Machine learning technique for morphological classification of galaxies from the SDSS

Abstract

Context. Machine learning methods are effective tools in astronomical tasks for classifying objects by their individual features. One of the promising utilities is related to the morphological classification of galaxies at different redshifts. Aims. We use the photometry-based approach for the SDSS data (1) to exploit five supervised machine learning techniques and define the most effective among them for the automated galaxy morphological classification; (2) to test the influence of photometry data on morphology classification; (3) to discuss problem points of supervised machine learning and labeling bias; and (4) to apply the best fitting machine learning methods for revealing the unknown morphological types of galaxies from the SDSS DR9 at z < 0.1. Methods. We used different galaxy classification techniques: human labeling, multi-photometry diagrams, naive Bayes, logistic regression, support-vector machine, random forest, k-nearest neighbors. Results. We present the results of a binary automated morphological classification of galaxies conducted by human labeling, multi-photometry, and five supervised machine learning methods. We applied it to the sample of galaxies from the SDSS DR9 with redshifts of 0.02 < z < 0.1 and absolute stellar magnitudes of −24m < Mr < −19.4m. For the analysis we used absolute magnitudes Mu, Mg, Mr, Mi, Mz; color indices Mu − Mr, Mg − Mi, Mu − Mg, Mr − Mz; and the inverse concentration index to the center R50/R90. We determined the ability of each method to predict the morphological type, and verified various dependencies of the method’s accuracy on redshifts, human labeling, morphological shape, and overlap of different morphological types for galaxies with the same color indices. We find that the morphology based on the supervised machine learning methods trained over photometric parameters demonstrates significantly less bias than the morphology based on citizen-science classifiers. Conclusions. The support-vector machine and random forest methods with Scikit-learn software machine learning library in Python provide the highest accuracy for the binary galaxy morphological classification. Specifically, the success rate is 96.4% for support-vector machine (96.1% early E and 96.9% late L types) and 95.5% for random forest (96.7% early E and 92.8% late L types). Applying the support-vector machine for the sample of 316 031 galaxies from the SDSS DR9 at z < 0.1 with unknown morphological types, we found 139 659 E and 176 372 L types among them.