Repository of University of Nova Gorica

Show document
A+ | A- | Help | SLO | ENG

Title:AutoSourceID-FeatureExtractor : optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation
Authors:ID Stoppa, F. (Author)
ID Ruiz de Austri, R. (Author)
ID Vreeswijk, P. (Author)
ID Bhattacharyya, Saptashwa (Author)
ID Caron, S. (Author)
ID Bloemen, S. (Author)
ID Zaharijas, Gabrijela (Author)
ID Principe, G. (Author)
ID Vodeb, Veronika (Author)
ID Groot, P. J. (Author)
ID Cator, E. (Author)
ID Nelemans, G. (Author)
Files:URL https://www.aanda.org/articles/aa/pdf/forth/aa46983-23.pdf
 
ASID-Feature_Extractor (806,65 KB)
MD5: 10F97497F35C94DE674C293F629B4D4F
 
URL https://www.aanda.org/component/article?access=doi&doi=10.1051/0004-6361/202346983
 
Language:English
Work type:Unknown
Typology:1.01 - Original Scientific Article
Organization:UNG - University of Nova Gorica
Abstract: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.
Keywords:data analysis, image processing, astronomical databases
Publication date:01.01.2023
Year of publishing:2023
Number of pages:str. 1-14
Numbering:Vol. 680, [article no.] A108
PID:20.500.12556/RUNG-8614-701bdf90-a97f-a029-211a-feaf3cb08f10 New window
COBISS.SI-ID:171359747 New window
UDC:52
ISSN on article:1432-0746
DOI:10.1051/0004-6361/202346983 New window
NUK URN:URN:SI:UNG:REP:P3XM16P5
Publication date in RUNG:08.11.2023
Views:1989
Downloads:13
Metadata:XML DC-XML DC-RDF
:
STOPPA, F., RUIZ DE AUSTRI, R., VREESWIJK, P., BHATTACHARYYA, Saptashwa, CARON, S., BLOEMEN, S., ZAHARIJAS, Gabrijela, PRINCIPE, G., VODEB, Veronika, GROOT, P. J., CATOR, E. and NELEMANS, G., 2023, AutoSourceID-FeatureExtractor : optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation. Astronomy & astrophysics [online]. 2023. Vol. 680, no. A108, p. 1–14. [Accessed 7 April 2025]. DOI 10.1051/0004-6361/202346983. Retrieved from: https://www.aanda.org/component/article?access=doi&doi=10.1051/0004-6361/202346983
Copy citation
  
Average score:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Record is a part of a journal

Title:Astronomy & astrophysics
Shortened title:Astron. astrophys.
Publisher:EDP Sciences
ISSN:1432-0746
COBISS.SI-ID:392577 New window

Licences

License:CC BY 4.0, Creative Commons Attribution 4.0 International
Link:http://creativecommons.org/licenses/by/4.0/
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Back