arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.03224astro-ph.GA
收藏

COSMOS2025: 0 < z < 3 早型和晚型星系的机器学习分类

COSMOS2025: Machine Learning Classification of Early- and Late-type Galaxies at 0 < z < 3

Institute for Advanced Studies in Basic Sciences (IASBS)（基础科学高等研究院）

Vahid Asadi, Najmeh Sheikhi

备注：
17 pages, 15 figures, 6 tables
发表信息：
The Astrophysical Journal, 1002:26 (15pp), 2026 May 1
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出一种快速、可解释的机器学习框架，利用 COSMOS2025 的宽波段颜色在 0<z<3 范围内对早型和晚型星系进行分类，无需图像标签或结构拟合，模拟训练后分类精度高，并揭示了颜色作为形态判据的双峰性。

摘要：

我们提出了一种快速、可解释的机器学习框架，用于对 COSMOS2025 星表中 $0 < z < 3$ 的早型和晚型星系进行分类，无需依赖基于图像的训练标签或计算昂贵的结构拟合。利用圣克鲁兹半解析模型，我们生成了一个训练集，其中包含由核球-总质量比和比恒星形成率定义的可靠形态标签。通过注入来自 COSMOS2025 的真实光度噪声，我们弥合了模拟与观测之间的域差距。基于 66 个宽波段颜色训练的 CatBoostClassifier 在模拟域中表现出色，晚型星系的精确率/召回率达到 98%，早型星系的精确率为 91%，召回率为 88%。将该模型应用于 44,132 个 COSMOS2025 星系，揭示出显著的双峰性：仅有约 6% 的星系具有中等概率（$0.3 < P( ext{早型}) < 0.7$）——与模拟中观测到的比例几乎相同。这表明宽波段颜色是决定性的形态判别依据，其余 94% 的星系被高置信度分类。与独立的核球+盘分解验证相比，总体准确率达到 70%，其中晚型星系的纯度为 78%，完备度为 74%。最重要的颜色特征 F277W-F444W 反映了年老和年轻恒星种群之间的预期光学/近红外对比。整个流程在标准硬件上不到 30 分钟即可完成，表明基于模拟训练的颜色分类器为大规模下一代巡天提供了一种可扩展、物理可解释的近似形态学途径。

英文摘要：

We present a fast, interpretable machine learning framework to classify early- and late-type galaxies in the COSMOS2025 catalog at $0 < z < 3$, without relying on image-based training labels or computationally expensive structural fitting. Using the Santa Cruz Semi-Analytic Model, we generate a training set with secure morphological labels defined by bulge-to-total mass ratio and specific star formation rate. We bridge the simulation-to-observation domain gap by injecting realistic photometric noise derived from COSMOS2025. A CatBoostClassifier trained on 66 broadband colors achieves excellent performance in the simulated domain, recovering late-types with 98\% precision/recall and early-types with 91\% precision and 88\% recall. Applied to 44,132 COSMOS2025 galaxies, the model reveals a striking bimodality: only about 6\% of galaxies receive intermediate probabilities ($0.3 < P(\text{Early type}) < 0.7$) -- nearly identical to the fraction observed in the simulation. This demonstrates that broadband colors are a decisive morphological discriminant, with the remaining 94\% classified at high confidence. Validation against independent bulge+disk decompositions yields 70\% overall accuracy, with late-types identified at 78\% purity and 74\% completeness. The most important color feature, F277W-F444W, reflects the expected optical/NIR contrast between old and young stellar populations. The full pipeline completes in under 30 minutes on standard hardware, demonstrating that simulation-trained color-based classifiers offer a scalable, physically interpretable route to approximate morphology for large next-generation surveys.

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。

↑