Machine Learning for LSST-scale Citizen Science

Citizen Science - the involvement of volunteers in analysing data - has proved an effective strategy in projects as diverse as galaxy morphology, the search for exoplanets and transient detection and classification. This project involves working directly with the team of web developers and scientists responsible for the world-leading (and Oxford led) Zooniverse.org platform to devise new strategies for effective citizen science in the run up to first light for the Large Synoptic Survey Telescope.
With millions of transient alerts expected each night during the survey's operation, any effective search will require the combination of machine learning with human classifications. This project will focus on methods for detecting and following up on the most unusual objects and events, deploying advanced machine learning techniques for identifying interesting outliers.
Using datasets from existing surveys, the student attached to this project might test and develop appropriate computer vision routines, explore the design of citizen science projects which incorporate their results, or investigate novel modes of combining both. I would also expect a student to contribute to the scientific exploitation of the results from these projects, which will be either related to galaxy morphology or supernovae and other transients.