The missing radial velocities of Gaia: blind predictions for DR3

TL;DR

This paper demonstrates that Bayesian neural networks can accurately predict missing radial velocities of stars in Gaia data, providing a large catalogue of posterior distributions to validate future Gaia DR3 measurements.

Contribution

The authors develop a Bayesian neural network approach to predict missing stellar radial velocities from Gaia data, producing a comprehensive catalogue of posterior distributions.

Findings

Successfully predicted radial velocities for 16 million stars.

Generated posterior distributions with median width of 25 km/s.

Predictions will be validated with upcoming Gaia DR3 data.

Abstract

While Gaia has observed the phase space coordinates of over a billion stars in the Galaxy, in the overwhelming majority of cases it has only obtained five of the six coordinates, the missing dimension being the radial (line-of-sight) velocity. Using a realistic mock dataset, we show that Bayesian neural networks are highly capable of 'learning' these radial velocities as a function of the other five coordinates, and thus filling in the gaps. For a given star, the network outputs are not merely point predictions, but full posterior distributions encompassing the intrinsic scatter of the stellar phase space distribution, the observational uncertainties on the network inputs, and any 'epistemic' uncertainty stemming from our ignorance about the stellar phase space distribution. Applying this technique to the real Gaia data, we generate and publish a catalogue of posteriors (median width: 25 km/s) for the radial velocities of 16 million Gaia DR2/EDR3 stars in the magnitude range 6<G<14.5. Many of these gaps will be filled in very soon by Gaia DR3, which will serve to test our blind predictions. Thus, the primary use of our published catalogue will be to validate our method, justifying its future use in generating an updated catalogue of posteriors for radial velocities missing from Gaia DR3.