Matteo Paz, a student at Pasadena High School, joined the Planet Finder Academy in the summer of 2022. The program immerses students in real world astronomy challenges. Under the mentorship of Caltech scientist Davy Kirkpatrick at the Infrared Processing and Analysis Center (IPAC), Paz examined a massive archive from NASA’s NEOWISE telescope.
Launched in 2009 to detect near Earth asteroids, NEOWISE collected a decade of full sky infrared observations. The dataset contained nearly 200 billion rows of measurements, capturing countless celestial objects and distant phenomena. While the research team initially planned to study a small subset manually, Paz designed a more ambitious approach.
Edit Fe
Drawing on his background in theoretical math, coding and time series analysis, he built an automated algorithm to process the archive. In six weeks, he created a machine-learning pipeline capable of detecting faint, variable light sources – objects whose brightness changes too subtly or unpredictably for humans or standard software to catch.
“The model started showing promise almost right away,” Kirkpatrick told Phys.org. “As Paz fine tuned it, the results only got more exciting.” The system identified flickering, pulsing, and fading objects that served as signatures of quasars, binary stars, and supernovae.
» People are reading this next: “Cows forgotten on an island survived alone for 130 years — their story fascinates scientists”
Paz’s breakthrough highlights a massive shift in modern astrophysics: the democratization of artificial intelligence. Tools that previously required massive institutional supercomputers and entire research departments are now being leveraged by high schoolers to decode the universe.
Paz’s model used Fourier transforms and wavelet analysis, mathematical tools for studying time-based signals. These techniques revealed faint variations in the infrared spectrum that NEOWISE’s sampling might otherwise have missed. Some objects changed so slowly or briefly that they had previously gone unnoticed. Detecting these variables is important for studying rare transients and cataclysmic variables, which do not follow predictable cycles.
He worked alongside Caltech researchers including Shoubaneh Hemmati, Daniel Masters, Ashish Mahabal, and Matthew Graham. Together, they refined the system to process the entire sky’s data, producing a catalog of more than 1.5 million variable light sources.
Released publicly in late 2025, this massive catalog is already driving active observations early this year at major facilities such as the Vera C. Rubin Observatory. It is providing immediate new insights into stellar evolution, distant galaxies, and high-energy cosmic processes.
Paz continued his work after the initial discovery. His momentum has only accelerated into the new year. Just weeks ago, NASA leadership publicly praised Paz’s breakthrough, highlighting a historic shift: major space institutions are now openly recognizing that revolutionary AI-driven discoveries can come from a teenager’s laptop just as easily as from a traditional agency.”
The tools he used, from algorithmic modeling to computational astrophysics, are normally reserved for graduate level study. He developed these skills through the Pasadena Unified School District’s Math Academy, a public program for mathematically gifted students.
“If I see their potential, I want to make sure they reach it,” Kirkpatrick said. “I’ll do whatever I can to help them.”
Paz hopes to extend his AI system beyond astronomy. Since the algorithm can analyze any time-based data, it could eventually be applied to fields like finance, environmental monitoring, or neuroscience, where subtle changes over time reveal important patterns. The project demonstrates how tools that advance cosmic discovery can also provide insight into complex systems on Earth.
Ultimately, Matteo Paz’s achievement serves as a powerful reminder for the scientific community: the next major leap in human knowledge might not come from a multi-billion-dollar lab, but from a teenager with a laptop, open-source data, and a completely fresh perspective.
Leave a Reply