Skip to yearly menu bar Skip to main content

Workshop: 2nd ICML Workshop on Machine Learning for Astrophysics

A Multi-input Convolutional Neural Network to Automate and Expedite Bright Transient Identification for the Zwicky Transient Facility

Nabeel Rehemtulla · Adam Miller · Michael Coughlin · Theophile Jegou Du Laz


The Bright Transient Survey (BTS) relies on visual inspection ("scanning") to select sources for accomplishing its mission of spectroscopically classifying all bright extragalactic transients found by the Zwicky Transient Facility (ZTF). We present a multi-input convolutional neural network to provide a bright transient score to individual ZTF detections using their image data and 16 extracted features. Our model has the ability to eliminate the need for human scanning by automatically identifying and requesting spectroscopic observations of new bright (m<18.5 mag) transient candidates. In validation, the model is 92% pure and 97% complete, outperforming human scanners. The model is now running in real-time on all new ZTF alert packets allowing for real-time and real-world validation.

Chat is not available.