How a Hobbyist Leveraged AI to Uncover a Planet
A 28‑year‑old product manager from Spain, Pavel Rabtsevich, used artificial intelligence to spot a possible planet around a distant star. He had no telescope or formal training, only a laptop, an internet connection, and access to several AI services. Last month he sifted through data from the Transiting Exoplanet Survey Satellite (TESS) and flagged a signal that could indicate a planet.
Breaking news
Town AI Secures $108 Million Series B, Valued at $1 Billion After $55 M Pre‑Series
Apple Prepares for Major Product Launch Event on October 28
Apple Releases Release Candidates for watchOS, tvOS and visionOS 27.2
Apple Limits iPhone Duo and iPhone 18 Pro Max to Reservation-Only Sales in Japan and South KoreaThe data set was public and massive, containing light curves from thousands of stars. Rabtsevich fed the raw measurements into a generative AI model that was trained on thousands of known exoplanet signatures. The model highlighted a subtle dip in brightness that a human eye might miss. He then cross‑checked the signal with other AI tools and found consistent patterns across multiple observations.
What Does This Mean for Amateur Astronomy?
Rabtsevich’s approach was unconventional. Instead of using traditional software, he relied on conversational AI to interpret the data. He asked the model to explain the light curve, and the AI provided a step‑by‑step analysis. The model suggested that the dip lasted about 1.5 hours and recurred every 12 days, matching the orbital period of a Neptune‑size planet. Rabtsevich verified the period by plotting the data and confirmed the repeatability of the signal.
When he presented his findings to the scientific community, the team at the European Southern Observatory (ESO) was intrigued. They performed follow‑up observations with the Very Large Telescope (VLT) and confirmed the presence of a planet, which they named „TESS‑P‑28.” The planet orbits a K‑type star about 600 light‑years away and has a radius roughly 4.5 times that of Earth.
Frequently Asked Questions
The discovery shows that AI can democratize the search for exoplanets. Hobbyists no longer need expensive equipment or deep expertise. They can use cloud‑based AI tools to analyze large data sets and spot promising candidates. However, the final confirmation still relies on professional observatories. This partnership between amateurs and institutions could accelerate the pace of discovery.
Future projects may incorporate more advanced machine‑learning models that can automatically flag anomalies and even predict planetary characteristics. As AI becomes more accessible, the line between professional and amateur research will blur, potentially leading to more citizen‑science breakthroughs.
