2023 Fiscal Year Final Research Report

Construction of a Transient Detection Survey Robot using Machine Learning

Research Project

PDF

Project/Area Number	20K04011
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Review Section	Basic Section 16010:Astronomy-related
Research Institution	Kyoto University (2023) Tokyo Institute of Technology (2020-2022)
Principal Investigator	Murata Katsuhiro 京都大学, 理学研究科, 特定准教授 (10735038)
Co-Investigator(Kenkyū-buntansha)	谷津陽一東京工業大学, 理学院, 准教授 (40447545) 篠田浩一東京工業大学, 情報理工学院, 教授 (10343097) 井上中順東京工業大学, 情報理工学院, 准教授 (10733397) 下川辺隆史東京大学, 情報基盤センター, 准教授 (40636049)
Project Period (FY)	2020-04-01 – 2024-03-31
Keywords	突発天体検知
Outline of Final Research Achievements	By integrating cutting-edge computer science technologies into existing optical telescopes, we have developed a system capable of rapidly detecting transient sources from observed images. The transient source identification algorithm, utilizing machine learning, achieves a detection accuracy of 97% for transient sources with a signal-to-noise ratio of 10 or higher, while limiting the false detection rate to 500 or fewer per night. This system has been implemented into our automated robotic telescope system and performed the observation of transient sources. Furthermore, a wide-field telescope has been newly installed to conduct observations for functional verification.
Free Research Field	光赤外線天文学
Academic Significance and Societal Importance of the Research Achievements	本研究で開発した突発天体検知システムを用いることで、大量の観測データから迅速に突発天体を発見することが期待できる。天文学に残された未開拓領域の一つである「突発天体現象」の理解には早期発見が重要であり、今後このシステムを用いて観測を続けることで、新たな天体現象の発見や、既存の現象のメカニズム解明に貢献することが期待される。