论文标题
使用机器学习确定的本地组螺旋星系M33中的巨大年轻恒星物体
Massive young stellar objects in the Local Group spiral galaxy M33 identified using machine learning
论文作者
论文摘要
我们提出了当地螺旋星系M \，33中恒星种群的监督机器学习分类。先前应用于NGC \，6822中种群的概率随机森林（PRF）方法论，都利用了近红外分类特征。它将源分为九个目标类别：年轻的恒星对象（YSO），氧气和富含碳的渐近巨型巨型分支星星，红色巨型分支和红色超级巨星，活跃的银河系核，蓝色星星（例如O-，B-，B-和A-A-Type主序列），Wolf-rayet sars），Wolf-Rayet星星和银河前景星星。在100个分类中，基于混乱矩阵，平均估计精度为$ \ sim $ \，86 \，基于混乱矩阵，平均估计准确度为$ \ sim $ \，86 \，平均估计准确度为162,746个来源。我们确定了M \，33磁盘上的4985 YSO，并应用了基于密度的聚类分析，以识别主要在银河系螺旋臂中的68个星形形成区域（SFRS）。 SFR与已知的H \，{\ sc ii}区域的sfr对应物被恢复，$ \ sim $ \，91 \，per \，sfrs sfrs sfrs在空间上与文献中确定的巨型分子云相吻合。我们使用NGC \，6822中的SFR进行了既定的进化序列作为基准，我们采用了一种新型方法，将[H $α$] $/$ [24 $μ$ M]和[250 $ $ M M] $/$ M M] $/$ [500 $ M] $/$ [500 $ M] $ [500 $ M] $ [500 $ M] $ [500 $ M]组合为估计的状态sfr asfres Alles Ivalsolution asfrs All All All All All Mors M.每个YSO的质量估计为6 \，$ - $ \，27 \，m $ _ \ odot $。使用这些质量，我们根据直接YSO计数0.63 \，m $ _ \ odot $ \，yr $^{ - 1} $估算恒星形成率1.42 \，$ \ pm $ \，0.16 \，m $ _ \ odot $ \，yr $^{ - 1} $全球。
We present a supervised machine learning classification of stellar populations in the Local Group spiral galaxy M\,33. The Probabilistic Random Forest (PRF) methodology, previously applied to populations in NGC\,6822, utilises both near and far-IR classification features. It classifies sources into nine target classes: young stellar objects (YSOs), oxygen- and carbon-rich asymptotic giant branch stars, red giant branch and red super-giant stars, active galactic nuclei, blue stars (e.g. O-, B- and A-type main sequence stars), Wolf-Rayet stars and Galactic foreground stars. Across 100 classification runs the PRF classified 162,746 sources with an average estimated accuracy of $\sim$\,86\,per\,cent, based on confusion matrices. We identified 4985 YSOs across the disk of M\,33, applying a density-based clustering analysis to identify 68 star forming regions (SFRs) primarily in the galaxy's spiral arms. SFR counterparts to known H\,{\sc ii} regions were recovered, with $\sim$\,91\,per\,cent of SFRs spatially coincident with giant molecular clouds identified in the literature. Using photometric measurements, as well as SFRs in NGC\,6822 with an established evolutionary sequence as a benchmark, we employed a novel approach combining ratios of [H$α$]$/$[24$μ$m] and [250$μ$m]$/$[500$μ$m] to estimate the relative evolutionary status of all M\,33 SFRs. Masses were estimated for each YSO ranging from 6\,$-$\,27\,M$_\odot$. Using these masses, we estimate star formation rates based on direct YSO counts of 0.63\,M$_\odot$\,yr$^{-1}$ in M\,33's SFRs, 0.79\,$\pm$\,0.16\,M$_\odot$\,yr$^{-1}$ in its centre and 1.42\,$\pm$\,0.16\,M$_\odot$\,yr$^{-1}$ globally.
