КИНЕМАТИЧЕСКИЕ СВИДЕТЕЛЬСТВА НАЛИЧИЯ ПРОТОПЛАНЕТЫ В ДИСКЕ HD 142666, ПОЛУЧЕННЫЕ С ПОМОЩЬЮ МАШИННОГО ОБУЧЕНИЯ

Currently, scientists' attention is focused on the integration of modern technologies into scientific research, for example, when observing protoplanets. A research team from the University of Georgia used machine learning models to study protoplanetary disks, the gas surrounding newly formed stars, for the presence of previously unknown exoplanets. They found that machine learning algorithms can identify the presence of exoplanets inside these disks. In the gas, these forming exoplanets cause deviations from Keplerian motion, which can be detected by observing molecular lines. Using machine learning models, a strong localized non-Keplerian motion was detected inside the HD 142666 disk. This led to the conclusion that there is a planet in HD 142666. The models were able to detect a signal in the data that people had already analyzed; they found something that had previously gone unnoticed. This breakthrough demonstrates the potential of machine learning, which can help scientists in deep space exploration, providing a valuable tool to improve the accuracy and efficiency of their research.