论文标题
使用深度学习与真实和模拟数据检测到的环星系的分析
Analysis of Ring Galaxies Detected Using Deep Learning with Real and Simulated Data
论文作者
论文摘要
了解具有非典型环状结构的环星系的形成和演变，对于促进黑洞和星系动力学的知识至关重要。但是，当前的环形星系目录是有限的，因为手动分析需要数月才能积累可观的环样本。本文提出了一个卷积神经网络（CNN），以识别未分类样品的环星系。在100,000个模拟星系上对CNN进行了训练，转移到了真实星系样本中，并应用于先前未分类的数据集中，以生成一个环目录，然后手动验证。还采用了使用生成对抗网络（GAN）来模拟星系图像的数据增强。由此产生的目录包含1967年的环形星系。然后从它们的光度法中估算这些星系的特性，并将其与环形动物园2的环目录进行比较。但是，由于实际数据集中的环严重失衡，该模型的精度目前受到限制，导致41.1％的假阳性率显着，这对数十亿星系的调查中的大规模应用构成了挑战。这项研究表明，使用低训练数据优化ML管道的稀有形态的潜力，并强调了进一步的细化，以增强广泛的调查的精度，例如Vera Rubin天文台对空间和时间的调查。
Understanding the formation and evolution of ring galaxies, which possess an atypical ring-like structure, is crucial for advancing knowledge of black holes and galaxy dynamics. However, current catalogs of ring galaxies are limited, as manual analysis takes months to accumulate an appreciable sample of rings. This paper presents a convolutional neural network (CNN) to identify ring galaxies from unclassified samples. A CNN was trained on 100,000 simulated galaxies, transfer learned to a sample of real galaxies, and applied to a previously unclassified dataset to generate a catalog of rings which was then manually verified. Data augmentation with a generative adversarial network (GAN) to simulate images of galaxies was also employed. The resulting catalog contains 1967 ring galaxies. The properties of these galaxies were then estimated from their photometry and compared to the Galaxy Zoo 2 catalog of rings. However, the model's precision is currently limited due to a severe imbalance of rings in real datasets, leading to a significant false-positive rate of 41.1%, which poses challenges for large-scale application in surveys imaging billions of galaxies. This study demonstrates the potential of optimizing ML pipelines with low training data for rare morphologies and underscores the need for further refinements to enhance precision for extensive surveys like the Vera Rubin Observatory Legacy Survey of Space and Time.
