Classifications of Fermi-LAT unassociated sources in multiple machine learning methods

Abstract

The classifications of Fermi-LAT unassociated sources are studied using multiple machine learning (ML) methods. The update data from 4FGL-DR3 are divided into high Galactic latitude (HGL, Galactic latitude $|b|>10^{\circ }$) and low Galactic latitude (LGL, $|b|\le 10^{\circ }$) regions. In the HGL region, a voting ensemble of four binary ML classifiers achieves a 91$\%$ balanced accuracy. In the LGL region, an additional Bayesian-Gaussian (BG) model with three parameters is introduced to eliminate abnormal soft spectrum AGNs from the training set and ML-identified AGN candidates, a voting ensemble of four ternary ML algorithms reach an 81$\%$ balanced accuracy. And then, a catalog of Fermi-LAT all-sky unassociated sources is constructed. Our classification results show that (i) there are 1037 AGN candidates and 88 pulsar candidates with a balanced accuracy of $0.918\pm 0.029$ in HGL region, which are consistent with those given in previous all-sky ML approaches; and (ii) there are 290 AGN-like candidates, 135 pulsar-like candidates, and 742 other-like candidates with a balanced accuracy of $0.815\pm 0.027$ in the LGL region, which are different from those in previous all-sky ML approaches. Additionally, different training sets and class weights were tested for their impact on classifier accuracy and predicted results. The findings suggest that while different training approaches can yield similar model accuracy, the predicted numbers across different categories can vary significantly. Thus, reliable evaluation of the predicted results is deemed crucial in the ML approach for Fermi-LAT unassociated sources.

arXiv comment21 pages, 9 figures, 6 Tables, accepted for publication in MNRAS

References in corpus (24)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• SMOTE: Synthetic Minority Over-sampling Technique
• Array Programming with NumPy
• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• The Large Area Telescope on the Fermi Gamma-ray Space Telescope Mission
• Fermi Large Area Telescope Fourth Source Catalog
• Incremental Fermi Large Area Telescope Fourth Source Catalog
• Machine Learning in Astronomy: a practical overview
• 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
• Fermi Large Area Telescope Fourth Source Catalog Data Release 2
• Fermi's Sibyl: Mining the gamma-ray sky for dark matter subhaloes
• 3FGL Demographics Outside the Galactic Plane using Supervised Machine Learning: Pulsar and Dark Matter Subhalo Interpretations
• Search for gamma-ray-emitting active galactic nuclei in the Fermi-LAT unassociated sample using machine learning
• Research and characterisation of blazar candidates among the Fermi/LAT 3FGL catalogue using multivariate classifications
• An image-based search for pulsars among Fermi unassociated LAT sources
• Evaluating the optical classification of Fermi BCUs using machine learning
• Classification of Fermi-LAT unidentified gamma-ray sources using CatBoost gradient boosting decision trees
• 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
• Artificial Neural Network Classification of 4FGL Sources
• Machine learning methods for constructing probabilistic Fermi-LAT catalogs
• Multi-class classification of Fermi-LAT sources with hierarchical class definition
• Classifying blazar candidates from the 3FGL unassociated catalog into BL Lacs and FSRQs using Swift and WISE data

Cited by in corpus (5)

• A Multiwavelength Machine-learning Approach to Classifying X-ray Sources in the Fields of Unidentified 4FGL-DR4 sources
• Low radio frequency detections of known pulsars and identification of new candidates with GLEAM-X: GP
• Classification of a New X-ray Catalog of Likely Counterparts to 4FGL-DR4 Unassociated Gamma-ray Sources Using a Neural Network
• Exploring the nature of Galactic unassociated sources detected by the Fermi-LAT
• GeV emission in the region of Vela: a new view of the supernova remnant