Separating wheat from chaff: Big data challenges from the Legacy Survey of Space and Time

The Legacy Survey of Space and Time (LSST) on the Vera C. Rubin Observatory will generate a data deluge: millions of astronomical transients and variable sources will need to be classified from their light curves. To study the physics of these objects, or to use them as cosmic beacons to measure the acceleration of the universe, requires classifying the objects into different types. This labelling by their optical photometry alone (rather than obtaining a spectrum of the objects signal), has long been a problem of interest in astronomy, and the issue of classification under sparse data is common across different fields in physics.  So the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC) was born. PLAsTiCC brings a wide range of astronomical transient models together, simulated under LSST-like conditions for the first time. The challenge was delivered to the community through the Kaggle data science platform, and was designed to stimulate interest in time-series photometric classification beyond just astronomers, to discover new approaches and methodologies that will advance the LSST science case. I will give an overview of the road to PLAsTiCC, the models and the validation of the data, present the results from PLAsTiCC (and tell you about how you can use this data set if you want to try your hand at data science!), and discuss the science impact of classification on photometric cosmology with Type Ia supernovae. I'll also discuss the Canadian context for participation in the Rubin Observatory.