Artificial İntelligence Helps İn The İdentification Of Astronomical Objects

Classifying celestial bodies is a long-running study. Sometimes it is difficult for researchers to distinguish between objects such as stars, galaxies, quasars or supernovas.

Pedro Cunha and Andrew Humphrey, researchers of the Instituto de Astrofísica e Ciências do Espaço (IA), sought to solve this classic problem by inventing Sheep, a machine learning algorithm that determines the nature of astronomical sources. Andrew Humphrey (IA and University of Porto, Portugal) says:

“Classifying celestial bodies is very challenging in terms of the numbers and complexity of the universe, and artificial intelligence is a very promising tool for this kind of task.”

“This work was born as a side project from my master’s thesis,” says Pedro Cunha, a PhD student at the University of Porto, first author of the paper published in the journal Astronomy and Astrophysics.

Pedro Cunha MSc advisor and PhD co-advisor Andrew Humphrey says: “It was very nice to have such an interesting result, especially from the MA thesis. SHEEPpredicts photometric redshifts. A controlled study that uses this information when classifying sources as a galaxy, quasar or star.” It is the machine learning pipeline. Photometric information is the easiest to obtain, and therefore it is very important to provide an initial analysis of the nature of the observed sources.”

SHEEP is a machine learning algorithm that determines the nature of astronomical sources.

Pedro Cunha says, “One of the most exciting parts is seeing how machine learning helps us better understand the universe. While our methodology shows us one possible path, new ones are created along the way. It’s an exciting time for astronomy.”

Imaging and spectroscopic research, understanding the visible content of the universe It is one of the main sources for Data from these surveys enable statistical surveys of stars, quasars and galaxies, and the discovery of more bizarre objects.

Lead researcher Polychronis Papaderos says: “TheSHEEP is an integral component of a coherent strategy. With IA’s ESA’s Euclidean space mission, scheduled to launch in 2023, SHEEP will provide unprecedented large photometric datasets for billions of galaxies. will present.”

Euclid will shed light on the nature of mysterious matter and dark energy while presenting a detailed map of the universe.