Fermi's Sibyl: Mining the gamma-ray sky for dark matter subhaloes

TL;DR

This paper introduces Sibyl, a machine learning classifier that predicts the nature of unassociated gamma-ray sources, aiding the search for dark matter subhaloes in the Milky Way.

Contribution

Sibyl is a novel Random Forest-based tool that accurately classifies gamma-ray sources, improving identification of potential dark matter subhaloes in the Fermi-LAT data.

Findings

Sibyl achieves up to 97.7% accuracy in classifying AGNs.

It predicts 216 of 269 unassociated sources as potential AGNs.

The classifier helps prioritize candidates for dark matter subhalo searches.

Abstract

Dark matter annihilation signals coming from Galactic subhaloes may account for a small fraction of unassociated point sources detected in the Second Fermi-LAT catalogue (2FGL). To investigate this possibility, we present Sibyl, a Random Forest classifier that offers predictions on class memberships for unassociated Fermi-LAT sources at high Galactic latitudes using gamma-ray features extracted from the 2FGL. Sibyl generates a large ensemble of classification trees that are trained to vote on whether a particular object is an active galactic nucleus (AGN) or a pulsar. After training on a list of 908 identified/associated 2FGL sources, Sibyl reaches individual accuracy rates of up to 97.7% for AGNs and 96.5% for pulsars. Predictions for the 269 unassociated 2FGL sources at |b| > 10 degrees suggest that 216 are potential AGNs and 16 are potential pulsars (with majority votes greater than 70%). The remaining 37 objects are inconclusive, but none is an extreme outlier. These results could guide future quests for dark matter Galactic subhaloes.