Artificial intelligence could soon be helping to deliver faster and more accurate weather forecasts, according to meteorologists in Germany behind new research into the use of AI in forecasting models.
Researchers from Germany's meteorological service Deutscher Wetterdienst (DWD) say that, in a world first, they relied exclusively on AI to successfully feed data from weather observation into forecasting models and analysis processes.
"Offering the potential to speed up and improve analyses and forecasts dramatically," this development is set to benefit anyone looking at weather forecasts, the DWD researchers say.
Professionals who rely on climate analyses, such as flood protection specialists or people in the energy sector, are also expected to appreciate the increased forecast precision and speed.
However the potential impact also appears to be largest for meteorologists themselves if AI can indeed replace traditional methods, reduce computing costs and speed up processes.
The arduous process of data assimilation - the integration of observation data into computerised weather models - has been a cornerstone of weather forecasting for decades, researchers say. However AI now has the potential to drastically cut this cost factor.
"This technology is a crucial building block for the current revolution in weather forecasting through AI," said Jan Keller, Head of Data Assimilation at DWD and co-author of the research.
Published in June, the study has not yet been peer-reviewed, but DWD researchers are confident this world first for weather observation technology now paves the way for fully data-driven forecasting systems in the future.