2025MNRAS.541.1670B

The T and Y spectral classes represent the coolest and lowest mass population of brown dwarfs, yet their census remains incomplete due to limited statistics. Existing detection frameworks are often constrained to identifying M, L, and early T dwarfs, owing to the sparse observational sample of ultracool dwarfs (UCDs) at later types. This paper presents a novel machine learning framework capable of detecting and classifying late-T and Y dwarfs, trained entirely on synthetic photometry from atmospheric models. Utilizing grids from the ATMO 2020 and Sonora Bobcat models, I produce a training data set over two orders of magnitude larger than any empirical set of $>$T6 UCDs. Polynomial colour relations fitted to the model photometry are used to assign spectral types to these synthetic models, which in turn train an ensemble of classifiers to identify and classify the spectral type of late UCDs. The model is highly performant when validating on both synthetic and empirical data sets, verifying catalogues of known UCDs with object classification metrics $>99~{{\ \rm per\ cent}}$ and an average spectral-type precision within $0.35 \pm 0.37$ subtypes. Application of the model to a $1.5^\circ$ region in Pisces and the UKIDSS UDS field results in the discovery of one previously uncatalogued T8.2 candidate, demonstrating the ability of this model-trained approach in discovering faint, late-type UCDs from photometric catalogues.