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: Measuring temperature fluctuations in the 21 cm signal from the epoch of reionization and the cosmic dawn is one of the most promising ways to study the universe at high redshifts. Unfortunately, the 21 cm signal is affected by both cosmology and astrophysics processes in a nontrivial manner. We run a suite of 1000 numerical simulations with different values of the main astrophysical parameters. From these simulations we produce tens of thousands of 21 cm maps at redshifts 10 <= z <= 20. We train a convolutional neural network to remove the effects of astrophysics from the 21 cm maps and output maps of the underlying matter field. We show that our model is able to generate 2D matter fields not only that resemble the true ones visually but whose statistical properties agree with the true ones within a few percent down to scales 2 Mpc(-1). We demonstrate that our neural network retains astrophysical information that can be used to constrain the value of the astrophysical parameters. Finally, we use saliency maps to try to understand which features of the 21 cm maps the network is using in order to determine the value of the astrophysical parameters.

Abstract: A search for astrophysical pointlike neutrino sources using the data collected by the ANTARES detector between 2007 January 29 and 2017 December 31 is presented. A likelihood method is used to assess the significance of an excess of muon neutrinos inducing track-like events in correlation with the location of a list of possible sources. Different sets of objects are tested in the analysis: (a) a subsample of the Fermi 3LAC catalog of blazars, (b) a jet-obscured population of active galactic nuclei, (c) a sample of hard X-ray selected radio galaxies, (d) a star-forming galaxy catalog, and (e) a public sample of 56 very-high-energy track events from the IceCube experiment. None of the tested sources shows a significant association with the sample of neutrinos detected by ANTARES. The smallest p-value is obtained for the catalog of radio galaxies with an equal-weights hypothesis, with a pre-trial p-value equivalent to a 2.8 sigma excess, which is equivalent to 1.6 sigma post-trial. In addition, the results of a dedicated analysis for the blazar MG3 J225517+2409 are also reported: this source is found to be the most significant within the Fermi 3LAC sample, with five ANTARES events located less than one degree from the source. This blazar showed evidence of flaring activity in Fermi data, in spacetime coincidence with a high-energy track detected by IceCube. An a posteriori significance of 2.6 sigma for the combination of ANTARES and IceCube data is reported.