@Article{Stoppa_etal2023,
author="Stoppa, F.
and Ruiz de Austri, R.
and Vreeswijk, P.
and Bhattacharyya, S.
and Caron, S.
and Bloemen, S.
and Zaharijas, G.
and Principe, G.
and Vodeb, V.
and Groot, P. J.
and Cator, E.
and Nelemans, G.",
title="AutoSourceID-FeatureExtractor Optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation",
journal="Astronomy {\&} Astrophysics",
year="2023",
publisher="Edp Sciences S A",
volume="680",
pages="A108 - 14pp",
optkeywords="astronomical databases: miscellaneous; methods: data analysis; stars: imaging; techniques: image processing",
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{\textquoteright} 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.",
optnote="WOS:001131898100003",
optnote="exported from refbase (https://references.ific.uv.es/refbase/show.php?record=5887), last updated on Sat, 27 Jan 2024 12:01:54 +0000",
issn="0004-6361",
doi="10.1051/0004-6361/202346983",
opturl="https://arxiv.org/abs/2305.14495",
opturl="https://doi.org/10.1051/0004-6361/202346983",
language="English"
}