Detecting outliers in astronomical images with deep generative networks
Detecting outliers in astronomical images with deep generative networks
复制标题
DOI：
10.1093/mnras/staa1647
复制
发表时间：
2020-08-01
影响因子：
4.8
通讯作者：
Zanisi, Lorenzo
中科院分区：
文献类型：
--
作者：
Margalef-Bentabol, Berta;Huertas-Company, Marc;Zanisi, Lorenzo
随着未来大数据调查的出现，用于无监督发现的自动化工具变得越来越必要。在这项工作中，我们探索了深度生成网络在天文成像数据集中检测异常值的能力。这种生成模型的主要优点是它们能够直接从像素空间学习复杂的表示。因此，这些方法使我们能够寻找微妙的形态偏差，通常错过了更传统的基于矩的方法。我们使用生成模型来学习由训练集定义的预期数据的表示，然后通过寻找给定对象的最佳重建来寻找与学习的表示的偏差。在第一个概念验证工作中，我们将我们的方法应用于两个不同的测试用例。我们首先表明，从一组模拟星系中，如果我们只使用孤立星系的样本来训练我们的网络，我们就能够检测到90%的合并星系。然后，我们探讨如何提出的方法可以用来比较观测和流体动力学模拟识别观测到的星系没有很好地代表在模型中。这里使用的代码可以在https://github.com/carlamb/astronomical-outliers-WGAN上找到。
With the advent of future big-data surveys, automated tools for unsupervised discovery are becoming ever more necessary. In this work, we explore the ability of deep generative networks for detecting outliers in astronomical imaging data sets. The main advantage of such generative models is that they are able to learn complex representations directly from the pixel space. Therefore, these methods enable us to look for subtle morphological deviations which are typically missed by more traditional moment-based approaches. We use a generative model to learn a representation of expected data defined by the training set and then look for deviations from the learned representation by looking for the best reconstruction of a given object. In this first proof-of-concept work, we apply our method to two different test cases. We first show that from a set of simulated galaxies, we are able to detect similar to 90 per cent of merging galaxies if we train our network only with a sample of isolated ones. We then explore how the presented approach can be used to compare observations and hydrodynamic simulations by identifying observed galaxies not well represented in the models. The code used in this is available at https://github.com/carlamb/astronomical-outliers-WGAN.