Neural network architecture for artifacts detection in ZTF survey

Семенихин, Т.А.

Автор: Семенихин Т.А.
Журнал: Системы и средства информатики
Том: 34
Номер: 1
Год издания: 2024
Издательство: ИПИ РАН
Местоположение издательства: М.
Первая страница: 70
Последняя страница: 79
DOI: 10.14357/08696527240106
Аннотация: 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.
Добавил в систему: Семенихин Тимофей Александрович

	ИСТИНА	Войти в систему Регистрация
	ИПМех РАН
	Главная Поиск Статистика О проекте Помощь

ИСТИНА

ИПМех РАН

Neural network architecture for artifacts detection in ZTF surveyстатья

Прикрепленные файлы