International Conference on Machine Learning for Astrophysics 2nd Ed. - ML4ASTRO2

Session

Past and future multiwavelength all-sky surveys

8 Jul 2024, 11:10

Aula Magna (Catania)

Conveners

Past and future multiwavelength all-sky surveys: II

• Eva Sciacca (Istituto Nazionale di Astrofisica (INAF))

210. Machine Learning-Driven Determination of 3D Structures of Molecular Clouds in High-Resolution mm Images

Efe Öztaban

08/07/2024, 11:10

The analysis of dust scattering halos (DSH), caused by the intense radiation from Galactic black hole transients (GBHTs), provides observational insights to understand the composition and structure of molecular clouds in the line of sight to the source and determine the distance to the source. Observations of DSH of 4U 1630−47, a GBHT, identified a significant molecular cloud (MC −79) that...

213. A domain-adaptation approach to classify ionised nebulae in nearby galaxies

Francesco Belfiore

08/07/2024, 11:30

The classification and the determination of physical parameters for astrophysical objects is often performed by comparing data with theoretical models. This comparison, however, can be biased by imperfect matching of the observational signatures in the data, and by simplifying assumptions and missing physics in the models. These factors limit the performance of classical machine learning tools...

215. A semi-supervised "cluster-then-label" scheme for photometric classification of evolved stars

Cristobal Bordiu

08/07/2024, 11:50

Evolved stars are the main drivers of Galactic evolution from a chemo-dynamical perspective. Therefore, a comprehensive census of these sources is essential for the study of stellar feedback. However, identifying evolved stars is a time-consuming task that often involves spectroscopic observations. With the advent of next-generation telescopes (Roman, LSST) capable of delivering deep, all-sky...

217. Machine learning for star parametrization

Alessio Turchi

08/07/2024, 12:10

An increasing amount of photometric data are made available by multiple large photometric surveys such as GAIA, SDSS, SKYMAPPER, among others. While the large statistical samples available from these catalogs are fundamental for astronomical analyses, parameters estimates (such as temperature, metallicity, or gravity) are difficult to obtain due to the limited reliability of analytical methods...

222. LEMON: Lens modeling with Bayesian neural networks

Valerio Busillo

08/07/2024, 12:30

Strong gravitational lensing is a powerful tool for constraining the total mass and mass density profiles of galaxies, by exploiting visible geometrical features such as lensed arcs, rings and multiple images around massive lens galaxies. Upcoming stage IV surveys, such as Euclid, are expected to discover between 10^4 and 10^5 new gravitational lenses over a total of 14,000 square degrees of...