For the first time, an AI system discovers supernova without human intervention

For the first time, artificial intelligence (AI) fully automated the process of discovering a supernova as it searched for, detected, confirmed, classified, and announced the findings without any human intervention. Led by Northwestern University, an international team of scientists has created a cutting-edge AI tool known as the Bright Transient Survey Bot (BTSbot).

What is the AI tool?

The university has reported that the new system not only allows automation of the entire search for new supernovae across the night sky but also eliminates human error and dramatically increases speed.

Add WION as a Preferred Source

BTSbot is a machine-learning algorithm which has been trained by using over 1.4 million images from nearly 16,000 sources, said the researchers in a statement. Scientists have estimated that in the last six years, humans have spent an estimated 2,200 hours visually inspecting and classifying supernova candidates.

“For the first time ever, a series of robots and AI algorithms has observed, then identified, then communicated with another telescope to finally confirm the discovery of a supernova,” said Northwestern’s Adam Miller, who led the work.

He added, “Ultimately, removing humans from the loop provides more time for the research team to analyze their observations and develop new hypotheses to explain the origin of the cosmic explosions that we observe.”

How does it work?

The current process of detecting and analysing supernovae involves humans working hand in hand with robotic systems and though supernovae are bright and energetic events, they are not that common, and certainly not easy to spot.

The traditional method involves relying on robotic telescopes repeatedly taking images of the same sections of the night sky to detect new sources of light after which humans take over. Subsequently, astronomers have to visually inspect large volumes of data.

This time-consuming process is believed to be the reason why astronomers have only discovered a small fraction of all supernovae that occur in the universe.

“Automated software presents a list of candidate explosions to humans, who spend time verifying the candidates and executing spectroscopic observations,” Miller explains.

He added, “We can only definitively know that a candidate is truly a supernova by collecting its spectrum – the source’s dispersed light, which reveals elements present in the explosion.”

BTSbot detected the newly discovered supernova named SN2023tyk in data from the Zwicky Transient Facility (ZTF), said the researchers, which is a robotic camera in the US state of California which scans the northern sky every two days.

This was also after BTSbot automatically requested the potential supernova’s spectrum from Palomar Observatory – where another robotic telescope, the Spectral Energy Distribution Machine (SEDM) performed an in-depth observation to obtain the source’s spectrum.

The spectrum was then sent to SNIascore – developed by Caltech’s Christoffer Fremling, an astronomer – to determine the supernova’s type. “Adding BTSbot to our workflow will eliminate the need for us to spend time inspecting these candidates,” said Fremling.

“This significantly streamlines large studies of supernovae, helping us better understand the life cycles of stars and the origin of elements supernovae create, like carbon, iron and gold,” said Nabeel Rehemtulla, who co-led the development.

WATCH WION LIVE HERE

You can now write for wionews.com and be a part of the community. Share your stories and opinions with us here.