English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Next generation interferometers, such as the Square Kilometre Array, are setto obtain vast quantities of information about the kinematics of cold gas ingalaxies. Given the volume of data produced by such facilities astronomers willneed fast, reliable, tools to informatively filter and classify incoming datain real time. In this paper, we use machine learning techniques with ahydrodynamical simulation training set to predict the kinematic behaviour ofcold gas in galaxies and test these models on both simulated and realinterferometric data. Using the power of a convolutional autoencoder we embedkinematic features, unattainable by the human eye or standard tools, into athree-dimensional space and discriminate between disturbed and regularlyrotating cold gas structures. Our simple binary classifier predicts thecircularity of noiseless, simulated, galaxies with a recall of $85\%$ andperforms as expected on observational CO and HI velocity maps, with a heuristicaccuracy of $95\%$. The model output exhibits predictable behaviour whenvarying the level of noise added to the input data and we are able to explainthe roles of all dimensions of our mapped space. Our models also allow fastpredictions of input galaxies' position angles with a $1\sigma$ uncertaintyrange of $\pm17^{\circ}$ to $\pm23^{\circ}$ (for galaxies with inclinations of$82.5^{\circ}$ to $32.5^{\circ}$, respectively), which may be useful forinitial parameterisation in kinematic modelling samplers. Machine learningmodels, such as the one outlined in this paper, may be adapted for SKA scienceusage in the near future.

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