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

Session

Past and future multiwavelength all-sky surveys

9 Jul 2024, 11:10

Aula Magna (Catania)

Conveners

Past and future multiwavelength all-sky surveys: VI

• Cristobal Bordiu (Istituto Nazionale di Astrofisica (INAF))

281. [INVITED] The Italian National Centre on HPC, Big Data and Quantum Computing NRRP From Research to Industry

Ugo Becciani

09/07/2024, 11:10

Oral Presentation

190. The GaXNet tools for Stage-IV Surveys and Cosmology with Galaxies and Galaxy Clusters

Nicola Napolitano

09/07/2024, 11:20

Oral Presentation

The upcoming all-sky surveys from ground and space will collect detailed imaging and spectroscopical information for up to billions of galaxies. These huge datasets encode fundamental information related to cosmology and galaxy formation mechanisms. We have an unprecedented chance to fully exploit galaxies as laboratories for the cosmology and the physics of dark and baryonic matter (i.e....

183. Exploring Multi-Band Imaging for Identifying z > 6.5 Quasars: A Contrastive Learning Approach Using HSC Data

Laura Natalia Martinez Ramirez

09/07/2024, 11:40

Quasars at z>6 are powerful laboratories to study the growth and evolution of supermassive black holes and massive galaxies, the properties of the intergalactic medium, and the formation of large-scale structures within the first Gyr from the Big Bang. Although these distant objects are the most luminous non-transient sources in the universe, it is challenging to find them because they are...

185. Predictive Modeling of Galaxy Spectra: A Comprehensive Framework Using Transformer Architecture

Ginés Martínez Solaeche

09/07/2024, 12:00

Oral Presentation

In this study, we developed a foundational model leveraging transformer architecture to analyze galaxy spectra across optical and UV photometric bands. Our objective is to create a comprehensive model capable of simultaneously predicting the characteristics of stellar populations, emission lines, and photometric redshifts from a given observational dataset. Utilizing data from the SDSS and the...

187. Multi-Task Neural Nets with Monte Carlo Dropout for Spectral Analysis of Galaxies

Michele Ginolfi

09/07/2024, 12:20

Oral Presentation

The upcoming era of large-scale astronomical surveys, exemplified by instruments like EUCLID and MOONS, demands innovative approaches for rapid and accurate analysis of extensive spectral data.
This talk introduces a pioneering deep learning tool that employs a multi-task convolutional neural network with residual learning to simultaneously derive key physical properties of galaxies, such as...

189. Galaxy Morphological Classification via Unsupervised Machine Learning in the Big Data Era led by JWST, EUCLID, LSST and SKA

Ilin Lazar

09/07/2024, 12:40

Oral Presentation

The morphological properties of galaxies are important tracers of the physical processes, e.g. minor/major mergers, gas accretion and tidal interactions, that have shaped their evolution. Forthcoming ‘Big data’ surveys (e.g. LSST/SKA), which will produce exabyte volumes of data will be the new ‘normal’ in this decade. These volumes will make morphological classification using traditional...