Modeling quasar variability through self-organizing map-based process

Abstract

Conditional Neural Process (QNPy) has shown to be a good tool for modeling quasar light curves. However, given the complex nature of the source and hence the data represented by light curves, processing could be time-consuming. In some cases, accuracy is not good enough for further analysis. In an attempt to upgrade QNPy, we examine the effect of the prepossessing quasar light curves via the Self-Organizing Map (SOM) algorithm on modeling a large number of quasar light curves. After applying SOM on SWIFT/BAT data and modeling curves from several clusters, results show the Conditional Neural Process performs better after SOM classification. We conclude that SOM classification of quasar light curves could be a beneficial prepossessing method for QNPy.

published in Serbian astronomical journal

References in corpus (10)

• The All-Sky Automated Survey for Supernovae (ASAS-SN) Light Curve Server v1.0
• The Discovery of the First "Changing Look" Quasar: New Insights into the Physics & Phenomenology of AGN
• Swift BAT Survey of AGN
• Long-term optical spectral monitoring of a changing-look AGN NGC 3516 I: Continuum and broad-line flux variability
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• Gaussian-mixture-model-based cluster analysis of gamma-ray bursts in the BATSE catalog
• A Method to Measure the Unbiased Decorrelation Timescale of the AGN Variable Signal from Structure Functions
• Hierarchical Clustering in Astronomy
• Latent Stochastic Differential Equations for Modeling Quasar Variability and Inferring Black Hole Properties
• A fast version of the k-means classification algorithm for astronomical applications