基于监督对比学习的莱曼断裂星系选择与红移测量
Lyman Break Galaxy selection and redshift measurement with supervised contrastive learning
浏览论文内容
中文总结 AI 辅助
针对DESI巡天中高红移莱曼断裂星系的红移测量与样本污染问题，提出监督加权对比学习方法，在小样本任务中实现了更优的异常分类与相当的红移识别性能。
中文摘要 AI 辅助
高精度宇宙学的后续研究方向之一聚焦于高红移、高密度宇宙。诸如暗能量光谱仪（DESI）二期DESI Run 2这类光谱巡天实验，将转向探测红移z~2至z~4.5的莱曼断裂星系（LBG）群体。对于这类暗弱样本，即便完成目标选择，光谱红移测量与样本去污染仍是挑战。本文提出一种基于监督加权对比学习的方法，旨在学习光谱的红移表征，同时将样本中的类星体与低红移发射线星系去除污染。该策略通过引入连续关系权重推广了对比学习损失方法，使网络同时学习红移与分类任务。在同一数据集上，与DESI此前使用的网络（QuasarNET的改进版本）相比，本模型展现出更强的异常值分类能力与相当的红移识别性能。尤其值得注意的是，考虑到本研究的多任务性质，对比学习非常适用于训练和测试所用的经目视检查的小样本。
英文摘要
Some of the next steps for high-precision cosmology lie within the high-redshift, high-density universe. Spectroscopic survey experiments such as the Dark Energy Spectroscopic Instrument (DESI)'s second phase DESI Run 2 will shift towards probing Lyman Break Galaxy (LBG) populations from z$\sim$2 to z$\sim$4.5. For this faint sample, spectroscopic redshift measurement and sample decontamination remains a challenge, even after target selection. We propose an approach based on supervised weighted contrastive learning, in order to both learn a redshift representation for spectra and decontaminate the sample from quasars and low redshift emission line galaxies. This strategy generalizes the contrastive learning loss approach with continuous relationship weights, such that the network simultaneously learns redshift and classification tasks. The model shows stronger outlier classification and comparable redshift identification performances when compared to the previous network used for DESI (a modified version of QuasarNET) on the same dataset. In particular, contrastive learning is well suited to the small, visually-inspected sample used for training and testing, especially given the multi-task nature of this work.
