Realtime Astronomical Time-series Classification and Broadcast Pipeline

The Transients Classification Pipeline (TCP) is a Berkeley-led, Python based project which federates data streams from multiple surveys and observatories, classifies with machine learning and astronomer defined science priors, and broadcasts sources of interest to various science clients. This multi-node pipeline uses Python wrapped classification algorithms, some of which will be generated by training machine learning software using astronomer classified time-series data. Dozens of context and time-series based features are generated in real time for astronomical sources using a variety of Python packages and remote services.