Multi-layer Perceptron for Predicting Galaxy Parameters (MLP-GaP): Stellar Masses and Star Formation Rates

doi:10.1088/1674-4527/ad95d7

YNAO OpenIR > 南方基地

	Multi-layer Perceptron for Predicting Galaxy Parameters (MLP-GaP): Stellar Masses and Star Formation Rates
	Guo, Xiaotong 1; Fang, Guanwen 1; Feng HC(封海成)2 ; Zhang, Rui 1
发表期刊	RESEARCH IN ASTRONOMY AND ASTROPHYSICS
	2024-12-01
卷号	24 期号:12
DOI	10.1088/1674-4527/ad95d7
产权排序	第2完成单位
收录类别	SCI
关键词	methods: data analysis galaxies: fundamental parameters galaxies: star formation
摘要	The large-scale imaging survey will produce massive photometric data in multi-bands for billions of galaxies. Defining strategies to quickly and efficiently extract useful physical information from this data is mandatory. Among the stellar population parameters for galaxies, their stellar masses and star formation rates (SFRs) are the most fundamental. We develop a novel tool, Multi-Layer Perceptron for Predicting Galaxy Parameters (MLP-GaP), that uses a machine learning (ML) algorithm to accurately and efficiently derive the stellar masses and SFRs from multi-band catalogs. We first adopt a mock data set generated by the Code Investigating GALaxy Emission (CIGALE) for training and testing data sets. Subsequently, we used a multi-layer perceptron model to build MLP-GaP and effectively trained it with the training data set. The results of the test performed on the mock data set show that MLP-GaP can accurately predict the reference values. Besides MLP-GaP has a significantly faster processing speed than CIGALE. To demonstrate the science-readiness of the MLP-GaP, we also apply it to a real data sample and compare the stellar masses and SFRs with CIGALE. Overall, the predicted values of MLP-GaP show a very good consistency with the estimated values derived from spectral energy distribution fitting. Therefore, the capability of MLP-GaP to rapidly and accurately predict stellar masses and SFRs makes it particularly well-suited for analyzing huge amounts of galaxies in the era of large sky surveys.
资助项目	National Nature Science Foundation of China[12303017]; National Nature Science Foundation of China[12203096]; Anhui Provincial Natural Science Foundation[2308085QA33]; China Manned Space Project
项目资助者	National Nature Science Foundation of China[12303017, 12203096] ; Anhui Provincial Natural Science Foundation[2308085QA33] ; China Manned Space Project
语种	英语
学科领域	天文学 ; 星系与宇宙学 ; 恒星与银河系
文章类型	Article
出版者	NATL ASTRONOMICAL OBSERVATORIES, CHIN ACAD SCIENCES
出版地	20A DATUN RD, CHAOYANG, BEIJING, 100101, PEOPLES R CHINA
ISSN	1674-4527
URL	查看原文
WOS记录号	WOS:001376598800001
WOS研究方向	Astronomy & Astrophysics
WOS类目	Astronomy & Astrophysics
关键词[WOS]	CONVOLUTIONAL NEURAL-NETWORKS ; DATA RELEASE ; AUTOMATIC CLASSIFICATION ; PHOTOMETRIC REDSHIFTS ; POPULATION SYNTHESIS ; MAIN-SEQUENCE ; EVOLUTION ; ULTRAVIOLET ; EXTINCTION ; COSMOLOGY
引用统计
文献类型	期刊论文
版本	出版稿
条目标识符	http://ir.ynao.ac.cn/handle/114a53/27852
专题	南方基地
作者单位	1.Institute of Astronomy and Astrophysics, Anqing Normal University, Anqing 246133, China; 2.Yunnan Observatories, Chinese Academy of Sciences, Kunming 650011, China
推荐引用方式 GB/T 7714	Guo, Xiaotong,Fang, Guanwen,Feng HC,et al. Multi-layer Perceptron for Predicting Galaxy Parameters (MLP-GaP): Stellar Masses and Star Formation Rates[J]. RESEARCH IN ASTRONOMY AND ASTROPHYSICS,2024,24(12).
APA	Guo, Xiaotong,Fang, Guanwen,封海成,&Zhang, Rui.(2024).Multi-layer Perceptron for Predicting Galaxy Parameters (MLP-GaP): Stellar Masses and Star Formation Rates.RESEARCH IN ASTRONOMY AND ASTROPHYSICS,24(12).
MLA	Guo, Xiaotong,et al."Multi-layer Perceptron for Predicting Galaxy Parameters (MLP-GaP): Stellar Masses and Star Formation Rates".RESEARCH IN ASTRONOMY AND ASTROPHYSICS 24.12(2024).

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Multi-layer Perceptr（2972KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文