Classification of Fermi-LAT sources with deep learning using energy and time spectra

Abstract

Despite the growing number of gamma-ray sources detected by Fermi-LAT, about one third of the sources in each survey remains of uncertain type. We present a new deep neural network approach for the classification of unidentified or unassociated gamma-ray sources in the last release of the Fermi-LAT catalogue (4FGL-DR2) obtained with 10 years of data. In contrast to previous work, our method directly uses the measurements of the photon energy spectrum and time series as input for the classification, instead of specific, human-crafted features. Dense neural networks, and for the first time in the context of gamma-ray source classification recurrent neural networks, are studied in depth. We focus on the separation between extragalactic sources, i.e.\ Active Galactic Nuclei, and Galactic pulsars, and on the further classification of pulsars into young and millisecond pulsars. Our neural network architectures provide powerful classifiers, with a performance that is comparable to previous analyses based on human-crafted features. Our benchmark neural network predicts that of the sources of uncertain type in the 4FGL-DR2, 1050 are Active Galactic Nuclei and 78 are Galactic pulsars, with both classes following the expected sky distribution and the clustering in the variability-curvature plane. We investigate the problem of sample selection bias by testing our architectures against a cross-match test data set using an older catalogue, and propose a feature selection algorithm using autoencoders. Our list of high-confidence candidate sources labelled by the neural networks provides a set of targets for further multiwavelength observations addressed to identify their nature. The deep neural network architectures we develop can be easily extended to include specific features, as well as multiwavelength data on the source photon energy and time spectra coming from different instruments.

arXiv commentMatches version accepted by MNRAS. Discussion of model and results improved, results unchanged

References in corpus (39)

• Adam: A Method for Stochastic Optimization
• SMOTE: Synthetic Minority Over-sampling Technique
• Unified Schemes for Radio-Loud Active Galactic Nuclei
• The Large Area Telescope on the Fermi Gamma-ray Space Telescope Mission
• Machine learning and the physical sciences
• Fermi Large Area Telescope Fourth Source Catalog
• Fermi Large Area Telescope First Source Catalog
• The Second Fermi Large Area Telescope Catalog of Gamma-ray Pulsars
• The spectrum of isotropic diffuse gamma-ray emission between 100 MeV and 820 GeV
• Fermi-LAT Observations of the Diffuse Gamma-Ray Emission: Implications for Cosmic Rays and the Interstellar Medium
• Active Galactic Nuclei: what's in a name?
• The Fermi Large Area Telescope On Orbit: Event Classification, Instrument Response Functions, and Calibration
• Development of the Model of Galactic Interstellar Emission for Standard Point-Source Analysis of Fermi Large Area Telescope Data
• Data Mining and Machine Learning in Astronomy
• The Fourth Catalog of Active Galactic Nuclei Detected by the Fermi Large Area Telescope
• Science with the Cherenkov Telescope Array
• Particle Acceleration Zones Above Pulsar Polar Caps: Electron and Positron Pair Formation Fronts
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Machine Learning in Astronomy: a practical overview
• The nature of the Diffuse Gamma-Ray Background
• A recurrent neural network for classification of unevenly sampled variable stars
• QCD-Aware Recursive Neural Networks for Jet Physics
• Classification and Ranking of Fermi LAT Gamma-ray Sources from the 3FGL Catalog using Machine Learning Techniques
• Fermi Large Area Telescope Fourth Source Catalog Data Release 2
• Fermi's Sibyl: Mining the gamma-ray sky for dark matter subhaloes
• Jet Charge and Machine Learning
• 3FGL Demographics Outside the Galactic Plane using Supervised Machine Learning: Pulsar and Dark Matter Subhalo Interpretations
• Blazar Flaring Patterns (B-FlaP): Classifying Blazar Candidates of Uncertain type in the third Fermi-LAT catalog by Artificial Neural Networks
• Machine Learning Techniques for Stellar Light Curve Classification
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• Search for gamma-ray-emitting active galactic nuclei in the Fermi-LAT unassociated sample using machine learning
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• 3FGLzoo. Classifying 3FGL Unassociated Fermi-LAT Gamma-ray Sources by Artificial Neural Networks
• An investigation on the factors affecting machine learning classifications in $\gamma$-ray astronomy
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Classification of Blazar Candidates of Uncertain Type from the Fermi LAT 8-Year Source Catalog with an Artificial Neural Network
• Searches for Pulsar-like Candidates from Unidentified Objects in the Third Catalog of Hard Fermi-LAT (3FHL) sources with Machine Learning Techniques
• Sensing Higgs cascade decays through memory

Cited by in corpus (17)

• The Third Fermi Large Area Telescope Catalog of Gamma-ray Pulsars
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• The TRAPUM L-band survey for pulsars in Fermi-LAT gamma-ray sources
• A deep learning method for the trajectory reconstruction of cosmic rays with the DAMPE mission
• Gradient boosting decision trees classification of blazars of uncertain type in the fourth Fermi-LAT catalog
• Machine learning methods for constructing probabilistic Fermi-LAT catalogs
• Classifications of Fermi-LAT unassociated sources in multiple machine learning methods
• Multi-class classification of Fermi-LAT sources with hierarchical class definition
• Towards resolving the Galactic center GeV excess with millisecond-pulsar-like sources using machine learning
• Fermi LAT AGN classification using supervised machine learning
• A New Mid-Infrared and X-ray Machine Learning Algorithm to Discover Compton-thick AGN
• 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
• Classification of Fermi-LAT blazars with Bayesian neural networks
• 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
• Feature Selection Techniques for CR Isotope Identification with the AMS-02 Experiment in Space