Using classical Convolutional Neural Networks (CNN) to classify the galaxies of the Galaxy Zoo dataset is by no means a novel idea and has been investigated repeatedly and with higher frequency with the rise of Machine Learning literacy and spread across Data Science domains.
However, combining modified galaxy images with other metrics captured in the SDSS DR7 & DR8 and feeding this collective information into a network presents an opportunity to increase accuracy of classifiers with the additional benefit of potentially learning something new about the classification of these abstract objects.