Classifying Cool Dwarfs: Comprehensive Spectral Typing of Field and Peculiar Dwarfs Using Machine Learning

TL;DR

This paper demonstrates that machine learning models can accurately classify spectral types, surface gravity, and metallicity of low-mass stars and brown dwarfs using low-resolution near-infrared spectra, enabling automated analysis of large datasets.

Contribution

The study applies and compares multiple ML algorithms to classify low-resolution spectra of M0--T9 dwarfs, achieving high accuracy and identifying key spectral features for subclass determination.

Findings

KNN model classifies 95.5% of sources within ±1 spectral type.

Surface gravity and metallicity subclasses are classified with 89.5% accuracy.

Higher SNR (>60) sources achieve over 95% classification accuracy.

Abstract

Low-mass stars and brown dwarfs -- spectral types (SpTs) M0 and later -- play a significant role in studying stellar and substellar processes and demographics, reaching down to planetary-mass objects. Currently, the classification of these sources remains heavily reliant on visual inspection of spectral features, equivalent width measurements, or narrow-/wide-band spectral indices. Recent advances in machine learning (ML) methods offer automated approaches for spectral typing, which are becoming increasingly important as large spectroscopic surveys such as Gaia, SDSS, and SPHEREx generate datasets containing millions of spectra. We investigate the application of ML in spectral type classification on low-resolution (R $\sim$ 120) near-infrared spectra of M0--T9 dwarfs obtained with the SpeX instrument on the NASA Infrared Telescope Facility. We specifically aim to classify the gravity- and metallicity-dependent subclasses for late-type dwarfs. We used binned fluxes as input features and compared the efficacy of spectral type estimators built using Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) models. We tested the influence of different normalizations and analyzed the relative importance of different spectral regions for surface gravity and metallicity subclass classification. Our best-performing model (using KNN) classifies 95.5 $\pm$ 0.6% of sources to within $\pm$1 SpT, and assigns surface gravity and metallicity subclasses with 89.5 $\pm$ 0.9% accuracy. We test the dependence of signal-to-noise ratio on classification accuracy and find sources with SNR $\gtrsim$ 60 have $\gtrsim$ 95% accuracy. We also find that zy-band plays the most prominent role in the RF model, with FeH and TiO having the highest feature importance.