SPACE — Artificial intelligence (AI) will soon help astronomers search for evidence of supernovae or stellar explosions. A new fully automated machine learning algorithm has successfully detected, identified and classified its first supernova.
This program, called Bright Transient Survey Bot (BTSbot), will be able to speed up the process of supernova analysis and classification. According to the BTSbot team, over the past six years alone, human astronomers have spent approximately 2,200 hours visually inspecting and classifying supernova candidates. With AI, these tasks can be done faster,
So far, supernovae have been discovered by combining the work of humans and computers working together. However, BTSbot can eliminate the human role from this task.
“For the first time, a series of robots and AI algorithms have observed, then identified, then communicated with other telescopes to finally confirm the discovery of a supernova,” team leader Adam Miller, a physics professor at Northwestern University in Illinois, was quoted as saying. Space.
Many supernovae occur when dying stars run out of fuel for nuclear fusion. Unable to support themselves against the force of gravity, the cores of these stars collapse while their outer layers explode as supernovae.
AI Testing
To eliminate the role of humans in this process, Miller and his team developed BTSbot and trained the AI with more than 1.4 million historical images from nearly 16,000 sources. The observed images include confirmed supernovae and other astronomical phenomena such as transient star burning, periodically changing stars, and galaxy burning.
To test their new AI tool, the researchers began hunting for a new supernova candidate named SN2023tyk. This candidate is believed to be a Type Ia supernova located about 760 million light years from Earth.
In the case of a Type Ia supernova, the explosion is triggered when a remnant star called a white dwarf is in a binary system and releases material from its companion star. This influx of material causes the white dwarf to reignite and explode, destroying it entirely.
These supernova explosions can be so bright that they exceed the combined light of every star in the surrounding galaxy. However, thanks to the vastness of space, even these extraordinary bursts of light don’t mean supernovas are easy to spot.
This supernova was discovered by the Zwicky Transient Facility (ZTF) robotic telescope on October 3. While searching for ZTF data, BTSbot was able to identify SN2023tyk on October 5, after which it collected a potential supernova spectrum from a robotic telescope at Palomar.
Through this automatic collaboration, SN2023tyk was classified as a Type Ia supernova. BSTbot doesn’t even need a human operator to share its information, as it was automatically shared with astronomers by AI on October 7.
“Simulated performance is great, but you never really know how it translates to the real world until you actually try it,” said Northwestern graduate student Nabeel Rehemtulla.
2023-10-17 02:33:00
#Time #Successfully #Identifies #Supernova #Human #Astronomers #Eliminated #Space #Space
