Fully AI driven weather prediction system could start revolution in forecasting
Peer-Reviewed Publication
Updates every hour. Last Updated: 20-Jun-2025 08:10 ET (20-Jun-2025 12:10 GMT/UTC)
A new AI weather prediction system, Aardvark Weather, can deliver accurate forecasts tens of times faster and using thousands of times less computing power than current AI and physics-based forecasting systems, according to research published today (Thursday 20 March) in Nature.
Summary:
A new study reveals that encapsulated heating methods, an often-used heat simulation method, significantly increase heart rates and cardiac strain compared to natural heat exposure like those experienced during hot weathers.
Understanding how extreme heat impacts heart function is crucial for developing effective strategies to protect vulnerable groups, especially as global temperatures continue to rise.
Kyushu University researchers have developed a new model that can predict sunlight patterns under different weather conditions. By categorizing sunlight into five groups based on intensity and quality, the model reveals that cloudy days can help plant growth by scattering light more evenly to lower leaves. The research can potentially help farmers optimize greenhouse conditions and planting schedules throughout the season to improve agricultural productivity, and enhance our understanding of how climate change affects photosynthesis.
In response to the UN declaration of 2025 as the International Year of Glaciers’ Preservation and UN Decade of Action for Cryospheric Research (2025–2034), an international team of glacier scientists has formed the Glacier Stewardship Program.