<i>Euclid</i> : Detecting Solar System objects in <i>Euclid</i> images and classifying them using Kohonen self-organising maps

The ESA <i>Euclid</i> mission will survey more than 14 000 deg² of the sky in visible and near-infrared wavelengths, mapping the extragalactic sky to constrain our cosmological model of the Universe. Although the survey focusses on regions further than 15° from the ecliptic, it should allow for the detection of more than about 10⁵ Solar System objects (SSOs). After simulating the expected signal from SSOs in <i>Euclid</i> images acquired with the visible camera (VIS), we describe an automated pipeline developed to detect moving objects with an apparent velocity in the range of 0.1–10″ h⁻¹ , typically corresponding to sources in the outer Solar System (from Centaurs to Kuiper-belt objects). In particular, the proposed detection scheme is based on <b>SExtractor<b> software and on applying a new algorithm capable of associating moving objects amongst different catalogues. After applying a suite of filters to improve the detection quality, we study the expected purity and completeness of the SSO detections. We also show how a Kohonen self-organising neural network can be successfully trained (in an unsupervised fashion) to classify stars, galaxies, and SSOs. By implementing an early-stopping method in the training scheme, we show that the network can be used in a predictive way, allowing one to assign the probability of each detected object being a member of each considered class.