Two observers watch the Pacific Ocean. One studies thermal maps of the surface, the other listens to the rhythm of temperature and heat storage in the water column. On their own, each notices only part of the picture, but together they can catch the approach of El Niño months before the warm current changes weather across the planet.
El Niño, the warm phase of a climate oscillation in the equatorial Pacific, brings droughts to Australia and floods to Peru, affecting fisheries and crops. An accurate forecast six months ahead gives time to prepare. Researchers at Vietnam National University built a model called ConvLSTM-XT, which combines the two observers in a single architecture. A convolutional neural network (CNN) processes thermal maps of sea surface temperature (SST), while long short-term memory (LSTM) analyzes time series of temperature and ocean heat content (OHC). The data span January 2000 to September 2023, with the region limited to the Niño 3.4 zone (5°S–5°N, 120°–170°W).
Forecast accuracy reached 90.57% for configurations where at least one of the five quarters used real observations and the rest used predictions. When all five quarters were predicted without relying on observations, accuracy dropped to 83.02%. Qualitative analysis of thermal maps from March to September 2023 showed that the model captured the transition from cold to warm anomalies typical of El Niño development, although it did not always exceed the 0.5°C threshold in all five periods. By joining forces, the two observers already provide several months of lead time in the face of a climate anomaly.
The 1982–1983 El Niño nearly wiped out the Peruvian anchovy population, which supported the world's largest fishery. Catches plummeted from 12 million tons to less than 1 million tons.
In Kim Stanley Robinson's novel 'Forty Signs of Rain', climate models play a key role in predicting extreme weather events, and scientists struggle to make their forecasts heard by policymakers. Developing more accurate El Niño models echoes this theme: the earlier and more precise the warning, the better the chances for adaptation.