The newly launched artificial intelligence-powered model can outperform conventional weather forecasting systems for up to 15 days ahead, the European Centre for Medium-Range Weather Forecasts said on Tuesday.
—
Europe’s new artificial intelligence-powered weather forecasting model became operational on Tuesday, promising to significantly improve meteorological and extreme weather predictions globally.
The Artificial Intelligence Forecasting System (AIFS) is the first fully operational weather prediction open model using machine learning technology, and will run side by side with its traditional physics-based Integrated Forecasting System (IFS), the European Centre for Medium-Range Weather Forecasts (ECMWF) said in a press release on Tuesday. The independent agency, which is headquartered in the UK, tested the model over the past 18 months and found that it outperformed conventional models’ predictions by up to 20%.
But aside from higher accuracy rates, including in predicting the track of tropical cyclones 12 hours further ahead, the system will also require some 1,000 times less energy and will be much faster at making a forecast.
Aside from tracking wind and temperature and providing details on precipitation types from snow to rain, it will also provide key data to maximize renewable energy operations, such as predictions of surface solar radiation levels or wind speeds at turbine levels.
ECMWF’s Director-General Florence Rabier called the new system a “milestone” that will “transform weather science and predictions” and make global predictions freely available to everyone at any time.
“It is not only us who are innovating as it is important to remember that, with ECMWF, 35 nations are working together to advance weather science to improve global predictions. This is to help national meteorological agencies in their work to contribute to a safe and thriving society,” Rabier said.
Enhanced Prediction System
AIFS’ forecast is based on the same combination of data its traditional physics-based counterpart, the IFS, feeds on. This data comes from satellites, planes, boats, sea buoys, and other Earth-based measurement stations, according to the ECMWF press release.
What distinguishes the two models, however, is that the new machine learning model assesses how these initial conditions will influence future weather based on its knowledge of how the weather has evolved in the past. IFS calculations, in contrast, rely on the laws of physics, which it integrates in its computer code.
“We see the AIFS and IFS as complementary, and part of providing a range of products to our user community, who decide what best suits their needs,” said ECMWF’s Director of Forecasts and Services, Florian Pappenberger.
Europe’s weather forecasts are currently reliable up to six to seven days ahead for precipitation and wind, and up to 14 or 15 days ahead for temperature, Pappenberger told the Financial Times.
AI and Climate Change
While the environmental impact of AI, mostly coming from its immense energy usage, is cause for genuine concern, its application in fields such as weather, biodiversity, and energy monitoring make the controversial technology a huge player in the fight against climate change.
Featured image: NASA Goddard Space Flight Center via Wikimedia Commons.
More on the topic: 7 Data-Based & Artificial Intelligence Projects To Help Fight Climate Change
This story is funded by readers like you
Our non-profit newsroom provides climate coverage free of charge and advertising. Your one-off or monthly donations play a crucial role in supporting our operations, expanding our reach, and maintaining our editorial independence.
About EO | Mission Statement | Impact & Reach | Write for us
