Machine Learning applied to Multifrequency Data in Astrophysics: Blazar Classification

Abstract

The study of machine learning (ML) techniques for the autonomous classification of astrophysical sources is of great interest, and we explore its applications in the context of a multifrequency data-frame. We test the use of supervised ML to classify blazars according to its synchrotron peak frequency, either lower or higher than 10${}^{15}$Hz. We select a sample with 4178 blazars labelled as 1279 high synchrotron peak (HSP: $\nu$-peak > 10${}^{15}$Hz) and 2899 low synchrotron peak (LSP: $\nu$-peak < 10${}^{15}$Hz). A set of multifrequency features were defined to represent each source, that includes spectral slopes (${\alpha }_{{\nu }_1,{\nu }_2}$) between the radio, infra-red, optical, and X-ray bands, also considering IR colours. We describe the optimisation of five ML classification algorithms that classify blazars into LSP or HSP: Random Forests (RF), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Gaussian Naive Bayes (GNB) and the Ludwig auto-ML framework. In our particular case, the SVM algorithm had the best performance, reaching 93% of balanced-accuracy. A joint-feature permutation test revealed that the spectral slopes alpha-radio-IR and alpha-radio-optical are the most relevant for the ML modelling, followed by the IR colours. This work shows that ML algorithms can distinguish multifrequency spectral characteristics and handle the classification of blazars into LSPs and HSPs. It is a hint for the potential use of ML for the autonomous determination of broadband spectral parameters (as the synchrotron $\nu$-peak), or even to search for new blazars in all-sky databases.

References in corpus (49)

• Scikit-learn: Machine Learning in Python
• SMOTE: Synthetic Minority Over-sampling Technique
• Gaia Data Release 2. Summary of the contents and survey properties
• Unified Schemes for Radio-Loud Active Galactic Nuclei
• The Eleventh and Twelfth Data Releases of the Sloan Digital Sky Survey: Final Data from SDSS-III
• The USNO-B Catalog
• Composite Quasar Spectra From the Sloan Digital Sky Survey
• The VizieR database of Astronomical Catalogues
• Fermi Large Area Telescope Fourth Source Catalog
• The Spectral Energy Distribution of Fermi bright blazars
• SUMSS: A Wide-Field Radio Imaging Survey of the Southern Sky. II. The Source Catalogue
• Active Galactic Nuclei: what's in a name?
• The Connection between X-ray- and Radio-Selected BL Lacertae Objects
• The Chandra Source Catalog
• The Third Catalog of Active Galactic Nuclei Detected by the Fermi Large Area Telescope
• Second ROSAT all-sky survey (2RXS) source catalogue
• Roma-BZCAT: A multifrequency catalogue of Blazars
• Data Mining and Machine Learning in Astronomy
• The Fourth Catalog of Active Galactic Nuclei Detected by the Fermi Large Area Telescope
• 3FHL: The Third Catalog of Hard Fermi-LAT Sources
• The XMM-Newton serendipitous survey. VII. The third XMM-Newton serendipitous source catalogue
• The 5th edition of the Roma-BZCAT. A short presentation
• The Last of FIRST: The Final Catalog and Source Identifications
• The first XMM-Newton slew survey catalogue: XMMSL1
• A simplified view of blazars: clearing the fog around long-standing selection effects
• The Hubble Space Telescope Wide Field Camera 3 Early Release Science data: Panchromatic Faint Object Counts for 0.2-2 microns wavelength
• Near-infrared template spectra of normal galaxies: k-corrections, galaxy models and stellar populations
• 1SXPS: A deep Swift X-ray Telescope point source catalog with light curves and spectra
• The 3HSP catalogue of Extreme & High Synchrotron Peaked Blazars
• Infrared Colors of the gamma-ray detected blazars
• 2WHSP: A catalog of HE and VHE gamma-ray blazars and blazar candidates
• Diffuse $\gamma$-ray emission from unresolved BL Lac objects
• 1WHSP: an IR-based sample of $\sim$1,000 VHE $\gamma$-ray blazar candidates
• ATPMN: accurate positions and flux densities at 5 and 8 GHz for 8,385 sources from the PMN survey
• Blazar Flaring Patterns (B-FlaP): Classifying Blazar Candidates of Uncertain type in the third Fermi-LAT catalog by Artificial Neural Networks
• The ASKAP/EMU Source Finding Data Challenge
• The Gamma-ray Blazar Quest: new optical spectra, state of art and future perspectives
• Machine learning Applied to Star-Galaxy-QSO Classification and Stellar Effective Temperature Regression
• A simplified view of blazars: contribution to the X-ray and gamma-ray cosmic backgrounds
• Research and characterisation of blazar candidates among the Fermi/LAT 3FGL catalogue using multivariate classifications
• Evaluating the optical classification of Fermi BCUs using machine learning
• The first Super Massive Black Holes: indications from models for future observations
• Extreme blazars
• Ludwig: a type-based declarative deep learning toolbox
• Classification of Blazar Candidates of Uncertain Type from the Fermi LAT 8-Year Source Catalog with an Artificial Neural Network
• VisIVO - Integrated Tools and Services for Large-Scale Astrophysical Visualization
• Extreme & High Synchrotron Peak Blazars beyond 4FGL: The 2BIGB $\gamma$-ray catalogue
• Evaluating Optical Classification for {\em Fermi} Blazar Candidates with a Statistical method using Broadband Spectral Indices
• The Open Universe Initiative

Cited by in corpus (6)

• Data mining techniques on astronomical spectra data. II : Classification Analysis
• A machine learning classifier for LOFAR radio galaxy cross-matching techniques
• Gradient boosting decision trees classification of blazars of uncertain type in the fourth Fermi-LAT catalog
• Searching for TeV Candidates in 4LAC High-synchrotron-peaked Frequency BL Lac Objects
• Selection of powerful radio galaxies with machine learning
• Deep Learning Blazar Classification based on Multi-frequency Spectral Energy Distribution Data