Zwicky's Quirky Transients

Large area surveys like the Zwicky Transient Facility are overwhelming for individual researchers as hundreds of thousands of varying objects are found. A fraction of these are artifacts (bogus). This project is to mark such bogus objects apart from real/genuine (astronomically varying) sources. You can help us do that. The classifications here will form input to machine learning algorithms. Once trained, the machine learning algorithm will provide a 'real'-ness to each object, a number between 0 and 1, called the RB-score. Improving the machine learning performance at all magnitudes and in crowded fields will help the ZTF project achieve its science goals. Real objects are of two types: (a) transients that are not persistent, and (b) variables that vary in brightness but are always detected. Bogus objects for the purpose of this exercise also come in two flavors: (a) artifacts from the instrumental setup, and (b) astronomical objects with subtraction artifacts. Details on how real and bogus objects look are in the tutorial and the field guide. Please take a look before starting.

Acknowledgements:

Based on observations obtained with the Samuel Oschin Telescope 48-inch and the 60-inch Telescope at the Palomar Observatory as part of the Zwicky Transient Facility project, a scientific collaboration among the California Institute of Technology, the Oskar Klein Centre, the Weizmann Institute of Science, the University of Maryland, the University of Washington, Deutsches Elektronen-Synchrotron, the University of Wisconsin-Milwaukee, and the TANGO Program of the University System of Taiwan. Further support is provided by the U.S.\ National Science Foundation under Grant No.\ AST-1440341. Part of this research was carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration.