Abstract
The El Niño Southern Oscillation (ENSO) occurs in three phases: neutral, warm (El Niño) and cool (La Niña). While classifying El Niño and La Niña is relatively straightforward, El Niño events can be broadly classified into two types: Central Pacific (CP) and Eastern Pacific (EP). Differentiating between CP and EP events is currently dependent on both the method and observational dataset used. In this study, we create a new classification scheme using supervised machine learning trained on 18 observational and reanalysis products. This builds on previous work by identifying classes of events using the temporal evolution of sea surface temperature in multiple regions across the tropical Pacific. By applying this new classifier to seven single model initial-condition large ensembles (SMILEs) we investigate both the internal variability and forced changes in each type of ENSO event, where events identified behave similar to those observed. It is currently debated whether the observed increase in the frequency of CP events after the late 1970s is due to climate change. We found it to be within the range of internal variability in the SMILEs. When considering future changes, we do not project a change in CP frequency or amplitude under a strong warming scenario (RCP8.5/SSP370) and we find model differences in EP El Niño and La Niña frequency and amplitude projections. Finally, we find that models show differences in projected precipitation and SST pattern changes for each event type that do not seem to be linked to the Pacific mean state SST change, although the SST and precipitation changes in individual SMILEs are linked. Our work demonstrates the value of combining machine learning with climate models, and highlights the need to use SMILEs when evaluating ENSO in climate models due to the large spread of results found within a single model due to internal variability alone.
Highlights
Understanding El Niño Southern Oscillation (ENSO) diversity is important due to the differing teleconnections and impacts of 20 different types of events (Capotondi et al, 2020, and refs therein)
Our work demonstrates the value of combining machine learning with climate models, and highlights the need to use single model initial-condition large ensembles (SMILEs) when evaluating ENSO in climate models due to the large spread of results found within a single model due to internal variability alone
We find that the observed frequencies of Eastern Pacific (EP) and Central Pacific (CP) El Niños and La Niña events are within the SMILE spread for all models except CSIRO, which does not realistically capture EP El Niño or La Niña frequency
Summary
Understanding El Niño Southern Oscillation (ENSO) diversity is important due to the differing teleconnections and impacts of 20 different types of events (Capotondi et al, 2020, and refs therein). We use supervised machine learning to build a new ENSO classifier We apply this classifier to climate models to identify events that resemble those found in the real world. We create a new classifier using supervised machine learning combined with 18 observational and reanalysis products This classifier has the advantage that it can learn both the spatial and temporal evolution of different events unlike previous studies that rely on pre-defined metrics and comparing multiple methods and products by 85 hand. Supervised learning algorithms use a labelled dataset (e.g. observations) to create a classifier, which can be applied to unlabelled data (e.g. climate model output). These steps are merged into sections as some steps are performed in unison and/or iterated through
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
