TY  - JOUR
AU  - Stoppa, F.
AU  - Bhattacharyya, S.
AU  - Ruiz de Austri, R.
AU  - Vreeswijk, P.
AU  - Caron, S.
AU  - Zaharijas, G.
AU  - Bloemen, S.
AU  - Principe, G.
AU  - Malyshev, D.
AU  - Vodeb, V.
AU  - Groot, P. J.
AU  - Cator, E.
AU  - Nelemans, G.
PY  - 2023
DA  - 2023//
TI  - AutoSourceID-Classifier Star-galaxy classification using a convolutional neural network with spatial information
T2  - Astron. Astrophys.
JO  - Astronomy & Astrophysics
SP  - A109 - 16pp
VL  - 680
PB  - Edp Sciences S A
KW  - methods: data analysis
KW  - techniques: image processing
KW  - astronomical databases: miscellaneous
KW  - stars: imaging
KW  - Galaxies: statistics
AB  - Aims. Traditional star-galaxy classification techniques often rely on feature estimation from catalogs, a process susceptible to introducing inaccuracies, thereby potentially jeopardizing the classification's reliability. Certain galaxies, especially those not manifesting as extended sources, can be misclassified when their shape parameters and flux solely drive the inference. We aim to create a robust and accurate classification network for identifying stars and galaxies directly from astronomical images.Methods. The AutoSourceID-Classifier (ASID-C) algorithm developed for this work uses 32x32 pixel single filter band source cutouts generated by the previously developed AutoSourceID-Light (ASID-L) code. By leveraging convolutional neural networks (CNN) and additional information about the source position within the full-field image, ASID-C aims to accurately classify all stars and galaxies within a survey. Subsequently, we employed a modified Platt scaling calibration for the output of the CNN, ensuring that the derived probabilities were effectively calibrated, delivering precise and reliable results.Results. We show that ASID-C, trained on MeerLICHT telescope images and using the Dark Energy Camera Legacy Survey (DECaLS) morphological classification, is a robust classifier and outperforms similar codes such as SourceExtractor. To facilitate a rigorous comparison, we also trained an eXtreme Gradient Boosting (XGBoost) model on tabular features extracted by SourceExtractor. While this XGBoost model approaches ASID-C in performance metrics, it does not offer the computational efficiency and reduced error propagation inherent in ASID-C's direct image-based classification approach. ASID-C excels in low signal-to-noise ratio and crowded scenarios, potentially aiding in transient host identification and advancing deep-sky astronomy.
SN  - 0004-6361
UR  - https://arxiv.org/abs/2307.14456
UR  - https://doi.org/10.1051/0004-6361/202347576
DO  - 10.1051/0004-6361/202347576
LA  - English
N1  - WOS:001131898100001
ID  - Stoppa_etal2023
ER  -