使用神经网络检测HI自吸收
Detecting HI Self-Absorption using Neural Networks
浏览论文内容
中文总结 AI 辅助
本文提出一种轻量级卷积神经网络，无需假设或辅助数据即可检测HI自吸收特征并推断速度，在合成数据上达到96.5%准确率，并能实时处理观测数据，支持下一代设施的大规模冷HI探测。
中文摘要 AI 辅助
冷原子氢在星际气体的生命周期中扮演着关键角色。它是星系内外暖弥散气体与驱动恒星形成的冷分子气体之间凝聚和冷却过程的中间相。21厘米发射线中的HI自吸收是冷HI气体最直接的观测示踪物，不需要连续谱背景源，但其系统性提取仍然是一个长期存在的挑战。现有的自吸收识别方法依赖于主观的目视检查或对底层发射的建模，这使得可重复、彻底和大规模的应用变得困难。我们提出了一种轻量级卷积神经网络，旨在检测自吸收特征并通过事后过程推断其速度，无需对底层发射进行假设或使用辅助数据。该神经网络在合成发射谱上训练，在保留的合成数据上达到了96.5%的准确率、96.0%的精确率和97.0%的召回率。将该网络应用于来自Riegel--Crutcher云和银道面方向巨分子纤维区域的观测21厘米发射数据，与之前的分析和辅助13CO发射数据相比，该网络恢复了已知自吸收结构的空间分布和速度。至关重要的是，该神经网络计算效率高，在单个消费级笔记本电脑GPU上每秒处理约15,000个谱的检测，使得在下一代设施如平方公里阵列预期的数据速率下能够实现实时冷HI检测。
英文摘要
Cold atomic hydrogen plays a crucial role in the life cycle of interstellar gas. It serves as the intermediary phase in the condensation and cooling processes that bridge the warm diffuse gas in and around galaxies, and the cold molecular gas that drives star formation. HI self-absorption in the 21-cm emission line is the most direct observational tracer of cold HI gas that does not require a continuum background source, yet its systematic extraction remains a long-standing challenge. Existing methods of self-absorption identification rely on subjective by-eye inspection or modelling of the underlying emission, making repeatable, thorough, and large-scale applications difficult. We present a lightweight convolutional neural network designed to detect self-absorption features and infer their velocities via a post-hoc process, without assumptions about the underlying emission or the use of ancillary data. Trained on synthetic emission spectra, the neural network achieves 96.5 per cent accuracy, 96.0 per cent precision, and 97.0 per cent recall on held-out synthetic data. Applied to observed 21-cm emission data from the Riegel--Crutcher cloud and giant molecular filament regions towards the Galactic Plane, the network recovers the spatial distributions and velocities of known self-absorption structures when compared to previous analyses and ancillary 13CO emission data. Crucially, the neural network is computationally efficient, processing detections for ~15,000 spectra per second on a single consumer laptop GPU, enabling real-time cold HI detection at the data rates anticipated by next-generation facilities such as the Square Kilometre Array.
发表机构
- The Australian National University（澳大利亚国立大学）
- SKA Observatory（平方公里阵列望远镜观测站）
- Google Australia（谷歌澳大利亚）
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université de Paris（巴黎高等师范学院物理实验室，ENS，巴黎文理研究大学，法国国家科学研究中心，索邦大学，巴黎大学）
- Macquarie University（麦考瑞大学）
- Australia Telescope National Facility, CSIRO Space & Astronomy（澳大利亚望远镜国家设施，CSIRO空间与天文）
- Korea Astronomy and Space Science Institute（韩国天体宇宙科学研究所）
机构由 AI 辅助整理，请以论文原文为准。
