A search for dark matter among Fermi-LAT unidentified sources with systematic features in Machine Learning

Abstract

Around one third of the point-like sources in the Fermi-LAT catalogs remain as unidentified sources (unIDs) today. Indeed, these unIDs lack a clear, univocal association with a known astrophysical source. If dark matter (DM) is composed of weakly interacting massive particles (WIMPs), there is the exciting possibility that some of these unIDs may actually be DM sources, emitting gamma rays from WIMPs annihilation. We propose a new approach to solve the standard, Machine Learning (ML) binary classification problem of disentangling prospective DM sources (simulated data) from astrophysical sources (observed data) among the unIDs of the 4FGL Fermi-LAT catalogue. We artificially build two {\it systematic} features for the DM data which are originally inherent to observed data: the detection significance and the uncertainty on the spectral curvature. We do it by sampling from the observed population of unIDs, assuming that the DM distributions would, if any, follow the latter. We consider different ML models: Logistic Regression, Neural Network (NN), Naive Bayes and Gaussian Process, out of which the best, in terms of classification accuracy, is the NN, achieving around $93.3\%\pm 0.7\%$ performance. Other ML evaluation parameters, such as the True Negative and True Positive rates, are discussed in our work. Applying the NN to the unIDs sample, we find that the degeneracy between some astrophysical and DM sources can be partially solved within this methodology. Nonetheless, we conclude that there are no DM source candidates among the pool of 4FGL Fermi-LAT unIDs.

arXiv comment14 pages, 18 figures, accepted by MNRAS

References in corpus (41)

• Planck 2015 results. XIII. Cosmological parameters
• Fermi Large Area Telescope Fourth Source Catalog
• PPPC 4 DM ID: A Poor Particle Physicist Cookbook for Dark Matter Indirect Detection
• Fermi-LAT Observations of the Diffuse Gamma-Ray Emission: Implications for Cosmic Rays and the Interstellar Medium
• 3FHL: The Third Catalog of Hard Fermi-LAT Sources
• Weak Corrections are Relevant for Dark Matter Indirect Detection
• 2FHL: The Second Catalog of Hard Fermi-LAT Sources
• Dark Matter Dynamics and Indirect Detection
• Sensitivity Projections for Dark Matter Searches with the Fermi Large Area Telescope
• Indirect dark matter searches in Gamma- and Cosmic Rays
• Dark matter vs. Pulsars: Catching the impostor
• Painting galaxies into dark matter halos using machine learning
• Unidentified sources in the Fermi-LAT second source catalog: the case for DM subhalos
• Dark Matter Subhalos In the Fermi First Source Catalog
• Examining The Fermi-LAT Third Source Catalog In Search Of Dark Matter Subhalos
• Searching For Dark Matter Subhalos In the Fermi-LAT Second Source Catalog
• (Non-)thermal production of WIMPs during kination
• Dark matter constraints from dwarf galaxies: a data-driven analysis
• Identifying WIMP dark matter from particle and astroparticle data
• Realistic estimation for the detectability of dark matter sub-halos with Fermi-LAT
• Reliability of Monte Carlo event generators for gamma ray dark matter searches
• Analyzing γ-rays of the Galactic Center with Deep Learning
• Is The Gamma-Ray Source 3FGL J2212.5+0703 A Dark Matter Subhalo?
• Unidentified Gamma-ray Sources as Targets for Indirect Dark Matter Detection with the Fermi-Large Area Telescope
• Spectral and spatial analysis of the dark matter subhalo candidates among Fermi Large Area Telescope unidentified sources
• Dark matter subhalos and unidentified sources in the Fermi 3FGL source catalog
• Gamma Rays From Dark Matter Subhalos Revisited: Refining the Predictions and Constraints
• Gamma-ray evidences of the dark matter clumps
• Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array
• Encoding large scale cosmological structure with Generative Adversarial Networks
• Learning from the machine: interpreting machine learning algorithms for point- and extended- source classification
• Optimizing neural network techniques in classifying Fermi-LAT gamma-ray sources
• Machine learning methods for constructing probabilistic Fermi-LAT catalogs
• Artificial Neural Network Classification of 4FGL Sources
• Spatial extension of dark subhalos as seen by Fermi-LAT and implications for WIMP constraints
• Galaxy And Mass Assembly (GAMA): Self-Organizing Map Application on Nearby Galaxies
• Comment on "Understanding the $\gamma$-ray emission from the globular cluster 47 Tuc: evidence for dark matter?"
• MAGIC and Fermi-LAT gamma-ray results on unassociated HAWC sources
• Searches for Pulsar-like Candidates from Unidentified Objects in the Third Catalog of Hard Fermi-LAT (3FHL) sources with Machine Learning Techniques
• Multimessenger TeV Dark Matter: a mini review
• Sensitivity Estimation for Dark Matter Subhalos in Synthetic Gaia DR2 using Deep Learning

Cited by in corpus (5)

• Redshift prediction of Fermi-LAT gamma-ray sources using CatBoost gradient boosting decision trees
• Classification of blazar candidates of unknown type in Fermi 4LAC by unanimous voting from multiple Machine Learning Algorithms
• Can prompt cusps of WIMP dark matter be detected as individual gamma-ray sources?
• Searching for dark matter subhalos in the Fermi-LAT catalog with Bayesian neural networks
• Deeper analysis of Fermi-LAT unassociated 4FGL J2112.5-3043 for possible identification