Detecting solar system objects with convolutional neural networks

TL;DR

This paper demonstrates that deep convolutional neural networks can effectively classify solar system objects in Euclid mission simulations, achieving high accuracy even with limited data, and can distinguish various astronomical sources.

Contribution

The study introduces a transfer learning approach with CNNs for classifying solar system objects in Euclid data, achieving over 94% accuracy with a small dataset.

Findings

Best model accuracy of 94% on Euclid simulations

Including Euclid's dither information improves accuracy to 96%

Model effectively classifies stars, galaxies, and cosmic rays

Abstract

In the preparation for ESA's Euclid mission and the large amount of data it will produce, we train deep convolutional neural networks on Euclid simulations classify solar system objects from other astronomical sources. Using transfer learning we are able to achieve a good performance despite our tiny dataset with as few as 7512 images. Our best model correctly identifies objects with a top accuracy of 94% and improves to 96% when Euclid's dither information is included. The neural network misses ~50% of the slowest moving asteroids (v < 10 arcsec/h) but is otherwise able to correctly classify asteroids even down to 26 mag. We show that the same model also performs well at classifying stars, galaxies and cosmic rays, and could potentially be applied to distinguish all types of objects in the Euclid data and other large optical surveys.