Machine Learning-Based Classification of Active Galaxies and Estimation of Supermassive Black Hole Masses

Abstract

Distinguishing active galaxies from star-forming galaxies is essential for understanding galaxy evolution. Diagnostic methods like the BPT (Baldwin, Phillips, and Terlevich) diagram use optical emission-line ratios to separate galaxies. However, with growing availability of large surveys and high-resolution instruments, manually identifying galaxy types has become increasingly challenging. In this study, we investigate machine learning to classify active and star-forming galaxies using properties like stellar mass, stellar velocity dispersion, colour, redshift, and [O III] luminosity. These new approaches enable faster AGN/star-forming galaxy classification than the BPT diagram and provide a flexible, scalable alternative that can complement traditional diagnostics, particularly for large surveys or low-quality data. We employ four classification algorithms -- Decision Tree, Random Forest, Support Vector Classifier (SVC), and k-Nearest Neighbours (KNN) -- using the Galaxy Zoo 1 dataset derived from the SDSS sample. The dataset contains 47,675 galaxies within the redshift range 0.02--0.05, including 17,002 pure star-forming and 2,254 active galaxies, labeled using the BPT diagram. These labels train and evaluate our models through confusion matrices, learning curves, and receiver operating characteristic (ROC) curves. Among the four algorithms, the SVC and Random Forest models achieve the highest accuracy of approximately 93\%, while KNN shows the lowest at 88\%. Furthermore, we estimate supermassive black hole masses using stellar velocity dispersion ($σ$) and the $M_{\rm BH}-σ$ relation. We apply four regression models -- Random Forest Regressor, Support Vector Regressor (SVR), KNN Regressor, and Polynomial Regression. All four models produce similar results, with $R^2$ values from 0.75 to 0.77, indicating consistent performance.

Figures (7)

• Figure 1: Bar plots of evaluation metrics used for classification models.
• Figure 2: ROC curves for applied classification models. The SVC model indicates the best performance (AUC=0.98), and the KNN model shows the worst one (AUC=0.93).
• Figure 3: Confusion matrix results for our classification models. The SVC and Random Forest classifiers achieve the highest number of correctly predicted class labels. The misclassification rates increase in the Decision Tree model. The KNN classifier produces the most false predictions in the Star-Forming class, indicating the weakest performance among the four classifiers.
• Figure 4: Learning curve results (F1-score versus training examples) for the four classifier models. The blue line denotes the training score, while the green line represents the cross-validation score. The shaded regions around each curve indicate the standard deviation.
• Figure 5: SHAP values are shown for each feature, with the color bar representing the actual values of the corresponding features.