Abstract: Context. At GeV energies, the sky is dominated by the interstellar emission from the Galaxy. With limited statistics and spatial resolution, accurately separating point sources is therefore challenging. Aims. Here we present the first application of deep learning based algorithms to automatically detect and classify point sources from gamma-ray data. For concreteness we refer to this approach as AutoSourceID. Methods. To detect point sources, we utilized U-shaped convolutional networks for image segmentation and k-means for source clustering and localization. We also explored the Centroid-Net algorithm, which is designed to find and count objects. Using two algorithms allows for a cross check of the results, while a combination of their results can be used to improve performance. The training data are based on 9.5 years of exposure from The Fermi Large Area Telescope (Fermi-LAT) and we used source properties of active galactic nuclei (AGNs) and pulsars (PSRs) from the fourth Fermi-LAT source catalog in addition to several models of background interstellar emission. The results of the localization algorithm are fed into a classification neural network that is trained to separate the three general source classes (AGNs, PSRs, and FAKE sources). Results. We compared our localization algorithms qualitatively with traditional methods and find them to have similar detection thresholds. We also demonstrate the robustness of our source localization algorithms to modifications in the interstellar emission models, which presents a clear advantage over traditional methods. The classification network is able to discriminate between the three classes with typical accuracy of similar to 70%, as long as balanced data sets are used in classification training. We published online our training data sets and analysis scripts and invite the community to join the data challenge aimed to improve the localization and classification of gamma-ray point sources.

Abstract: The Fermi Collaboration has recently updated their analysis of gamma rays from the center of the Galaxy. They reconfirm the presence of an unexplained emission feature which is most prominent in the region of 1-10 GeV, known as the Galactic Center GeV excess (GCE). Although the GCE is now fi rmly detected, an interpretation of this emission as a signal of self-annihilating dark matter (DM) particles is not unambiguously possible due to systematic effects in the gamma-ray modeling estimated in the Galactic Plane. In this paper we build a covariance matrix, collecting different systematic uncertainties investigated in the Fermi Collaboration's paper that affect the GCE spectrum. We show that models where part of the GCE is due to annihilating DM is still consistent with the new data. We also re-evaluate the parameter space regions of the minimal supersymmetric Standard Model (MSSM) that can contribute dominantly to the GCE via neutralino DM annihilation. All recent constraints from DM direct detection experiments such as PICO, LUX, PandaX and Xenon1T, limits on the annihilation cross section from dwarf spheroidal galaxies and the Large Hadron Collider limits are considered in this analysis. Due to a slight shift in the energy spectrum of the GC excess with respect to the previous Fermi analysis, and the recent limits from direct detection experiments, we find a slightly shifted parameter region of the MSSM, compared to our previous analysis, that is consistent with the GCE. Neutralinos with a mass between 85-220 GeV can describe the excess via annihilation into a pair of W-bosons or top quarks. Remarkably, there are models with low fine-tuning among the regions that we have found. The complete set of solutions will be probed by upcoming direct detection experiments and with dedicated searches in the upcoming data of the Large Hadron Collider.

Abstract: The Galactic Center Excess (GCE) in GeV gamma rays has been debated for over a decade, with the possibility that it might be due to dark matter annihilation or undetected point sources such as millisecond pulsars (MSPs). This study investigates how the gamma-ray emission model (-yEM) used in Galactic center analyses affects the interpretation of the GCE's nature. To address this issue, we construct an ultra-fast and powerful inference pipeline based on convolutional Deep Ensemble Networks. We explore the two main competing hypotheses for the GCE using a set of-yEMs with increasing parametric freedom. We calculate the fractional contribution (fsrc) of a dim population of MSPs to the total luminosity of the GCE and analyze its dependence on the complexity of the ryEM. For the simplest ryEM, we obtain fsrc = 0.10 f 0.07, while the most complex model yields fsrc = 0.79 f 0.24. In conclusion, we find that the statement about the nature of the GCE (dark matter or not) strongly depends on the assumed ryEM. The quoted results for fsrc do not account for the additional uncertainty arising from the fact that the observed gamma-ray sky is out-of-distribution concerning the investigated ryEM iterations. We quantify the reality gap between our ryEMs using deep-learning-based One-Class Deep Support Vector Data Description networks, revealing that all employed ryEMs have gaps to reality. Our study casts doubt on the validity of previous conclusions regarding the GCE and dark matter, and underscores the urgent need to account for the reality gap and consider previously overlooked “out of domain” uncertainties in future interpretations.