表示空间中射电源的形态

中文摘要 AI 辅助

理解射电源的形态及其分类仍然具有挑战性。我们此前开发了一种基于自监督学习的深度聚类方法，用于对LOFAR两米巡天DR2中的一个子样本射电源进行分类，这产生了一个标记子集，用于微调分类器集成模型。我们的目标是在包含超过1300万个源的LoTSS-DR3子样本中识别罕见的形态类别，这些类别超出了DR2样本中先前识别的12个类别。我们还旨在表征所得的类别分布。我们应用分类器集成模型来推导样本的类别概率和表示。在类别概率较低的DR3源中，我们在表示空间中搜索新的聚类，此外，我们将这些聚类用作质心来对低概率子集进行分类。我们发现，88%的源属于表示空间中与DR2聚类重合的清晰分离的聚类。在剩余的源中，我们识别出六个额外形态类别的代表，包括翼状源和FR模糊源等罕见形态。所得18个类别的源数量呈现强烈偏态分布，其中四个主导类别占DR3样本的69%，而罕见形态仅占很小一部分。额外形态类别的识别表明，在未探索的数据集中，利用表示学习进行开放集识别是可行的。与将单个源标记为不常见的异常检测不同，该方法识别出新形态类别的代表，为发现新的源种群提供了框架。这种高度偏态的类别分布对构建平衡的训练数据集构成了根本性挑战，并强调了未来观测中需要开放集方法。

英文摘要

Understanding radio source morphologies and their classification remains challenging. We previously developed a deep clustering method based on self-supervised learning to classify a subsample of radio sources from the LOFAR Two-meter Sky Survey DR2. This yielded a labelled subset used to fine-tune an ensemble of classifiers. We aim to identify rare morphological classes in a subsample of LoTSS-DR3, which contains > 13 million sources, beyond the 12 classes previously recognised in the DR2 sample. We further aim to characterise the resulting class distribution. We applied the classifier ensemble to derive class probabilities and representations for our samples. Among DR3 sources with low class probabilities, we searched for new clusters in representation space. Moreover, we use these clusters as centroids to classify the low-probability subset. We found that 88% of the sources fall into clearly separated clusters in representation space, coinciding with the DR2 clusters. Within the remaining sources, we identified representatives of six additional morphological classes, including rare morphologies like winged and FR-ambiguous sources. The number of sources in the resulting 18 classes exhibit a strongly skewed distribution, with four dominant classes constituting 69% of the DR3 sample, while rare morphologies account for only a small fraction. The identification of additional morphological classes shows the possibility of open-set recognition with representation learning in an unexplored dataset. Unlike anomaly detection, which flags individual sources as uncommon, this approach identifies representatives of novel morphological classes, providing a framework for discovering novel source populations. The highly skewed class distribution poses a fundamental challenge for constructing balanced training datasets and highlights the need for open-set approaches in future observations.

发表机构

• Hamburger Sternwarte, Universität Hamburg（汉堡天文台，汉堡大学）

机构由 AI 辅助整理，请以论文原文为准。