用CGAN同时预测星系光谱红移点估计和概率分布。
Determination of galaxy photometric redshifts using Conditional Generative Adversarial Networks (CGANs)
- 基于条件生成对抗网络，联合建模光度数据与红移关系。
- 在暗能量巡天数据上表现接近混合密度网络，误差略高但可比。
- 适合需要红移不确定性估计的天文大数据分析任务。
精确可靠的光谱红移确定是大范围光度巡天的关键挑战之一。传统方法依赖机器学习模型，在同时具备光度与光谱数据的校准样本上进行训练。本文提出一种基于条件生成对抗网络（CGAN）的新方法，用于估算星系的光谱红移。该方法不仅能给出红移的点估计，还能提供概率密度估计。模型在暗能量巡天（DES Y1）数据集上进行了测试，并与混合密度网络（MDN）等现有方法进行对比。结果表明，尽管MDN表现略优，但CGAN的性能指标接近其水平，展现出在光谱红移估计中应用的潜力。
原文摘要 · Abstract (English)
Accurate and reliable photometric redshift determination is one of the key aspects for wide-field photometric surveys. Determination of photometric redshift for galaxies, has been traditionally solved by use of machine-learning and artificial intelligence techniques trained on a calibration sample of galaxies, where both photometry and spectrometry are available. On this paper, we present a new algorithmic approach for determining photometric redshifts of galaxies using Conditional Generative Adversarial Networks (CGANs). The proposed implementation is able to determine both point-estimation and probability-density estimations for photometric redshifts. The methodology is tested with data from Dark Energy Survey (DES) Y1 data and compared with other existing algorithm such as a Mixture Density Network (MDN). Although results obtained show a superiority of MDN, CGAN quality-metrics are close to the MDN results, opening the door to the use of CGAN at photometric redshift estimation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。