top of page

El Niño, La Niña, Artificial Intelligence (AI) and extreme weather forecast

El Niño and the Southern Oscillation, also known as ENSO is a periodic fluctuation in sea surface temperature and the air pressure of the overlying atmosphere across the equatorial Pacific Ocean.

According to the 13 July ENSO diagnostic discussion by the US National Oceanic and Atmospheric Administration (NOAA) there is a greater than 90% chance that El Niño will continue through the Northern Hemisphere winter. Additional perspectives and analysis are regularly available in an ENSO blog.

Considering the impact in the Northern Hemisphere, recall this post from July 2022 "Jet Stream: impact of global warming at the highest altitudes of the Earth's atmosphere".

Historically speaking, El Niño and La Niña events, that typically recur every 2-7 years, tend to develop during the period Apr-Jun, reaching maximum strength during Oct-Feb, and persisting for 9-12 months, occasionally for up to 2 years.

What about the potential for artificial intelligence (AI) to make faster and more accurate weather forecasts? Nature published about that last July 5:

  • "Skilful nowcasting of extreme precipitation with NowcastNet" (authors from Tsinghua University China, Berkeley USA, others). The model combines deep-learning methods with physics equations to give local predictions of heavy rain up to three hours in advance. According to meteorologists, better in most cases than leading ‘nowcasting’ systems.

  • "Accurate medium-range global weather forecasting with 3D neural networks" (authors from Huawei Cloud, China). About the Pangu-Weather program, that can forecast weather up to seven days in advance. Trained on 39 years of weather data, it can retrospectively predict global temperature, pressure and wind speed a week in advance. It’s 10,000 times faster and no less accurate than making predictions on the basis of an understanding of physics.

Conventional weather-prediction models are based on physical equations that are implemented using numerical models. Generative AI weather models work differently: instead of making predictions on the basis of an understanding of physics, they forecast weather patterns that are statistically plausible given historical measurements.

AI could help make more complex, better and cheaper weather predictions. And given the changing climate human oversight and curation will be key. By the way, wildfires and smoke dispersion can obvioulsy also be added.

And you? Do you know about other recent studies about the usage of AI for climate and meteorology? Share as a comment.


Rated 0 out of 5 stars.
No ratings yet

Add a rating


“Nothing in life is to be feared, it is only to be understood. Now is the time to understand more, so that we may fear less.”

“I am among those who think that science has great beauty”

Madame Marie Curie (1867 - 1934) Chemist & physicist. French, born Polish.

bottom of page