The Aardvark Weather System uses thousands of times lower strength computation and works faster than modern systems, researchers say. It can be a success in the industry.
Scientists from the University of Cambridge have created the Aardvark Weather System to predict the AI -Based period, reports The Guardian.
Usually, creating weather forecasting systems requires the years of the work of large teams of researchers, and forecasts themselves are formed using a complex set of stages, each of which takes a lot of work hours on special supercomputer, which requires large expert commands to develop, support and deploy them.
The Aardvark Weather offers a plan for changing the entire process by teaching artificial intelligence with unarmed data from weather stations, satellites, meteorological balloons, ships and aircraft from around the world to make it forecasts.
The system is based on recent studies of Huawei, Google and Microsoft, showing that one of the stages of the weather forecasting process, known as a numeric resolver calculated how the weather changes over time, can be replaced with artificial intelligence to gain faster and most accurate forecasts.
Scientists say that over time, the model can provide accurate eight -day forecasts instead of five -day forecasts today, as well as hyperlocalized forecasts. In addition, it will help to better predict natural phenomena – air quality, ocean dynamics, sea ice and natural disasters, such as hurricanes, forest fires, tornadoes, etc.
Only 10% of all input data demanded by existing systems is sufficient for Aardvark to overcome the national USS forecasting system in certain aspects and even compete with US meteorological service forecasts, researchers said.
Scientists have published research in the journal Nature.
We remind you, earlier it was reported that scientists have developed an ecological method for plastic splitting.
In Ukraine, it eats three times faster than the world
News from CORRESPONDENT.NET On the telegram and whatsapp. Subscribe to our channels https://t.me/KorresPondentNet and WhatsApp
Source: korrespondent
I am Ben Stock, a passionate and experienced digital journalist working in the news industry. At the Buna Times, I write articles covering technology developments and related topics. I strive to provide reliable information that my readers can trust. My research skills are top-notch, as well as my ability to craft engaging stories on timely topics with clarity and accuracy.