Improved Galaxy Morphology Classification with Convolutional Neural Networks

• Published in: Universe (Basel) Vol. 10; no. 6; p. 230
• Main Authors: Urechiatu, Raul, Frincu, Marc
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-06-2024
• Subjects: Accuracy; Algorithms; Astronomers; Automation; Cigars; Classification; convolutional neural networks; Datasets; Decision trees; Galaxies; galaxy classification; Galaxy Zoo 2; image processing; Machine learning; Morphology; Neural networks; Stars & galaxies; Romania
• ISSN: 2218-1997; 2218-1997
• DOI: 10.3390/universe10060230

The increased volume of images and galaxies surveyed by recent and upcoming projects consolidates the need for accurate and scalable automated AI-driven classification methods. This paper proposes a new algorithm based on a custom neural network architecture for classifying galaxies from deep space surveys. The convolutional neural network (CNN) presented is trained using 10,000 galaxy images obtained from the Galaxy Zoo 2 dataset. It is designed to categorize galaxies into five distinct classes: completely round smooth, in-between smooth (falling between completely round and cigar-shaped), cigar-shaped smooth, edge-on, and spiral. The performance of the proposed CNN is assessed using a set of metrics such as accuracy, precision, recall, F1 score, and area under the curve. We compare our solution with well-known architectures like ResNet-50, DenseNet, EfficientNet, Inception, MobileNet, and one proposed model for galaxy classification found in the recent literature. The results show an accuracy rate of 96.83%, outperforming existing algorithms.