Systems and Means of Informatics
2024, Volume 34, Issue 1, pp pp 70-79
NEURAL NETWORK ARCHITECTURE FOR ARTIFACTS DETECTION IN ZTF SURVEY
Abstract
Today, astronomers are faced with a challenge of handling vast volume of data as modern astronomical surveys are capable of generating terabytes of data in a single night. One of such survey is the Zwicky Transient Facility (ZTF), an automated sky survey that provides approximately a million alerts per observational night. However, a significant part of the detected objects turn out to be artifacts, i. e., phenomena of a nonastrophysical origin. Therefore, specialists must invest time in manually classifying these objects as there is currently no efficient method that can perform this task without human intervention.
The goal of the work is the development of an algorithm to predict whether a light curve from the ZTF data releases (DRs) has a bogus nature or not, based on the sequence of frames. A labeled dataset provided by experts from SNAD team was utilized, comprising 2230 frames series. Due to substantial size of the frame sequences, the application of a variational autoencoder (VAE) was deemed necessary for mapping the images into lower-dimensional vectors.
For the task of binary classification based on sequences of compressed frame vectors, a recurrent neural network (RNN) was employed. Several neural network models were considered and the quality metrics were assessed using k-fold crossvalidation. The final performance metrics, including ROC-AUC = 0.86 ± 0.01 and Accuracy = 0.80 ± 0.02, suggest that the model has practical utility. The code implementing the algorithm is available on GitHub.
[+] References (12)
- Bellm, E.C., S. R. Kulkarni, M.J. Graham, et al. 2019. The Zwicky Transient Facility: System overview, performance, and first results. Publ. Astron. Soc. Pac. 131 (995):018002. 19 p. doi: 10.1088/1538-3873/aaecbe.
- ellm, E. C., S. R. Kulkarni, T. Barlow, et al. 2019. The Zwicky Transient Facility: Surveys and scheduler. Publ. Astron. Soc. Pac. 131(1000):068003. 13 p. doi: 10.1088/1538-3873/ab0c2a.
- Bertin, E., and S. Arnouts. 1996. SExtractor: Software for source extraction. Astron. Astrophys. Sup. 117(2):393{404. doi: 10.1051/aas:1996164.
- Malanchev, K. L., M. V. Pruzhinskaya, V. S. Korolev, et al. 2021. Anomaly detection in the Zwicky transient facility DR3. Mon. Not. R. Astron. Soc. 502(4):5147{5175. doi: 10.1093/mnras/stab316.
- Ho-Sang, C., V. A. Villar, S. Cheung, et al. 2022. Searching for anomalies in the ZTF catalog of periodic variable stars. Astrophys. J. 932(2): 118. 21 p. doi: 10.3847/1538- 4357/ac69d4.
- Pruzhinskaya, M.V., E.E.O. Ishida, A. K. Novinskaya, et al. 2023. Supernova search with active learning in ZTF DR3. Astron. Astrophys. 672:A111. 22 p. doi: 10.1051/0004-6361/202245172.
- Deng, L. 2012. The MNIST database of handwritten digit images for machine learning research. IEEE Signal Proc. Mag. 29(6):141A42. doi: 10.1109/MSP.2012.2211477.
- Kingma, D. P., and J. Ba. 2017. Adam: A method for stochastic optimization. arXiv.org. 15 p. Available at: https://arxiv.org/abs/1412.6980 (accessed March 11, 2024).
- Hochreiter, S., and J. Schmidhuber. 1997. Long short-term memory. Neural Comput. 9(8):1735A780. doi: 10.1162/neco.1997.9.8.1735.
- Cho, K., B. Merrienboer, C. Gulcehre, et al. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.org. 15 p. Available at: https://arxiv.org/abs/1406.1078 (accessed March 11, 2024).
- Salehi, S., D. Erdogmus, and A. Gholipour. 2017. Tversky loss function for image segmentation using 3D fully convolutional deep networks. arXiv.org. 9 p. Available at: https://arxiv.org/abs/1706.05721 (accessed March 11, 2024).
- Ishida, E.E.O., M.V. Kornilov, K. L. Malanchev, et al. 2021. Active anomaly detection for time-domain discoveries. Astron. Astrophys. 650:A195. 9 p. doi: 10.1051/0004-6361/202037709.
[+] About this article
Title
NEURAL NETWORK ARCHITECTURE FOR ARTIFACTS DETECTION IN ZTF SURVEY
Journal
Systems and Means of Informatics
Volume 34, Issue 1, pp 70-79
Cover Date
2024-04-10
DOI
10.14357/08696527240106
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
neural network; data analysis; real-bogus classification
Authors
T. A. Semenikhin 
Author Affiliations
Sternberg Astronomical Institute, M. V. Lomonosov Moscow State University, 13 Universitetsky Prosp., Moscow 119234, Russian Federation
|