准确的测光红移(photo-$z$)估计需要多波段观测数据的支持。然而,在实际的天文观测和数据处理过程中,由于各种原因,某些源在某些波段可能存在观测数据缺失。这可能会极大影响这些源的photo-$z$估计的准确性和可靠性,甚至使某些估计方法无法使用。即将到来的中国空间站望远镜(CSST)也可能存在同样的情况。在本研究中,我们采用一种名为生成对抗插补网络(GAIN)的深度学习方法来插补CSST中缺失的测光数据,旨在减少数据缺失对photo-$z$估计的影响并提高估计准确性。我们的结果表明,使用GAIN技术可以有效填补CSST中缺失的测光数据。特别是,当数据缺失率低于30%时,测光数据的插补表现出较高的准确性,其中$g$、$r$、$i$、$z$和$y$波段的准确性高于$NUV$和$u$波段。填补缺失值后,广泛使用的Easy and Accurate Zphot from Yale(EAZY)软件获得的photo-$z$估计质量显著提高。用于评估photo-$z$估计质量的指标,包括灾难性异常值比例($f_{out}$)、归一化中位绝对偏差($\ m {σ_{NMAD}}$)和测光红移偏差($bias$),均显示出一定程度的改善。我们的研究将有助于最大化观测数据的利用率,并为需要完整测光数据才能产生结果的应用提供处理样本缺失值的新方法。
英文摘要:
Accurate photometric redshift (photo-$z$) estimation requires support from multi-band observational data. However, in the actual process of astronomical observations and data processing, some sources may have missing observational data in certain bands for various reasons. This could greatly affect the accuracy and reliability of photo-$z$ estimation for these sources, and even render some estimation methods unusable. The same situation may exist for the upcoming Chinese Space Station Telescope (CSST). In this study, we employ a deep learning method called Generative Adversarial Imputation Networks (GAIN) to impute the missing photometric data in CSST, aiming to reduce the impact of data missing on photo-$z$ estimation and improve estimation accuracy. Our results demonstrate that using the GAIN technique can effectively fill in the missing photometric data in CSST. Particularly, when the data missing rate is below 30\%, the imputation of photometric data exhibits high accuracy, with higher accuracy in the $g$, $r$, $i$, $z$, and $y$ bands compared to the $NUV$ and $u$ bands. After filling in the missing values, the quality of photo-$z$ estimation obtained by the widely used Easy and Accurate Zphot from Yale (EAZY) software is notably enhanced. Evaluation metrics for assessing the quality of photo-$z$ estimation, including the catastrophic outlier fraction ($f_{out}$), the normalized median absolute deviation ($\rm {σ_{NMAD}}$), and the bias of photometric redshift ($bias$), all show some degree of improvement. Our research will help maximize the utilization of observational data and provide a new method for handling sample missing values for applications that require complete photometry data to produce results.
A Multi-modal Fusion Network for Star-Galaxy Classification from CSST Simulated Datasets
National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);School of Astronomy and Space Science, University of Chinese Academy of Sciences(中国科学院大学天文与空间科学学院);Institute for Frontiers in Astronomy and Astrophysics of Beijing Normal University(北京师范大学天文与空间科学研究院);Zhejiang Lab(浙江实验室)
Probing Large-scale Structure and the Multi-Phase IGM at the Cosmic Noon -- Insights from a Joint Survey with Euclid, CSST, JPCam, and JUST
Purple Mountain Observatory, Chinese Academy of Sciences(中国科学院紫金山天文台);Observatório Nacional(国家天文台);University of Michigan(密歇根大学);National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);School of Astronomy and Space Science, University of Chinese Academy of Sciences(UCAS)(中国科学院大学天文与空间科学学院);Department of Astronomy, Tsinghua University(清华大学天文系);Department of Physics, University of Milano-Bicocca(米兰比可卡大学物理系);Shanghai Jiao Tong University(上海交通大学)
Stellar Density Classification and Regression for CSST Multi-color Imaging Using Deep Learning
National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);School of Astronomy and Space Science, University of Chinese Academy of Sciences(中国科学院大学天文与空间科学学院);Institute for Frontiers in Astronomy and Astrophysics, Beijing Normal University(北京师范大学天文与前沿科学研究院);School of Physics and Astronomy, China West Normal University(西华师范大学物理与天文学学院)
LEO Satellite Track Correction for CSST Multi-Band Imaging Data
Key Laboratory of Space Astronomy and Technology, National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台空间天文与技术重点实验室);University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Kavli Institute for Astronomy and Astrophysics, Peking University(北京大学柯利天体物理研究所);Purple Mountain Observatory, Chinese Academy of Sciences(中国科学院紫金山天文台)
Quasar photometric redshifts from incomplete data using Deep Learning
即将到来的天文巡天预计将探测到如此大量的新光源,以至于测量它们的光谱红移测量将是不切实际的。因此,人们对使用机器学习来从每个物体的测光中产生红移很感兴趣。我们对Square Kilometre Array探测到的射电源(类星体)特别感兴趣,并发现深度学习,在大量光学选择的准恒星物体样本上进行训练,可以有效地预测三个外部射电源样本的红移。然而,要求九个不同的星等,从近红外,光学和紫外波段,有显着减少的影响,可以预测的红移源的数量。在这里,我们探索使用机器学习来估算缺失特征的可能性。我们发现,对于训练样本,简单的插补是足够的,特别是用该波段的最大值替换缺失的幅度,从而假设未检测到的是在灵敏度极限。然而,对于测试样本,这并不像多变量插补那样有效,这表明许多缺失的量值不是极限,但确实没有被观察到。从广泛的测试模型,我们建议,插补是最好的限制,每个源两个缺失值。在最坏的情况下,当源在天空中重叠时,这将使红移可以被估计的源的比例从46%增加到80%,而对于其他样本则达到>90%。
School of Physics and Astronomy, Sun Yat-Sen University(中山大学物理与天文学院);CSST Science Center for the Guangdong-Hongkong-Macau Greater Bay Area, SYSU(粤港澳大湾区空间望远镜科学中心,中山大学);Department of Mathematics and Theory, Peng Cheng Laboratory(鹏城实验室数学与理论部);National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);School of Astronomy and Space Sciences, University of Chinese Academy of Sciences (UCAS)(中国科学院大学天文与空间科学学院);Science Center for China Space Station Telescope, National Astronomical Observatories, Chinese Academy of Sciences(中国空间站望远镜科学中心,中国科学院国家天文台)
Probabilistic redshift estimation of unresolved galaxies from multi-band background light maps
Ruhr University Bochum(鲁尔大学波鸿);Stanford University(斯坦福大学);SLAC National Accelerator Laboratory(斯坦福直线加速器中心);The University of British Columbia(不列颠哥伦比亚大学)