Related papers: Classification of Fermi-LAT unidentified gamma-ray…
We present a likelihood profile stacking technique based on the {\it Fermi}-Large Area Telescope (LAT) data to explore the $\gamma$-ray characteristics of {\it Fermi}-LAT undetected astrophysical populations. The pipeline is applied to a…
The Fermi Large Area Telescope (Fermi-LAT) 3FHL catalog is the latest catalog of >10 GeV sources and will remain an important resource for the high-energy community for the foreseeable future. Therefore, it is crucial that this catalog is…
A significant fraction ($\sim 30$ %) of the high-energy gamma-ray sources listed in the second $\textit{Fermi}$ LAT (2FGL) catalog are still of unknown origin, being not yet associated with counterparts at lower energies. In order to…
We present an application of a particular machine-learning method (Boosted Decision Trees, BDTs using AdaBoost) to separate stars and galaxies in photometric images using their catalog characteristics. BDTs are a well established machine…
This work explores the use of gradient boosting in the context of classification. Four popular implementations, including original GBM algorithm and selected state-of-the-art gradient boosting frameworks (i.e. XGBoost, LightGBM and…
We have analyzed all the archival X-ray data of 134 unidentified (unID) gammaray sources listed in the first Fermi/LAT (1FGL) catalog and subsequently followed up by Swift/XRT. We constructed the spectral energy distributions (SEDs) from…
Gradient boosting methods based on Structured Categorical Decision Trees (SCDT) have been demonstrated to outperform numerical and one-hot-encodings on problems where the categorical variable has a known underlying structure. However, the…
The fourth-DR3 version (4FGL-DR3) of the Fermi/LAT catalogue of $\gamma$-ray sources contains $\sim$ 1000 objects at a galactic latitude |b| > 10$^{\circ}$ which are not identified with an optical counterpart (UGS). We performed a…
For many practical, high-risk applications, it is essential to quantify uncertainty in a model's predictions to avoid costly mistakes. While predictive uncertainty is widely studied for neural networks, the topic seems to be under-explored…
The ESA's X-ray Multi-Mirror Mission (XMM-Newton) created a new, high quality version of the XMM-Newton serendipitous source catalogue, 4XMM-DR9, which provides a wealth of information for observed sources. The 4XMM-DR9 catalogue is…
We present an incremental version (4FGL-DR4, for Data Release 4) of the fourth Fermi-LAT catalog containing 7194 gamma-ray sources. Based on the first 14 years of science data in the energy range from 50 MeV to 1 TeV, it uses the same…
The global contribution of unresolved gamma-ray point sources to the extragalactic gamma-ray background has been recently measured down to gamma-ray fluxes lower than those reached with standard source detection techniques, and by employing…
The Javalambre Photometric Local Universe Survey (J-PLUS) is a 12-band photometric survey using the 83-cm JAST telescope. Data Release 3 includes 47.4 million sources. J-PLUS DR3 only provides star-galaxy classification so that quasars are…
We present a new method for identifying blazar candidates by examining the locus, i.e. the region occupied by the Fermi gamma-ray blazars in the three-dimensional color space defined by the WISE infrared colors. This method is a refinement…
This paper explores the application of machine learning methods for classifying astronomical sources using photometric data, including normal and emission line galaxies (ELGs; starforming, starburst, AGN, broad line), quasars, and stars. We…
Gradient Boosting Decision Tree (GBDT) has achieved remarkable success in a wide variety of applications. The split finding algorithm, which determines the tree construction process, is one of the most crucial components of GBDT. However,…
This paper presents the key algorithmic techniques behind CatBoost, a new gradient boosting toolkit. Their combination leads to CatBoost outperforming other publicly available boosting implementations in terms of quality on a variety of…
The identification of low-energy counterparts for gamma-ray sources is one of the biggest challenge in modern gamma-ray astronomy. Recently, we developed and successfully applied a new association method to recognize gamma-ray blazar…
Context. Based on their overwhelming dominance among associated Fermi gamma ray catalogue sources, it is expected that a large fraction of the unidentified Fermi objects are blazars. Through crossmatching between the positions of…
Revealing the nature of unassociated high-energy (> 100 MeV) gamma-ray sources remains a challenge 35 years after their discovery. Of the 934 gamma-ray sources at high Galactic latitude (|b| > 15 degrees) in the First Fermi-LAT catalogue…