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

2025-08-12

AI Summary

This study addresses the challenge of automated spectral classification for low-mass M0–T9 dwarfs and brown dwarfs from low-resolution near-infrared spectra. We systematically apply three machine learning algorithms—Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbors (k-NN)—to jointly predict spectral type, surface gravity, and metallicity subclass. Using SpeX spectroscopic data, we extract features including z- and y-band fluxes and molecular band indices (e.g., FeH, TiO), employing binned flux representations and multiple normalization strategies. Results show that the optimized k-NN model achieves 95.5±0.6% accuracy in spectral type classification (within ±1 subtype) and 89.5±0.9% accuracy for gravity and metallicity subclasses. For spectra with signal-to-noise ratio >60, overall classification accuracy exceeds 95%. This work significantly enhances the efficiency and robustness of physical parameter classification for late-type dwarfs in large-scale surveys.

Technology Category

• Machine Learning: Classification and Regression
• Data Mining & Knowledge Management: Data Compression
• Natural Language Processing: Text Classification & Sentiment Analysis

Application Category

• Web Mining and Content Analysis: Machine learning and data science for the Web
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Automate spectral typing of M0-T9 dwarfs using machine learning.
• Classify gravity and metallicity subclasses for late-type dwarfs.
• Evaluate ML models for accuracy in low-resolution near-infrared spectra.

Innovation

• Machine learning for spectral type classification
• Random Forest, SVM, KNN models compared
• KNN achieves 95.5% classification accuracy