A high school student at Caltech has made a groundbreaking discovery using artificial intelligence (AI) to reveal 1.5 million previously unknown objects in space. Matteo “Matthew” Paz, who is also a part-time employee at IPAC, developed an innovative algorithm that can be used by other astronomers and astrophysicists for their own research.
Paz’s journey began when he attended public stargazing lectures at Caltech as a student. He was inspired to learn more about astronomy and joined the Caltech Planet Finder Academy, led by Professor Andrew Howard. Astronomer Davy Kirkpatrick served as Paz’s mentor, who helped him develop his skills in AI and machine learning.
Kirkpatrick grew up in a farming community in Tennessee and realized his dream of becoming an astronomer with the help of his ninth-grade chemistry and physics teacher, Marilyn Morrison. He now aims to pass on that same mentoring experience to others by identifying potential students like Paz.
Paz used the NEOWISE infrared telescope’s data to develop a machine-learning technique that analyzed the entire dataset and flagged potential variable objects. With Kirkpatrick’s guidance, he consulted with other Caltech astronomers who shared their expertise in machine learning techniques for astronomy. The AI model was refined to process all of the raw data from NEOWISE’s observations, resulting in the discovery of 1.5 million new objects.
Paz plans to publish his research and refine his algorithm further. He believes that his technique can be applied to other time-domain studies in astronomy and potentially even to stock market chart analysis or studying atmospheric effects. With his first paying job as a Caltech employee, Paz continues to grow as a scientist and mentor, following the footsteps of his mentors who paved the way for him.
Source: https://phys.org/news/2025-04-high-school-student-ai-reveal.html