arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.08626astro-ph.GAastro-ph.IM
收藏

S-PLUS:基于机器学习方法的恒星/星系分类

The S-PLUS: a star/galaxy classification based on a Machine Learning approach

M. V. Costa-Duarte, L. Sampedro, A. Molino, H. S. Xavier, F. R. Herpich, A. L. Chies-Santos, C. E. Barbosa, A. Cortesi, W. Schoenell, A. Kanaan, T. Ribeiro, C. … 展开作者

M. V. Costa-Duarte, L. Sampedro, A. Molino, H. S. Xavier, F. R. Herpich, A. L. Chies-Santos, C. E. Barbosa, A. Cortesi, W. Schoenell, A. Kanaan, T. Ribeiro, C. Mendes de Oliveira, S. Akras, A. Alvarez-Candal, C. L. Barbosa, J. L. N. Castellón, P. Coelho, M. L. L. Dantas, R. Dupke, A. Ederoclite, A. Galarza, T. S. Gonçalves, J. A. Hernandez-Jimenez, Y. Jiménez-Teja, A. Lopes, P. A. A. Lopes, R. Lopes de Oliveira, J. L. Melo de Azevedo, L. M. Nakazono, H. D. Perottoni, C. Queiroz, K. Saha, L. Sodré, E. Telles, R. C. Thom de Souza

摘要:

我们提出了一个恒星/星系分类的南方测光本地宇宙调查(S-PLUS),基于机器学习方法:随机森林算法。我们使用S-PLUS光学光度计对算法进行训练,直到$r$ =21,与SDSS/DR 13和形态参数相匹配。重要性度量被定义为当与某个特征相关的所有相关性消失时初始精度的相对降低。一般来说,宽光度带比窄光度带具有更高的重要性。的形态参数的影响进行了评估训练RF与和不包括形态参数,分别呈现95.0%和88.1%的准确度值。特别是,形态参数{ \rm FWHM/PSF}在所有特征中表现出最高的重要性,以区分恒星和星系,这表明将物体分类为恒星和星系是至关重要的。我们研究了恒星和星系在宽带色-色图$(g-r)$和$(r-i)$中的错误分类。形态学可以显着改善图中误分类相对较高的区域处的对象的分类。因此,它为统计研究提供了更干净的样本。作为红移的函数的红星系的预期污染率的估计,提供红色星系样本的校正。类星体作为河外天体的分类仅使用光度计的情况稍微好一些。在没有任何形态学特征(仅SED信息)的情况下,通过对光度红移和{ \rm FWHM/PSF}值的附加约束,利用分类法给出了河外点源星表。

英文摘要:

We present a star/galaxy classification for the Southern Photometric Local Universe Survey (S-PLUS), based on a Machine Learning approach: the Random Forest algorithm. We train the algorithm using the S-PLUS optical photometry up to $r$=21, matched to SDSS/DR13, and morphological parameters. The metric of importance is defined as the relative decrease of the initial accuracy when all correlations related to a certain feature is vanished. In general, the broad photometric bands presented higher importance when compared to narrow ones. The influence of the morphological parameters has been evaluated training the RF with and without the inclusion of morphological parameters, presenting accuracy values of 95.0\% and 88.1\%, respectively. Particularly, the morphological parameter {\rm FWHM/PSF} performed the highest importance over all features to distinguish between stars and galaxies, indicating that it is crucial to classify objects into stars and galaxies. We investigate the misclassification of stars and galaxies in the broad-band colour-colour diagram $(g-r)$ versus $(r-i)$. The morphology can notably improve the classification of objects at regions in the diagram where the misclassification was relatively high. Consequently, it provides cleaner samples for statistical studies. The expected contamination rate of red galaxies as a function of the redshift is estimated, providing corrections for red galaxy samples. The classification of QSOs as extragalactic objects is slightly better using photometric-only case. An extragalactic point-source catalogue is provided using the classification without any morphology feature (only the SED information) with additional constraints on photometric redshifts and {\rm FWHM/PSF} values.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑