Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks

Abstract

Next-generation radio surveys will yield an unprecedented amount of data, warranting analysis by use of machine learning techniques. Convolutional neural networks are the deep learning technique that has proven to be the most successful in classifying image data. Capsule networks are a more recently developed technique that use capsules comprised of groups of neurons, that describe properties of an image including the relative spatial locations of features. The current work explores the performance of different capsule network architectures against simpler convolutional neural network architectures, in reproducing the classifications into the classes of unresolved, FRI and FRII morphologies. We utilise images from a LOFAR survey which is the deepest, wide-area radio survey to date, revealing more complex radio-source structures compared to previous surveys, presenting further challenges for machine learning algorithms. The 4- and 8-layer convolutional networks attain an average precision of 93.3% and 94.3% respectively, compared to 89.7% obtained with the capsule network, when training on original and augmented images. Implementing transfer learning achieves a precision of 94.4%, that is within the confidence interval of the 8-layer convolutional network. The convolutional networks always outperform any variation of the capsule network, as they prove to be more robust to the presence of noise in images. The use of pooling appears to allow more freedom for the intra-class variability of radio galaxy morphologies, as well as reducing the impact of noise.

17 pages, 11 figures, Accepted for publication in MNRAS

References in corpus (6)

• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The LOFAR Two-metre Sky Survey - I. Survey Description and Preliminary Data Release
• Capsule Network Performance on Complex Data
• A pilot study of the radio-emitting AGN population: the emerging new class of FR0 radio-galaxies
• Classifying Radio Galaxies with Convolutional Neural Network
• On the two main classes of Active Galactic Nuclei

Cited by in corpus (23)

• Revisiting the Fanaroff-Riley dichotomy and radio-galaxy morphology with the LOFAR Two-Metre Sky Survey (LoTSS)
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The Planck clusters in the LOFAR sky. I. LoTSS-DR2: new detections and sample overview
• CNN Architecture Comparison for Radio Galaxy Classification
• Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps
• Attention-gating for improved radio galaxy classification
• The evolution of barred galaxies in the EAGLE simulations
• Bars formed in galaxy merging and their classification with deep learning
• Deep Learning Assisted Data Inspection for Radio Astronomy
• Rapid sorting of radio galaxy morphology using Haralick features
• Normative Epistemology for Lethal Autonomous Weapons Systems
• A machine learning classifier for LOFAR radio galaxy cross-matching techniques
• Radio Galaxy Zoo: New Giant Radio Galaxies in the RGZ DR1catalogue
• Diffuse radio emission from non-Planck galaxy clusters in the LoTSS-DR2 fields
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• Identifying anomalous radio sources in the EMU Pilot Survey using a complexity-based approach
• Challenging interferometric imaging: Machine learning-based source localization from uv-plane observations
• Morphological Classification of Extragalactic Radio Sources Using Gradient Boosting Methods
• Classification of Radio Sources Through Self-Supervised Learning
• The Complexity and Information Content of Simulated Universes
• E(2)-Equivariant Features in Machine Learning for Morphological Classification of Radio Galaxies
• Transformer-Based Source Detection and Morphological Classification in LOFAR Deep-Field Continuum Images