Poster Open Access

Finding flares with recurrent deep neural networks

Vida, Krisztián; Bódi, Attila; Szklenár, Tamás; Seli, Bálint

Stellar flares are an important aspect of magnetic activity—both for stellar evolution and circumstellar habitability viewpoints—but automatically and accurately finding them is still a challenge to researchers in the Big Data era of astronomy. We present an experiment to detect flares in space-borne photometric data using deep neural networks. Using a set of artificial data and real photometric data we trained a set of neural networks, and found that the best performing architectures were the recurrent neural networks (RNNs) using Long Short-Term Memory (LSTM) layers. The aim for the trained network is not just detect flares but also be able to distinguish typical false signals (e.g. maxima of RR Lyr stars) from real flares.

BS was supported by the ÚNKP-19-3 New National Excellence Program of the Ministry for Innovation and Technology. This project has been supported by the Lendület Program of the Hungarian Academy of Sciences, project No. LP2018-7/2020, the NKFI KH-130526, NKFI K-131508, and 2019-2.1.11-TÉT-2019-00056 grants. On behalf of the Analysis of space-borne photometric data project we thank for the usage of MTA Cloud that helped us achieve the results published in this paper. Authors acknowledge the financial support of the Austrian-Hungarian Action Foundation (95öu3, 98öu5, 101öu13).
Files (725.0 kB)
Name Size
flatwrm2.pdf
md5:3b09129f7cf3499650cbe97aa9be3b63
725.0 kB Download
87
96
views
downloads
All versions This version
Views 8787
Downloads 9696
Data volume 69.6 MB69.6 MB
Unique views 8585
Unique downloads 9090

Share

Cite as