Using machine learning to study the kinematics of cold gas in galaxies
Using machine learning to study the kinematics of cold gas in galaxies
复制标题
DOI：
10.1093/mnras/stz3097
复制
发表时间：
2019-11
影响因子：
4.8
通讯作者：
James M. Dawson;T. Davis;E. Gomez;Justus Schock;N. Zabel;T. Williams
中科院分区：
文献类型：
--
作者：
James M. Dawson;T. Davis;E. Gomez;Justus Schock;N. Zabel;T. Williams
下一代干涉仪，如平方公里阵列，将获得有关星系中冷气体运动学的大量信息。考虑到这些设施产生的数据量，天文学家将需要快速、可靠的工具来对真实的输入数据进行信息过滤和分类。在本文中，我们使用机器学习技术与流体动力学模拟训练集来预测星系中冷气体的运动学行为，并在模拟和真实的干涉数据上测试这些模型。利用卷积自动编码器的强大功能，我们将人眼或标准工具无法实现的运动学特征嵌入到三维空间中，并区分受干扰和定期旋转的冷气结构。我们简单的二元分类器预测的无噪声，模拟，星系与召回85\%$的圆形，并执行预期的观测CO和HI速度图，具有启发式的准确性为95\%$。当改变添加到输入数据中的噪声水平时，模型输出表现出可预测的行为，并且我们能够解释映射空间的所有维度的作用。我们的模型还允许快速预测输入星系的位置角，其1σ不确定度范围为±17○至±23○（对于倾角分别为82.5○至32.5○的星系），这可能对运动学建模采样器的初始参数化有用。机器学习模型，如本文中概述的模型，可能在不久的将来适用于SKA科学用途。
Next generation interferometers, such as the Square Kilometre Array, are set to obtain vast quantities of information about the kinematics of cold gas in galaxies. Given the volume of data produced by such facilities astronomers will need fast, reliable, tools to informatively filter and classify incoming data in real time. In this paper, we use machine learning techniques with a hydrodynamical simulation training set to predict the kinematic behaviour of cold gas in galaxies and test these models on both simulated and real interferometric data. Using the power of a convolutional autoencoder we embed kinematic features, unattainable by the human eye or standard tools, into a three-dimensional space and discriminate between disturbed and regularly rotating cold gas structures. Our simple binary classifier predicts the circularity of noiseless, simulated, galaxies with a recall of $85\%$ and performs as expected on observational CO and HI velocity maps, with a heuristic accuracy of $95\%$. The model output exhibits predictable behaviour when varying the level of noise added to the input data and we are able to explain the roles of all dimensions of our mapped space. Our models also allow fast predictions of input galaxies’ position angles with a 1σ uncertainty range of ±17○ to ±23○ (for galaxies with inclinations of 82.5○ to 32.5○, respectively), which may be useful for initial parameterisation in kinematic modelling samplers. Machine learning models, such as the one outlined in this paper, may be adapted for SKA science usage in the near future.