AI Enhances Astrometric Registration of Chinese Historical Astronomical Plates

This work introduces a Transformer-based classification model to enhance astrometric registration of digitized Chinese historical astronomical plates. China has systematically collected nighttime astronomical plates since 1900, creating a large historical dataset that has been digitized with optical scanners. However, suboptimal early storage conditions and subsequent environmental deterioration have impeded accurate source matching, resulting in processing failures for several thousand digitized plates. The AI model 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, the AI-based classifier was then applied to SExtractor detected sources of 1883 digitized plates, enabling the completion of 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. The research demonstrates the potential of AI to overcome challenges in processing historical scientific data and unlock valuable insights into long-term astronomical phenomena. The successful application of the Transformer-based model highlights the effectiveness of deep learning techniques in addressing complex image analysis tasks. This research contributes to the preservation and utilization of historical astronomical data, enabling new discoveries and a deeper understanding of the universe.

_Context: This intelligence report was compiled by the DailyOrbitalWire Strategy Engine. Verified for Art. 50 Compliance._