Deep Learning of Quasar Lightcurves in the LSST Era

• Published in: Universe (Basel) Vol. 9; no. 6; p. 287
• Main Authors: Kovačević, Andjelka B., Ilić, Dragana, Popović, Luka Č., Andrić Mitrović, Nikola, Nikolić, Mladen, Pavlović, Marina S., Čvorović-Hajdinjak, Iva, Knežević, Miljan, Savić, Djordje V.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2023
• Subjects: Accretion disks; Algorithms; astronomy data modeling; astrostatistics techniques; computational astronomy; Deep learning; Gravitational waves; high-energy astrophysics; Light; Machine learning; Neural networks; Quasars; time series analysis
• ISSN: 2218-1997; 2218-1997
• DOI: 10.3390/universe9060287

Deep learning techniques are required for the analysis of synoptic (multi-band and multi-epoch) light curves in massive data of quasars, as expected from the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). In this follow-up study, we introduce an upgraded version of a conditional neural process (CNP) embedded in a multi-step approach for the analysis of large data of quasars in the LSST Active Galactic Nuclei Scientific Collaboration data challenge database. We present a case study of a stratified set of u-band light curves for 283 quasars with very low variability ∼0.03. In this sample, the CNP average mean square error is found to be ∼5% (∼0.5 mag). Interestingly, besides similar levels of variability, there are indications that individual light curves show flare-like features. According to the preliminary structure–function analysis, these occurrences may be associated with microlensing events with larger time scales of 5–10 years.