Dataset of artefacts for machine learning applications in astronomy

New Astronomy. 2026. Vol. 122. Article 102466.

Sreejith S., Pruzhinskaya M., Volnova A., Krushinsky V., Malanchev K., Ishida E. O., Lavrukhina A., Semenikhin T., Gangler E., Matwey V. Kornilov, Korolev V.

Accurate photometry in astronomical surveys is challenged by image artefacts, which affect measurements and
degrade data quality. Due to the large amount of available data, this task is increasingly handled using machine
learning algorithms, which often require a labelled training set to learn data patterns. We present an expert-
labelled dataset of 1127 artefacts with 1213 labels from 26 fields in ZTF DR3, along with a complementary set
of nominal objects. The artefact dataset was compiled using the active anomaly detection algorithm PineForest,
developed by the SNAD team. These datasets can serve as valuable resources for real-bogus classification,
catalogue cleaning, anomaly detection, and educational purposes. Both artefacts and nominal images are
provided in FITS format in two sizes (28 × 28 and 63 × 63 pixels). The datasets are publicly available for
further scientific applications.

Keywords: astronomy, Machine Learning