Enhancing astrometric registration of Chinese historical Astronomical Digital Plates with deep learning

TL;DR

This paper introduces a Transformer-based AI classifier to improve the identification of trustworthy stellar sources on digitized historical astronomical plates, significantly increasing successful astrometric registration rates.

Contribution

The work presents a novel deep learning model that enhances source reliability assessment, enabling more accurate registration of degraded historical astronomical plates.

Findings

Successfully registered 1353 out of 1883 plates using the AI classifier.

Improved source matching accuracy over traditional methods.

Streamlined processing of large historical astronomical datasets.

Abstract

China has systematically collected nighttime astronomical plates since 1900, creating a large historical dataset that has been digitized with optical scanners. For astrometric registration of these digitized plates, sources were first extracted using SExtractor, and then matched astrometrically with Astrometry.net and the Gaia catalog. However, suboptimal early storage conditions and subsequent environmental deterioration have impeded accurate source matching, resulting in processing failures for several thousand digitized plates. In this work, we introduce a Transformer-based classification model that takes cutouts of SExtractor-detected sources as input and leverages multi-scale feature fusion to identify trustworthy stellar sources on the plates. Trained on plates with successful astrometric calibration, our AI-based classifier was then applied to SExtractor detected sources of 1883 digitized plates, enabling us to complete the astrometric registration for 1353 of them. This AI-augmented pipeline streamlines the processing of historical plate archives and enhances their scientific value for long-term time-domain astronomical studies.