Repozitorij Univerze v Novi Gorici

Izpis gradiva
A+ | A- | Pomoč | SLO | ENG

Naslov:AutoSourceID-FeatureExtractor : optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation
Avtorji:ID Stoppa, F. (Avtor)
ID Ruiz de Austri, R. (Avtor)
ID Vreeswijk, P. (Avtor)
ID Bhattacharyya, Saptashwa (Avtor)
ID Caron, S. (Avtor)
ID Bloemen, S. (Avtor)
ID Zaharijas, Gabrijela (Avtor)
ID Principe, G. (Avtor)
ID Vodeb, Veronika (Avtor)
ID Groot, P. J. (Avtor)
ID Cator, E. (Avtor)
ID Nelemans, G. (Avtor)
ASID-Feature_Extractor (806,65 KB)
MD5: 10F97497F35C94DE674C293F629B4D4F
Jezik:Angleški jezik
Vrsta gradiva:Neznano
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:UNG - Univerza v Novi Gorici
Opis:Aims: In astronomy, machine learning has been successful in various tasks such as source localisation, classification, anomaly detection, and segmentation. However, feature regression remains an area with room for improvement. We aim to design a network that can accurately estimate sources' features and their uncertainties from single-band image cutouts, given the approximated locations of the sources provided by the previously developed code AutoSourceID-Light (ASID-L) or other external catalogues. This work serves as a proof of concept, showing the potential of machine learning in estimating astronomical features when trained on meticulously crafted synthetic images and subsequently applied to real astronomical data. Methods: The algorithm presented here, AutoSourceID-FeatureExtractor (ASID-FE), uses single-band cutouts of 32x32 pixels around the localised sources to estimate flux, sub-pixel centre coordinates, and their uncertainties. ASID-FE employs a two-step mean variance estimation (TS-MVE) approach to first estimate the features and then their uncertainties without the need for additional information, for example the point spread function (PSF). For this proof of concept, we generated a synthetic dataset comprising only point sources directly derived from real images, ensuring a controlled yet authentic testing environment. Results: We show that ASID-FE, trained on synthetic images derived from the MeerLICHT telescope, can predict more accurate features with respect to similar codes such as SourceExtractor and that the two-step method can estimate well-calibrated uncertainties that are better behaved compared to similar methods that use deep ensembles of simple MVE networks. Finally, we evaluate the model on real images from the MeerLICHT telescope and the Zwicky Transient Facility (ZTF) to test its transfer learning abilities.
Ključne besede:data analysis, image processing, astronomical databases
Datum objave:01.01.2023
Leto izida:2023
Št. strani:str. 1-14
Številčenje:Vol. 680, [article no.] A108
PID:20.500.12556/RUNG-8614-701bdf90-a97f-a029-211a-feaf3cb08f10 Novo okno
COBISS.SI-ID:171359747 Novo okno
ISSN pri članku:1432-0746
DOI:10.1051/0004-6361/202346983 Novo okno
Datum objave v RUNG:08.11.2023
Število ogledov:834
Število prenosov:8
Kopiraj citat
Skupna ocena:(0 glasov)
Vaša ocena:Ocenjevanje je dovoljeno samo prijavljenim uporabnikom.
Objavi na:Bookmark and Share

Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše podrobnosti ali sproži prenos.

Gradivo je del revije

Naslov:Astronomy & astrophysics
Skrajšan naslov:Astron. astrophys.
Založnik:EDP Sciences
COBISS.SI-ID:392577 Novo okno


Licenca:CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
Opis:To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.