Atmospheric model-trained machine learning selection and classification of ultracool TY dwarfs

TL;DR

This paper introduces a machine learning framework trained on synthetic atmospheric model photometry to detect and classify ultracool T and Y dwarfs, significantly expanding the known sample and enabling discovery of new faint objects.

Contribution

The novel approach trains classifiers on synthetic data from atmospheric models, overcoming limited empirical samples of ultracool dwarfs for improved detection and classification.

Findings

Achieved >99% classification accuracy on known UCDs.

Spectral type precision within 0.37 subtypes.

Discovered a new T8.2 candidate in a test region.

Abstract

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 dataset over two orders of magnitude larger than any empirical set of >T6 UCDs. Polynomial color 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 datasets, verifying catalogs of known UCDs with object classification metrics >99% and an average spectral type precision within 0.35 +/- 0.37 subtypes. Application of the model to a 1.5 degree region around 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 catalogs.