A breakthrough in forecasting using machine-learning means the unpredictable nature of the El Niño global climate phenomenon on weather patterns, ecosystems, communities and their livelihoods may be a thing of the past.

Warming from El Niño has a significant impact on the tropical Atlantic region and, say researchers at Bjerknes Centre for Climate Research in Bergen, Norway, this can lead to extensive effects on local marine ecosystems and some African countries' climates. However, no one has been able to predict warm events in this region until now.

“We are extremely excited because it was the first time we could actually produce some predictions useful for communities building traditional models, and achieving that goal that we had two years before,” says Marie-Lou Bachèlery, who was working at the Geophysical Institute at the University of Bergen and is now based at the Euro-Mediterranean Center on Climate Change in Italy.

The tropical Atlantic Ocean is situated between the Brazilian coast to the west and the West African coast to the east. The Central Atlantic Niño is characterised by warm sea surface temperatures concentrated in the central equatorial Atlantic, while the eastern Atlantic Niño features warming in the eastern equatorial Atlantic, near the West African coast.

As a significant component of climate systems, variations in the ocean influence local weather patterns. These changes also impact marine ecosystems and the livelihoods of people who depend on the ocean's fish resources.

The South Atlantic is one of the regions that has quite strong warming in the ocean, and this is problematic for facilities like commercial fisheries and makes it particularly important to predict extreme events.

“My idea was to do predictions of those events using climate models," says Bachèlery. "The project got funded through the Marie Skłodowska-Curie Actions and after a year and a half of work, we realised that it did not work and that we were kind of in a deadlock situation.”

Climate models often struggle to predict warm events in the tropical Atlantic due to their low resolution. These models fail to accurately represent upwelling dynamics, where wind-driven processes bring deeper, cooler water to the surface.

“With innovative techniques such as machine learning, I started to think of the possibilities," Bachèlery explains, "and that I knew the region very well. I knew exactly what I needed to put in to predict those events.”

Exciting result

Professor Noel Keenlyside was Bachèlery’s supervisor and has worked with prediction in the Atlantic region over decades.

“For the first time it is actually possible to predict these events and overcome the issue of model errors by using a different approach," he says. "Many people have been trying to predict that area for a few decades, that's why Marie Lou’s results are exciting.

“When extreme events occur, managers may limit the fishing in this region, to reduce effects of the additional pressure from the environment.”

Bachèlery says that when they first got the results, she did not believe what she saw.

“I rechecked what felt like a billion times to make sure that we were not over predicting, because that is a common feature in machine learning. Even if the system is not necessarily for their region, the whole technique can be applied for any other system, and I think people are really excited about that.”

The research team is now working to make these forecasts available through a dashboard.

“We are in dialogue with forecast users from National Institute for Fisheries in Angola (INIP) to further improve and refine the information to their needs. It is particularly pleasing to see that basic research is becoming societally relevant,” Professor Keenlyside says.

The study was carried out under the TRIATLAS-project with support from the Bjerknes Climate Prediction Unit and funding from the Trond Mohn Research Foundation. The paper appears in Science Advances.