arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.06016astro-ph.GA
收藏

GAMMA:质量、金属丰度与年龄星系属性数据集

GAMMA: Galactic Attributes of Mass, Metallicity, and Age Dataset

Ufuk Çakır, Tobias Buck

AI总结:

本文发布面向机器学习的 GAMMA 星系数据集及扩展代码,涵盖 11 727 个星系的年龄、金属丰度和质量图,并通过 PCA 验证其高效降维与形态重建能力。

摘要:

我们介绍 GAMMA(Galactic Attributes of Mass, Metallicity, and Age,质量、金属丰度与年龄星系属性)数据集,这是一个为机器学习应用量身定制的综合性星系数据集合。该数据集提供 11 727 个星系的详细二维地图和三维数据立方体,捕捉关键属性:恒星年龄、金属丰度和质量。在发布数据集的同时,我们还公开了代码,用于从原始模拟套件中提取任何其他恒星或气体属性,从而将数据集扩展到这些初始属性之外,确保其适用于各种计算任务。GAMMA 非常适合特征提取、聚类和回归任务,为利用计算方法探索星系结构提供了独特视角,并成为连接天体物理模拟与科学机器学习(ML)领域的桥梁。作为首个基准测试,我们对该数据集应用了主成分分析(PCA)。我们发现,PCA 能够用少量成分有效捕捉星系的关键形态特征。对于二维图像(三维数据立方体),我们实现了约 200 倍(3650 倍)的降维,且重建精度误差低于 5%。

英文摘要:

We introduce the GAMMA (Galactic Attributes of Mass, Metallicity, and Age) dataset, a comprehensive collection of galaxy data tailored for Machine Learning applications. This dataset offers detailed 2D maps and 3D cubes of 11 727 galaxies, capturing essential attributes: stellar age, metallicity, and mass. Together with the dataset, we publish our code to extract any other stellar or gaseous property from the raw simulation suite to extend the dataset beyond these initial properties, ensuring versatility for various computational tasks. Ideal for feature extraction, clustering, and regression tasks, GAMMA offers a unique lens to explore galactic structures using computational methods and is a bridge between astrophysical simulations and the field of scientific machine learning (ML). As a first benchmark, we applied Principal Component Analysis (PCA) to this dataset. We find that PCA effectively captures the key morphological features of galaxies with a small number of components. We achieve a dimensionality reduction by a factor of approximately 200 (3650) for 2D images (3D cubes) with a reconstruction accuracy below 5%.

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。

↑