña-like patterns are derived, for the (positive phase of) node 3 (figure 5). The positive trends in node 3 suggest that the western Pacific is warming faster compared to the eastern Pacific during JFM (consistent with the findings of [23]). Trend analysis on global SST data also supports the significant warming over some western parts of the tropical Pacific during JFM (figure S3, top panel).…”

“…For instance, [21] found that the application of a neural network to create a nonlinear PCA approach was successful in extracting periodic modes in the tropical Pacific. References [22][23][24][25] used convolutional neural networks to forecast the time amplitude and type of ENSO. Labe and Barnes [26] applied ANN to predict the onset of slowdowns in decadal warming trends of global mean surface temperature.…”