Hareesh Thuruthipilly

Narodowe Centrum Badań Jądrowych

Sesja VII: Kosmologia i ewolucja galaktyk

Czwartek 14.09.2023 16:48 – 17:00

abstrakt:
Low surface brightness galaxies (LSBGs), which are defined as galaxies that are fainter than the night sky, play a crucial role in understanding galaxy evolution and cosmological models. Upcoming large-scale surveys like Rubin Observatory Legacy Survey of Space and Time (LSST) and Euclid are expected to observe approximately 10^9 astronomical objects. In this context, using semi-automatic methods to identify LSBGs while rejecting artefacts would be a highly challenging and time-consuming process. To address this issue, we propose a new machine learning architecture known as 'transformers’ for the detection of LSBGs. We study the use of transformers in separating LSBGs from artefacts from the Dark Energy Survey (DES) and report the identification of 4,083 new LSBGs with transformers from DES. We also analyse the unusual clustering nature of LSBGs and their properties to give more insights into the nature of LSBGs. In addition, our results also increase the number density of LSBGs to 5.5 per deg^2, forecasting more than 100,000 LSBGs from LSST highlighting the necessity of fast automated methods for the analysis.