The University of California, Santa Cruz has led an astronomy collaboration that used artificial intelligence to discover the explosion of a massive star in orbit with a black hole. The event, named SN 2023zkd, was detected in July 2023 through a new AI algorithm designed to identify unusual stellar explosions as they happen.
This early detection allowed astronomers to begin immediate follow-up observations using both ground-based and space telescopes. Among these were two telescopes at the Haleakalā Observatory in Hawaiʻi, which are part of the Young Supernova Experiment (YSE) based at UC Santa Cruz.
“Something exactly like this supernova has not been seen before, so it might be very rare,” said Ryan Foley, associate professor of astronomy and astrophysics at UC Santa Cruz. “Humans are reasonably good at finding things that ‘aren’t like the others,’ but the algorithm can flag things earlier than a human may notice. This is critical for these time-sensitive observations.”
Foley’s team manages YSE, which surveys about 4% of the night sky every three days and has found thousands of cosmic explosions and other transient events—many within hours or days after their occurrence.
Researchers believe that SN 2023zkd resulted from an inevitable collision between a massive star and its black hole companion. As energy was lost from their orbit, the distance between them shrank until gravitational stress caused by the black hole triggered the supernova as it partially consumed the star.
The findings were published on August 13 in the Astrophysical Journal. “Our analysis shows that the blast was sparked by a catastrophic encounter with a black hole companion, and is the strongest evidence to date that such close interactions can actually detonate a star,” said lead author Alexander Gagliano, a fellow at the NSF Institute for Artificial Intelligence and Fundamental Interactions.
An alternative explanation considered by researchers is that the black hole completely destroyed the star before it could explode independently. In either scenario, only one heavier black hole remains after the event.
SN 2023zkd is located approximately 730 million light-years from Earth. While initially appearing as a typical supernova with one burst of light, its brightness unexpectedly increased again months later. Archival data revealed that this system had been gradually brightening for over four years prior to its explosion—a rare pattern among observed supernovae.
Analysis conducted partly at UC Santa Cruz indicated that material shed by the star before dying shaped how its light appeared after exploding. Early brightening resulted from interaction with low-density gas; later brightening was due to continued collision with denser material around it. These findings suggest significant gravitational stress on the dying star likely came from proximity to its compact companion.
Foley described working closely with Gagliano on interpreting spectral data: “Our team also built the software platform that we use to consolidate data and manage observations. The AI tools used for this study are integrated into this software ecosystem,” Foley said. “Similarly, our research collaboration brings together the variety of expertise necessary to make these discoveries.”
Enrico Ramirez-Ruiz, professor of astronomy and astrophysics at UC Santa Cruz, led theoretical work on this project. V. Ashley Villar from Harvard provided AI expertise. The discovery team included members from Center for Astrophysics | Harvard & Smithsonian and Massachusetts Institute of Technology as part of YSE.
Funding came from several sources including National Science Foundation (NSF), NASA, Moore Foundation, and Packard Foundation.
However, Foley noted challenges ahead: “The uncertainty means we are shrinking,” he said, “reducing the number of students who are admitted to our graduate program—many of them being forced out of the field or to take jobs outside the U.S.”
Looking forward, Foley commented on broader applications: “You can easily imagine similar techniques being used to screen for diseases, focus attention for terrorist attacks, treat mental health issues early, and detect financial fraud,” he explained. “Anywhere real-time detection of anomalies could be useful, these techniques will likely eventually play a role.”
