Machine learning methods for constructing probabilistic Fermi-LAT catalogs

Abstract

Classification of sources is one of the most important tasks in astronomy. Sources detected in one wavelength band, for example using gamma rays, may have several possible associations in other wavebands, or there may be no plausible association candidates. In this work we aim to determine the probabilistic classification of unassociated sources in the third Fermi Large Area Telescope (LAT) point source catalog (3FGL) and the fourth Fermi LAT data release 2 point source catalog (4FGL-DR2) using two classes - pulsars and active galactic nuclei (AGNs) - or three classes - pulsars, AGNs, and "OTHER" sources. We use several machine learning (ML) methods to determine a probabilistic classification of Fermi-LAT sources. We evaluate the dependence of results on the meta-parameters of the ML methods, such as the maximal depth of the trees in tree-based classification methods and the number of neurons in neural networks. We determine a probabilistic classification of both associated and unassociated sources in the 3FGL and 4FGL-DR2 catalogs. We cross-check the accuracy by comparing the predicted classes of unassociated sources in 3FGL with their associations in 4FGL-DR2 for cases where such associations exist. We find that in the two-class case it is important to correct for the presence of OTHER sources among the unassociated ones in order to realistically estimate the number of pulsars and AGNs. We find that the three-class classification, despite different types of sources in the OTHER class, has a similar performance as the two-class classification in terms of reliability diagrams and, at the same time, it does not require adjustment due to presence of the OTHER sources among the unassociated sources. We show an example of the use of the probabilistic catalogs for population studies, which include associated and unassociated sources.

arXiv comment35 pages, 34 figures, 20 tables, data products are available at http://cdsarc.u-strasbg.fr/viz-bin/cat/J/A+A/660/A87, v2: tables added v3: version accepted to A&A, appendices, tables, plots added

References in corpus (51)

• Adam: A Method for Stochastic Optimization
• SMOTE: Synthetic Minority Over-sampling Technique
• Astropy: A Community Python Package for Astronomy
• The SIMBAD astronomical database
• Fermi Large Area Telescope Fourth Source Catalog
• Fermi Large Area Telescope Second Source Catalog
• Fermi Large Area Telescope First Source Catalog
• New cosmological constraints on primordial black holes
• SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
• The H.E.S.S. Galactic plane survey
• Physical properties of molecular clouds for the entire Milky Way disk
• 3FHL: The Third Catalog of Hard Fermi-LAT Sources
• Intrinsically Red Sources observed by Spitzer in the Galactic Mid-Plane
• The Milky Way Project First Data Release: A Bubblier Galactic Disk
• The Fermi-LAT high-latitude Survey: Source Count Distributions and the Origin of the Extragalactic Diffuse Background
• The Origin of the Extragalactic Gamma-Ray Background and Implications for Dark-Matter Annihilation
• Resolving the Extragalactic $\gamma$-ray Background above 50 GeV with Fermi-LAT
• The nature of the Diffuse Gamma-Ray Background
• A Statistical Approach to Recognizing Source Classes for Unassociated Sources in the First Fermi-LAT Catalog
• Classification and Ranking of Fermi LAT Gamma-ray Sources from the 3FGL Catalog using Machine Learning Techniques
• Search for extended sources in the Galactic Plane using 6 years of Fermi-Large Area Telescope Pass 8 data above 10 GeV
• Composition of the Fermi-LAT isotropic gamma-ray background intensity: Emission from extragalactic point sources and dark matter annihilations
• Application of the Gaussian mixture model in pulsar astronomy -- pulsar classification and candidates ranking for {\it Fermi} 2FGL catalog
• Parkes radio searches of Fermi gamma-ray sources and millisecond pulsar discoveries
• Statistics of gamma-ray point sources below the Fermi detection limit
• 3FGL Demographics Outside the Galactic Plane using Supervised Machine Learning: Pulsar and Dark Matter Subhalo Interpretations
• Deciphering Contributions to the Extragalactic Gamma-Ray Background from 2 GeV to 2 TeV
• Blazar Flaring Patterns (B-FlaP): Classifying Blazar Candidates of Uncertain type in the third Fermi-LAT catalog by Artificial Neural Networks
• Gamma-Ray Active Galactic Nucleus Type through Machine-Learning Algorithms
• Unveiling the Gamma-ray Source Count Distribution Below the Fermi Detection Limit with Photon Statistics
• Search for gamma-ray-emitting active galactic nuclei in the Fermi-LAT unassociated sample using machine learning
• The Initial Conditions of Stellar Protocluster Formation: III. The Herschel counterparts of the Spitzer Dark Cloud catalogue
• Statistical Measurement of the Gamma-ray Source-count Distribution as a Function of Energy
• Research and characterisation of blazar candidates among the Fermi/LAT 3FGL catalogue using multivariate classifications
• 3FGLzoo. Classifying 3FGL Unassociated Fermi-LAT Gamma-ray Sources by Artificial Neural Networks
• Constraints on Dark Matter Annihilation/Decay from the Isotropic Gamma-Ray Background
• Deriving the contribution of blazars to the Fermi-LAT Extragalactic $\gamma$-ray background at $E>10$ GeV with efficiency corrections and photon statistics
• Probabilistic Catalogs for Crowded Stellar Fields
• An investigation on the factors affecting machine learning classifications in $\gamma$-ray astronomy
• Young Stellar Objects in the Massive Star-Forming Regions W51 and W43
• Morphological and spectral study of 4FGL J1115.1-6118 in the region of the young massive stellar cluster NGC 3603
• The diffuse gamma-ray emission toward the Galactic mini starburst W43
• On the gamma-ray emission of W44 and its surroundings
• Classification of Blazar Candidates of Uncertain Type from the Fermi LAT 8-Year Source Catalog with an Artificial Neural Network
• Inference of Unresolved Point Sources At High Galactic Latitudes Using Probabilistic Catalogs
• Classification of Fermi-LAT sources with deep learning using energy and time spectra
• Searching for AGN and Pulsar Candidates in 4FGL Unassociated Sources Using Machine Learning
• Identification of point sources in gamma rays using U-shaped convolutional neural networks and a data challenge
• Optimizing neural network techniques in classifying Fermi-LAT gamma-ray sources
• Searches for Pulsar-like Candidates from Unidentified Objects in the Third Catalog of Hard Fermi-LAT (3FHL) sources with Machine Learning Techniques
• High-velocity interstellar absorption associated with the supernova remnant W28

Cited by in corpus (11)

• Gradient boosting decision trees classification of blazars of uncertain type in the fourth Fermi-LAT catalog
• Classifications of Fermi-LAT unassociated sources in multiple machine learning methods
• Multi-class classification of Fermi-LAT sources with hierarchical class definition
• A search for dark matter among Fermi-LAT unidentified sources with systematic features in Machine Learning
• Towards resolving the Galactic center GeV excess with millisecond-pulsar-like sources using machine learning
• Fermi LAT AGN classification using supervised machine learning
• Effect of covariate shift on multi-class classification of Fermi-LAT sources
• Searching for dark matter subhalos in the Fermi-LAT catalog with Bayesian neural networks
• Deepening gamma-ray point-source catalogues with sub-threshold information
• GeV emission in the region of Vela: a new view of the supernova remnant
• Exploring the nature of Galactic unassociated sources detected by the Fermi-LAT