Related papers: Classifying Unidentified X-ray Sources in the Chan…

Machine learning (ML) research has yielded powerful tools for training accurate prediction models despite complex multivariate associations (e.g. interactions and heterogeneity). In fields such as medicine, improved interpretability of ML…

In the era of large photometric surveys, the importance of automated and accurate classification is rapidly increasing. Specifically, the separation of resolved and unresolved sources in astronomical imaging is a critical initial step for a…

We present a new, multi-mission catalogue of ultraluminous X-ray source (ULX) candidates, based on recent data releases from each of the XMM-Newton, Swift and Chandra observatories (the 4XMM-DR10, 2SXPS and CSC2 catalogues, respectively).…

Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small label spaces and…

Despite the growing number of gamma-ray sources detected by Fermi-LAT, about one third of the sources in each survey remains of uncertain type. We present a new deep neural network approach for the classification of unidentified or…

Cataloging is challenging in crowded fields because sources are extremely covariant with their neighbors and blending makes even the number of sources ambiguous. We present the first optical probabilistic catalog, cataloging a crowded (~0.1…

The more than 80 nearby galaxies imaged with the Chandra Advanced CCD Imaging Spectrometer have been analyzed in a search for Ultra-Luminous X-ray (ULX) sources. The sample of galaxies span the range of Hubble morphological types and…

We present an extension to our XMM-Newton X-ray source catalogue of M 31, containing 39 newly found sources. In order to classify and identify more of the sources we search for X-ray time variability in XMM-Newton archival data of the M 31…

Science is currently at an age where there is more data than we know how to deal with. Machine learning (ML) is an emerging tool that is useful for drawing valuable science out of incomprehensibly large datasets and identifying complex…

In this work, we perform a comprehensive study of the machine learning (ML) methods for the purpose of characterising the quantum set of correlations. As our main focus is on assessing the usefulness and effectiveness of the ML approach, we…

The deepest extragalactic X-ray observation, the 2 Ms Chandra Deep Field North (CDF-N), resolves ~80% of the total extragalactic cosmic X-ray background (CXB) in the 1-2 keV band. Recent work has shown that 70% of the remaining CXB flux is…

We describe detailed simulations of X-ray-emitting populations to evaluate the levels of contamination by both Galactic and extragalactic X-ray sources unrelated to a star-forming region under study. For Galactic contaminations, we consider…

The next generation of data-intensive surveys are bound to produce a vast amount of data, which can be dealt with using machine-learning methods to explore possible correlations within the multi-dimensional parameter space. We explore the…

We present a deep machine learning (ML) approach to constraining cosmological parameters with multi-wavelength observations of galaxy clusters. The ML approach has two components: an encoder that builds a compressed representation of each…

The powerful combination of the Chandra X-ray telescope, the SCUBA submillimetre-wave camera and the gravitational lensing effect of the massive galaxy clusters A2390 and A1835 has been used to place stringent X-ray flux limits on six faint…

The Extended Chandra Deep Field-South (ECDFS) survey consists of 4 Chandra ACIS-I pointings and covers $\approx$ 1100 square arcminutes ($\approx$ 0.3 deg$^2$) centered on the original CDF-S field to a depth of approximately 228 ks. This is…

The X-ray populations of Local group galaxies have been classified in detail by Einstein, ROSAT and ASCA revealing a mix of binaries, supernova remnants and HII regions. However, these observatories were unable to resolve X-ray sources in…

Identifying stars belonging to different classes is vital in order to build up statistical samples of different phases and pathways of stellar evolution. In the era of surveys covering billions of stars, an automated method of identifying…

With the increasing prevalence of encrypted network traffic, cyber security analysts have been turning to machine learning (ML) techniques to elucidate the traffic on their networks. However, ML models can become stale as new traffic…

The adaptation and use of Machine Learning (ML) in our daily lives has led to concerns in lack of transparency, privacy, reliability, among others. As a result, we are seeing research in niche areas such as interpretability, causality, bias…