Date of Award
Deep learning, Galaxy Zoo, Morphology, Residual networks
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
The field of astronomy has made tremendous progress in recent years thanks to advancements in technology and the development of sophisticated algorithms. One area of interest for astronomers is the classification of galaxy morphology, which involves categorizing galaxies based on their visual appearance. However, with the sheer number of galaxy images available, it would be a daunting task to manually classify them all.
To address this challenge, a novel Residual Neural Network (ResNet) model, called ResNet_Var, that can automatically classify galaxy images is proposed in this study. Galaxy Zoo 2 dataset is used in this research, which contains over 28,000 images for the five-class classification task and over 25,000 images for the seven-class classification task.
To evaluate the effectiveness of the ResNet_Var model, various metrics such as accuracy, precision, recall, and F1 score were calculated. The results were impressive, with the ResNet_Var model outperforming other popular networks such as VGG16, VGG19, Inception, and ResNet50. Specifically, the overall classification accuracy of the ResNet_Var model was 95.35% for the five-class classification task and 93.54% for the seven-class classification task.
The potential applications of the ResNet_Var model are vast. With such a high accuracy rate, the ResNet_Var model is well-suited for large-scale galaxy classification in optical space surveys. By automating the classification process, astronomers can quickly and accurately categorize galaxy images according to their morphology. This, in turn, can help advance our understanding of galaxy formation and evolution, as well as provide valuable insights into the properties of dark matter and the nature of the universe.
Patel, Jaykumar, "Classifying Galaxy Images Using Improved Residual Networks" (2023). Electronic Theses and Dissertations. 9112.