Researchers at the University of California, Davis are designing machine-learning systems to enable supercomputers to identify large-scale atmospheric structures, such as hurricanes and atmospheric rivers, in climate data.
The researchers conduct their experiments on the U.S. Department of Energy's National Energy Research Scientific Computing Center's CORI supercomputer.
Climate and weather systems change over time, so the researchers must find patterns not only in space but over time. They are developing algorithms that enable computers to identify structures in data without knowing what they are in advance.
A supercomputer can use pattern discovery to learn how to identify hurricanes or other features in climate and weather data, and it could be able to identify new kinds of structures that are too complex for humans to perceive.
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found