A team led by the University of California, Santa Cruz has discovered a supernova explosion triggered by a black hole, using artificial intelligence to identify the event in real time. The explosion, named SN 2023zkd, was first detected in July 2023 through an AI algorithm developed to scan for unusual cosmic explosions as they happen. This early detection enabled astronomers to quickly begin follow-up observations.
The discovery involved multiple telescopes, including two at the Haleakalāa Observatory in Hawaiʻi that are part of the Young Supernova Experiment (YSE), which is based at UC Santa Cruz. YSE surveys about 4% of the night sky every three days and has identified thousands of new cosmic events, many within hours or days after their occurrence.
“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.”
The research team believes that SN 2023zkd resulted from a collision between a massive star and a black hole. As energy was lost from their orbit, their separation decreased until gravitational stress caused the star to explode while being partially consumed by the black hole.
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.
Another possible explanation considered by researchers is that the black hole completely tore apart the star before it could explode independently. In both scenarios, only one heavier black hole remains after the event.
SN 2023zkd is located approximately 730 million light-years from Earth. Initially appearing as an ordinary supernova with one burst of light, its brightness increased again months later—a rare behavior among supernovae. Archival data showed that this system had been gradually brightening for over four years prior to exploding.
Further analysis indicated that material shed by the star before its death shaped how light from the explosion appeared. The initial brightening was due to interaction with low-density gas; later increases were caused by collisions with denser material around it. These features suggest strong gravitational influence from a nearby compact object such as a black hole.
Foley described discussions with Gagliano about 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, another professor at UC Santa Cruz, leads theoretical work on these phenomena; V. Ashley Villar from Harvard contributed AI expertise; and institutions including MIT participated in YSE’s efforts.
Funding came from several sources including National Science Foundation grants and support from NASA and private foundations. However, Foley noted concerns about future funding: “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.”
Foley also commented on broader uses for AI-driven anomaly detection: “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.”
