Using machine learning to study the kinematics of cold gas in galaxies

Abstract

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 $1\sigma$ uncertainty range of $\pm 17^{\circ }$ to $\pm 23^{\circ }$ (for galaxies with inclinations of $82.5^{\circ }$ to $32.5^{\circ }$, 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.

15 pages, 11 figures

References in corpus (9)

• The EAGLE project: Simulating the evolution and assembly of galaxies and their environments
• The EAGLE simulations of galaxy formation: calibration of subgrid physics and model variations
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• A black-hole mass measurement from molecular gas kinematics in NGC4526
• The EAGLE simulations of galaxy formation: Public release of particle data
• Optimization of Moment Masking for CO Spectral Line Surveys
• The SAMI Galaxy Survey: Asymmetry in Gas Kinematics and its links to Stellar Mass and Star Formation
• Classifying the formation processes of S0 galaxies using Convolutional Neural Networks

Cited by in corpus (3)

• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Using Artificial Intelligence and real galaxy images to constrain parameters in galaxy formation simulations
• A self-supervised, physics-aware, Bayesian neural network architecture for modelling galaxy emission-line kinematics