arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.01596astro-ph.IMastro-ph.CO
收藏

利用主动学习改进DESI光谱处理流水线的类星体识别

Using Active Learning to Improve Quasar Identification for the DESI Spectra Processing Pipeline

Dylan Green, David Kirkby, J. Aguilar, S. Ahlen, D. M. Alexander, E. Armengaud, S. Bailey, A. Bault, D. Bianchi, A. Brodzeller, D. Brooks, T. Claybaugh, R. de B… 展开作者

Dylan Green, David Kirkby, J. Aguilar, S. Ahlen, D. M. Alexander, E. Armengaud, S. Bailey, A. Bault, D. Bianchi, A. Brodzeller, D. Brooks, T. Claybaugh, R. de Belsunce, A. de la Macorra, P. Doel, V. A. Fawcett, S. Ferraro, A. Font-Ribera, J. E. Forero-Romero, E. Gaztañaga, S. Gontcho A Gontcho, G. Gutierrez, M. Ishak, S. Juneau, R. Kehoe, T. Kisner, A. Kremin, A. Lambert, M. Landriau, L. Le Guillou, M. E. Levi, M. Manera, A. Meisner, R. Miquel, J. Moustakas, A. D. Myers, N. Palanque-Delabrouille, F. Prada, I. Pérez-Ràfols, G. Rossi, E. Sanchez, C. Saulder, D. Schlegel, M. Schubnell, H. Seo, F. Sinigaglia, D. Sprayberry, T. Tan, G. Tarlé, B. A. Weaver, S. Youles, J. Yu, R. Zhou, H. Zou

AI总结:

本研究针对DESI巡天的QuasarNET类星体分类模型,提出含自组织映射离群点剔除的主动学习算法,仅用原训练数据的十分之一就实现了更优的分类完备度与纯度,还发现并修正了红移估计的系统误差。

摘要:

暗能量光谱仪(Dark Energy Spectroscopic Instrument, DESI)巡天采用自动光谱分类流水线对光谱进行分类。QuasarNET是该流水线的组成部分之一,是一个最初利用重子振荡光谱巡天(Baryon Oscillation Spectroscopic Survey, BOSS)数据训练的卷积神经网络。本文实现了一种主动学习算法,用于最优选择仅基于DESI数据训练新版QuasarNET权重文件的光谱,核心目标是提升分类精度。该主动学习算法包含一个新颖的离群点剔除步骤,采用自组织映射(Self-Organizing Map)确保我们标记的光谱能够代表DESI观测到的更大量类星体样本。我们开展了两轮主动学习流水线迭代,最终构建了包含5600条标记光谱的数据集,这仅为DESI第一版数据发布中约130万个类星体目标的一小部分。将光谱划分为训练集与验证集后,我们在验证集上计算得到的完备度与纯度达到或超过了此前训练的权重文件,而所用训练数据量不足其十分之一。与旧权重文件相比,新权重在应用于未标记数据时,对天体的分类结果一致性更高。在提升QuasarNET分类精度的过程中,我们发现了QuasarNET红移估计中的一个系统误差,并利用相关发现深化了对QuasarNET红移结果的认知。

英文摘要:

The Dark Energy Spectroscopic Instrument (DESI) survey uses an automatic spectral classification pipeline to classify spectra. QuasarNET is a convolutional neural network used as part of this pipeline originally trained using data from the Baryon Oscillation Spectroscopic Survey (BOSS). In this paper we implement an active learning algorithm to optimally select spectra to use for training a new version of the QuasarNET weights file using only DESI data, specifically to improve classification accuracy. This active learning algorithm includes a novel outlier rejection step using a Self-Organizing Map to ensure we label spectra representative of the larger quasar sample observed in DESI. We perform two iterations of the active learning pipeline, assembling a final dataset of 5600 labeled spectra, a small subset of the approx 1.3 million quasar targets in DESI's Data Release 1. When splitting the spectra into training and validation subsets we meet or exceed the previously trained weights file in completeness and purity calculated on the validation dataset with less than one tenth of the amount of training data. The new weights also more consistently classify objects in the same way when used on unlabeled data compared to the old weights file. In the process of improving QuasarNET's classification accuracy we discovered a systemic error in QuasarNET's redshift estimation and used our findings to improve our understanding of QuasarNET's redshifts.

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。

↑