Spectral classification of OB-type stars using tree-based ensemble methods and evaluation of their explainability
Abstract
[Abridged] The advent of large-scale spectroscopic surveys will deliver tens of thousands of spectra of blue massive stars. This data volume renders traditional spectral classification techniques increasingly impractical. We aim to develop a robust ML framework for the automated spectral classification of massive OB stars by assessing several tree-based ensemble algorithms. Using a large catalog of high-quality optical spectra of OB stars, we design 3 hierarchical experiments of increasing complexity: classification into broad SpT; fine-grained classification within the O and B domains; and joint classification of SpT and LC. We evaluate 6 algorithms, ranging from single Decision Trees to ensemble methods and gradient boosting techniques. We further analyze model consensus and probabilistic outputs, and employ SHAP value analysis to provide an interpretation of the model decisions by identifying the features that drive each classification. Models achieve excellent performance for broad SpT classification, with LGBM reaching an accuracy of 98%. For fine-grained SpT, RF provides the most robust results (89\%). For the most challenging task combining SpT subtype and LC the XGB reaches a 77% accuracy. Decrease in performance is primarily driven by intrinsic degeneracies in the classical spectral classification scheme. SHAP analysis confirms that the models rely on meaningful spectral features. We also find a high level of agreement among different algorithms, indicating that current performance limits are largely set by the intrinsic complexity of the classification problem rather than by model choice. Tree-based ensemble methods provide a reliable and interpretable framework for the automated spectral classification of OB stars. The combination of full-spectrum modeling, algorithm comparison, and model interpretability offers a robust approach for future large-scale spectroscopic surveys.
Related
- Domain models of turbulent magnetic fields and the spectral shape of ensemble averaged axion-photon conversion
- The NEMESIS general young stellar object catalogue. I. Supervised classification with deep learning methods
- Data representation matters: Optimising machine learning for X-ray source classification by leveraging spatio-spectral information
- Chromospheric sensitivity of stellar spectral lines: an unsupervised machine learning classification
- Feature-Based and Deep Learning Methods for Astronomical Light Curve Classification
BibTeX
@misc{gonzales2026spectral,
title = {{Spectral classification of OB-type stars using tree-based ensemble methods and evaluation of their explainability}},
author = {J. E. Gonzales and S. Simón-Díaz and S. Cuellar and J. A. Conejero and G. Holgado and A. de Burgos},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18590},
eprint = {2609.18590},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18590},
}
RIS
TY - UNPB
TI - Spectral classification of OB-type stars using tree-based ensemble methods and evaluation of their explainability
AU - J. E. Gonzales
AU - S. Simón-Díaz
AU - S. Cuellar
AU - J. A. Conejero
AU - G. Holgado
AU - A. de Burgos
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18590
UR - https://arxiv.org/abs/2609.18590
AB - [Abridged] The advent of large-scale spectroscopic surveys will deliver tens of thousands of spectra of blue massive stars. This data volume renders traditional spectral classification techniques increasingly impractical. We aim to develop a robust ML framework for the automated spectral classification of massive OB stars by assessing several tree-based ensemble algorithms. Using a large catalog of high-quality optical spectra of OB stars, we design 3 hierarchical experiments of increasing complexity: classification into broad SpT; fine-grained classification within the O and B domains; and joint classification of SpT and LC. We evaluate 6 algorithms, ranging from single Decision Trees to ensemble methods and gradient boosting techniques. We further analyze model consensus and probabilistic outputs, and employ SHAP value analysis to provide an interpretation of the model decisions by identifying the features that drive each classification. Models achieve excellent performance for broad SpT classification, with LGBM reaching an accuracy of 98%. For fine-grained SpT, RF provides the most robust results (89\%). For the most challenging task combining SpT subtype and LC the XGB reaches a 77% accuracy. Decrease in performance is primarily driven by intrinsic degeneracies in the classical spectral classification scheme. SHAP analysis confirms that the models rely on meaningful spectral features. We also find a high level of agreement among different algorithms, indicating that current performance limits are largely set by the intrinsic complexity of the classification problem rather than by model choice. Tree-based ensemble methods provide a reliable and interpretable framework for the automated spectral classification of OB stars. The combination of full-spectrum modeling, algorithm comparison, and model interpretability offers a robust approach for future large-scale spectroscopic surveys.
ER -