New AI tool tracks early signs of hurricane formation
Peer-Reviewed Publication
Updates every hour. Last Updated: 16-Nov-2025 22:11 ET (17-Nov-2025 03:11 GMT/UTC)
A research team led by a Ph.D. student at the University of Miami Rosenstiel School of Marine, Atmospheric, and Earth Science has developed a new artificial intelligence (AI) tool that can automatically identify and track tropical easterly waves (TEWs)—clusters of clouds and wind that often develop into hurricanes—and separate them from two major tropical wind patterns: the Intertropical Convergence Zone (ITCZ) and the monsoon trough (MT).
Kyoto, Japan -- The size of our universe and the bodies within it is incomprehensible for us lowly humans. The sun has a mass that is more than 330,000 that of our Earth, and yet there are stars in the universe that completely dwarf our sun.
Stars with masses more than eight times that of the sun are considered high mass stars. These form rapidly in a process that gives off stellar wind and radiation, which could not result in stars of such high mass without somehow overcoming this loss of mass, or feedback. Something is feeding these stars, but how exactly they can accumulate so much mass so quickly has remained a mystery.
Observations of enormous disk-like structures that form around a star -- accretion disks -- had been proposed as the chief way of rapidly feeding young stars. However, a team of researchers from several institutions including Kyoto University and the University of Tokyo, has discovered another possibility.