A high school student has discovered 1.5 million previously unknown objects in space through the development of a sophisticated AI algorithm.
Matteo (Matthew) Paz, still completing his high school education, has accomplished what many career scientists strive for – publishing a single-author paper in The Astronomical Journal detailing an AI algorithm he created that has significantly expanded our catalog of celestial objects.
Paz’s pioneering work not only revealed these astronomical objects but also broadened the potential of NASA’s NEOWISE (Near-Earth Object Wide-field Infrared Survey Explorer) mission, a now-retired infrared telescope that had been scanning the skies for over a decade.
“I wanted to learn more about astronomy since grade school, when my mother brought me to public Stargazing Lectures at Caltech,” Paz explained.
This early curiosity eventually led him to join the Caltech Planet Finder Academy in the summer of 2022, a program led by Professor of Astronomy Andrew Howard.
Behind Paz’s success was a crucial mentorship relationship with IPAC senior scientist Davy Kirkpatrick, who saw potential in the young researcher’s ambitious goals.
“I’m so lucky to have met Davy,” Paz said. “I remember the first day I talked to him, I said that I was considering working on a paper to come out of this, which is a much larger goal than six weeks. He didn’t discourage me. He said, ‘OK, so let’s talk about that.’ He has allowed an unbridled learning experience. I think that’s why I’ve grown so much as a scientist.”
For Kirkpatrick, who grew up in a farming community in Tennessee and became an astronomer thanks to a supportive teacher, mentoring Paz was a way to pay forward the guidance he once received.
What began as a modest summer project to analyze “a little piece of the sky” quickly evolved when Paz approached the challenge with fresh perspective. Rather than manually sifting through NEOWISE’s massive dataset, which contained nearly 200 billion rows of detections collected over a decade, Paz applied his knowledge of artificial intelligence.
Drawing from his mathematical background in Pasadena Unified School District’s Math Academy and his interest in AI from an elective combining coding, theoretical computer science, and formal mathematics, Paz created a machine-learning technique to analyze the entire dataset.
Kirkpatrick connected Paz with other Caltech astronomers including Shoubaneh Hemmati, Daniel Masters, Ashish Mahabal, and Matthew Graham, who provided expertise in machine learning for astronomy and in studying variable celestial objects.
The NEOWISE telescope, while primarily searching for asteroids and near-Earth objects, had also detected countless variable objects – phenomena like quasars, exploding stars, and binary star systems eclipsing each other. However, this treasure trove of data remained largely untapped until Paz’s algorithm.
Beyond the Initial Discovery
As the summer of 2022 concluded, Paz’s work was far from finished. He continued the collaboration with Kirkpatrick in 2024, this time taking on the role of mentor to other high school students while refining his AI model.
The refined algorithm successfully processed all raw data from NEOWISE, detecting minute differences in infrared measurements to flag and classify 1.5 million potential new variable objects.
In 2025, Paz and Kirkpatrick plan to publish a complete catalog of objects that showed significant brightness variations in the NEOWISE data.
While still completing high school, Paz has secured his first paying job as a Caltech employee, working for Kirkpatrick at IPAC, which manages data from NEOWISE and other NASA and NSF-supported space missions.
You must be logged in to post a comment.