Large modern surveys require efficient review of data in order to find transient sources such as supernovae, and to distinguish such sources from artefacts and noise. Much effort has been put into the development of automatic algorithms, but surveys still rely on human review of targets. This paper presents an integrated system for the identification of supernovae in data from Pan-STARRS1, combining classifications from volunteers participating in a citizen science project with those from a convolutional neural network. The unique aspect of this work is the deployment, in combination, of both human and machine classifications for near real-time discovery in an astronomical project. We show that the combination of the two methods outperforms either one used individually. This result has important implications for the future development of transient searches, especially in the era of LSST and other large-throughput surveys.
10 pages, 9 figures, submitted to MNRAS