Detection and classification of astronomical sources with Astro-RetinaNet in crowded stellar fields

TL;DR

Astro-RetinaNet is a deep learning model designed to detect and classify blended astronomical sources in crowded fields, significantly outperforming traditional methods in accuracy and completeness, especially for faint and heavily blended stars.

Contribution

This paper introduces Astro-RetinaNet, a novel deep learning approach based on Retinanet, tailored for detecting and classifying blended sources in crowded astronomical images, addressing a key challenge in modern sky surveys.

Findings

Achieves high precision in detecting blended stars with varying degrees of crowding.

Outperforms traditional source extraction methods like SExtractor and Photutils in completeness.

Effectively detects faint sources in crowded fields, improving survey data quality.

Abstract

Upcoming next-generation sky surveys will detect large number of faint objects with magnitudes larger than 25. When objects are crowded within a limited a field of view, blending becomes unavoidable. Blending leads to the omission of many sources during photometry in these fields, which cause an underestimates of tens of percent in crowded fields, and remains a major challenge for existing source-extraction techniques. Although artificial neural networks had shown promising results in the detection and classification in wide-field surveys, they often fail with severely blended stars. We developed a robust deep learning model, Astro-RetinaNet, based on the Retinanet algorithm to detect and classify blended sources in single-band astronomical images. After training and evaluating the performance of our network on simulated images, we find precision of 0.96, 0.89,0.70, 0.50,0.75 for single star, 2-star, 3-star, 4-star and 5-or-more star blending cases, respectively, with star number density $\sim$22000 stars per $\rm arcmin^2$. We compare our method's detection capability and completeness both on CSST simulated NGC 2298 images and HST observed M31 images. In crowded and non-crowded stellar fields of simulated NGC 2298, our results show that the model can recover $82\%$ and $95\%$ sources respectively at magnitude ($i$ band) of 25, while for SExtractor and Photutils the completeness reduces to $20\%, 59\%$ and $60\%, 88\%$ respectively. In the M31 case, as faint as 27 magnitude ($F814W$) in a crowded field, Astro-RetinaNet detects 2,224 sources, significantly outperforming Photutils and SExtractor by factors of 3.4 and 7.1, respectively.