A brand-new artificial intelligence (AI) tool has for the first time successfully detected, identified and classified its first supernova, removing humans from the entire process.
A supernova is an extremely bright, super-powerful explosion of a star. It is one of the most energetic explosions ever seen in the Universe. Currently, the process of detecting and analysing supernovae involves both robots and humans. In the past six years, humans have spent an estimated total of 2,200 hours visually inspecting and classifying supernova candidates.
The new fully automated system, developed by an international collaboration led by Northwestern University, not only rapidly accelerates the process of analyzing and classifying new supernova candidates, but also bypasses human error.
Called the Bright Transient Survey Bot (BTSbot), the new AI tool is a machine-learning algorithm, trained with more than 1.4 million historical images from 16,000 astronomical sources.
The researchers believe that cutting out humans from the discovery process will give them more time to perform in-depth observations.
“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. This represents an important step forward as further refinement of models will allow the robots to isolate specific subtypes of stellar explosions. 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,” said Northwestern’s Adam Miller, who led the work.
The team tested the new automated system in a newly discovered supernova candidate dubbed SN2023tyk.
The international collaboration included astronomers from Caltech, the University of Minnesota, Liverpool John Moores University in England and Stockholm University in Sweden.
More details about the tool and its simulated performance can be found here.
