基于树集成方法的OB型恒星光谱分类及其可解释性评估
Spectral classification of OB-type stars using tree-based ensemble methods and evaluation of their explainability
- Instituto de Astrofísica de Canarias（加那利群岛天体物理研究所）
- Departamento de Astrofísica, Universidad de La Laguna（拉各鲁纳大学天体物理学系）
- Centro Multidisciplinario de Física, Vicerrectoría de Investigación, Universidad Mayor（马约尔大学多学科物理中心）
- Instituto Universitario de Matemática Pura y Aplicada. Universitat Politècnica de València（瓦伦西亚理工大学纯数学和应用数学大学研究所）
- European Southern Observatory（欧洲南方天文台）
- Departamento de Matemática Aplicada, Universidad Nacional Autónoma de Honduras（洪都拉斯国立自治大学应用数学系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究利用树集成算法（如LGBM、RF、XGB）对OB型恒星光谱进行分类，在宽分类、细分类及联合分类任务中分别达到98%、89%和77%的准确率，并通过SHAP分析验证了模型的可解释性，为大规模光谱巡天提供了可靠方案。
AI中文摘要：
[节略] 大规模光谱巡天的到来将提供数万条蓝色大质量恒星的光谱。这一数据量使得传统的光谱分类技术日益不切实际。我们旨在通过评估几种基于树的集成算法，开发一个稳健的机器学习框架，用于大质量OB恒星的自动光谱分类。利用一个大型高质量OB恒星光学光谱目录，我们设计了3个复杂度递增的层次实验：宽光谱型（SpT）分类；O域和B域内的细粒度分类；以及光谱型和光度级（LC）的联合分类。我们评估了6种算法，从单一决策树到集成方法和梯度提升技术。我们进一步分析了模型共识和概率输出，并采用SHAP值分析，通过识别驱动每个分类的特征来提供模型决策的解释。模型在宽光谱型分类上取得了优异性能，其中LGBM达到了98%的准确率。对于细粒度光谱型，RF提供了最稳健的结果（89%）。对于结合光谱型亚型和光度级的最具挑战性任务，XGB达到了77%的准确率。性能下降主要由经典光谱分类方案中的内在简并性驱动。SHAP分析证实模型依赖于有意义的谱特征。我们还发现不同算法之间高度一致，表明当前性能限制主要由分类问题的内在复杂性决定，而非模型选择。基于树的集成方法为OB恒星的自动光谱分类提供了一个可靠且可解释的框架。全谱建模、算法比较和模型可解释性的结合为未来大规模光谱巡天提供了一种稳健的方法。
英文摘要：
[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.
