American high school student Matteo Paz from Pasadena High School in California has achieved an unexpected breakthrough in astronomy. Utilizing artificial intelligence, he analyzed archival data from NASA's NEOWISE telescope and identified over 1.5 million previously unknown variable light sources.
It all began in the summer of 2022 when Paz joined the Planet Finder Academy program. Under the guidance of Caltech scientist Davy Kirkpatrick at the Infrared Processing and Analysis Center (IPAC), he worked with a massive dataset from the NEOWISE telescope, which was launched in 2009 to search for near-Earth asteroids.
Over six weeks, Paz developed an automated machine learning algorithm. He applied Fourier transforms and wavelet analysis to detect subtle changes in the brightness of objects that had previously eluded standard methods.
The system successfully identified flickering, pulsating, and dimming sources, which are indicative of quasars, binary stars, and supernovae. The catalog of 1.5 million objects was published in late 2025 and is already being utilized by the Vera C. Rubin Observatory.
Researchers from Caltech, including Shubanit Hemmati, Daniel Masters, Ashish Mahabal, and Matthew Graham, supported the work. In early 2026, NASA leadership publicly acknowledged the teenager's significant contribution.
Paz honed his skills at the Pasadena Unified School District’s Math Academy. His algorithm is capable of analyzing any time-series data and is potentially applicable in diverse fields, ranging from finance to neuroscience.
What if the next major scientific leap comes not from a massive laboratory, but from a high school student with a laptop and access to open data?
Paz's discovery underscores the increasing role of AI in modern astronomy. In February 2026, the Vera C. Rubin Observatory had already sent out 800,000 alerts in a single night, with expectations of up to seven million daily in the future. Without machine learning, managing such a colossal data stream would be impossible.
An article detailing this groundbreaking work was published in The Astronomical Journal. The catalog is already proving instrumental in studying stellar evolution, distant galaxies, and high-energy processes throughout the universe.
