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.

arXiv comment17 pages, 11 figures, Accepted for publication in MNRAS

References in corpus (24)

• Adam: A Method for Stochastic Optimization
• LOFAR: The LOw-Frequency ARray
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• The LOFAR Two-metre Sky Survey - I. Survey Description and Preliminary Data Release
• The LOFAR Two-metre Sky Survey - II. First data release
• EMU: Evolutionary Map of the Universe
• Improving galaxy morphologies for SDSS with Deep Learning
• On the Relationship between BL-Lacertae Objects and FRI Radio Galaxies
• Relativistic Jets and the Fanaroff-Riley Classification of Radio Galaxies
• Capsule Network Performance on Complex Data
• Radio-loud AGN in the first LoTSS data release: The lifetimes and environmental impact of jet-driven sources
• The LOFAR Two-metre Sky Survey (LoTSS) III. First Data Release: optical/IR identifications and value-added catalogue
• A pilot study of the radio-emitting AGN population: the emerging new class of FR0 radio-galaxies
• Classifying Radio Galaxies with Convolutional Neural Network
• Radio Galaxy Zoo: host galaxies and radio morphologies derived from visual inspection
• On the two main classes of Active Galactic Nuclei
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• Radio Galaxy Zoo: Compact and extended radio source classification with deep learning
• Radio Galaxy Zoo: Machine learning for radio source host galaxy cross-identification
• The FIRST Classifier: Compact and Extended Radio Galaxy Classification using Deep Convolutional Neural Networks
• Transfer learning for radio galaxy classification
• Understanding the Fanaroff-Riley radio galaxy classification
• Galaxy morphology prediction using capsule networks

Cited by in corpus (26)

• 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
• Machine learning technique for morphological classification of galaxies from the SDSS. I. Photometry-based approach
• 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
• CapsNets Continuing the Convolutional Quest
• 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
• Diffuse radio emission from non-Planck galaxy clusters in the LoTSS-DR2 fields
• Radio Galaxy Zoo: New Giant Radio Galaxies in the RGZ DR1catalogue
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• The morphological classification of distant radio galaxies explored with three-dimensional simulations
• 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
• Classification of Radio Sources Through Self-Supervised Learning
• Morphological Classification of Extragalactic Radio Sources Using Gradient Boosting Methods
• 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