Dataset for the Real/Bogus classifier in the Tomo-e Gozen transient survey

This is a subset of the dataset used in the following paper:
Ichiro Takahashi, Ryo Hamasaki, Naonori Ueda, Masaomi Tanaka, Nozomu Tominaga, Shigeyuki Sako, Ryou Ohsawa, Naoki Yoshida, Deep-learning real/bogus classification for the Tomo-e Gozen transient survey, Publications of the Astronomical Society of Japan, 2022;, psac047, https://doi.org/10.1093/pasj/psac047

This dataset is available for training and testing the Real/Bogus classifier that classifies real transient objects and false detections in the Tomo-e Gozen transient survey. The source code for training is available at https://github.com/ichiro-takahashi/tomoe-realbogus.

The dataset consists of images (npy) and meta data (csv). Each sample of the image data includes a set of three images: reference image, observed new image, and subtracted image. Each of them is a cutout image around the transient candidate (29×29 pixels).

The training data are divided into the following four parts, all of which must be unzipped into the same directory.

tomoerb_train_Q1.tar.gz

tomoerb_train_Q2.tar.gz

tomoerb_train_Q3.tar.gz

tomoerb_train_Q4.tar.gz

The unzipped data are separated according to the detector ID of the Tomo-e Gozen camera (111-444).

The meta data contain the following labels:

rand_artificial_real: Real

galx_artificial_real:  Real

artifact:                 Bogus

The test data are separated into real objects and bogus objects, and the meta data contain the detector ID.

The number of samples in the training and test data are as follows:

Training data:

Real:    1224710

Bogus: 2031132

Test data:

Real:            292

Bogus:   255711

Acknowledgement:

This work has been supported by Japan Science and Technology Agency (JST)  AIP Acceleration Research Grant Number JP20317829 and the Japan Society for the Promotion of Science (JSPS) KAKENHI grants 21H04491, 18H05223, and 17H06363.

This work is supported in part by the Optical and Near-Infrared Astronomy Inter-University Cooperation Program.

The Pan-STARRS1 Surveys (PS1) and the PS1 public science archive have been made possible through contributions by the Institute for Astronomy, the University of Hawaii, the Pan-STARRS Project Office, the Max-Planck Society and its participating institutes, the Max Planck Institute for Astronomy, Heidelberg and the Max Planck Institute for Extraterrestrial Physics, Garching, The Johns Hopkins University, Durham University, the University of Edinburgh, the Queen's University Belfast, the Harvard-Smithsonian Center for Astrophysics, the Las Cumbres Observatory Global Telescope Network Incorporated, the National Central University of Taiwan, the Space Telescope Science Institute, the National Aeronautics and Space Administration under Grant No. NNX08AR22G issued through the Planetary Science Division of the NASA Science Mission Directorate, the National Science Foundation Grant No. AST-1238877, the University of Maryland, Eotvos Lorand University (ELTE), the Los Alamos National Laboratory, and the Gordon and Betty Moore Foundation.