Feature Guided Training and Rotational Standardisation for the Morphological Classification of Radio Galaxies

Abstract

State-of-the-art radio observatories produce large amounts of data which can be used to study the properties of radio galaxies. However, with this rapid increase in data volume, it has become unrealistic to manually process all of the incoming data, which in turn led to the development of automated approaches for data processing tasks, such as morphological classification. Deep learning plays a crucial role in this automation process and it has been shown that convolutional neural networks (CNNs) can deliver good performance in the morphological classification of radio galaxies. This paper investigates two adaptations to the application of these CNNs for radio galaxy classification. The first adaptation consists of using principal component analysis (PCA) during preprocessing to align the galaxies' principal components with the axes of the coordinate system, which will normalize the orientation of the galaxies. This adaptation led to a significant improvement in the classification accuracy of the CNNs and decreased the average time required to train the models. The second adaptation consists of guiding the CNN to look for specific features within the samples in an attempt to utilize domain knowledge to improve the training process. It was found that this adaptation generally leads to a stabler training process and in certain instances reduced overfitting within the network, as well as the number of epochs required for training.

arXiv comment20 pages, 17 figures, this is a pre-copyedited, author-produced PDF of an article accepted for publication in the Monthly Notices of the Royal Astronomical Society

References in corpus (32)

• Array Programming with NumPy
• LOFAR: The LOw-Frequency ARray
• Machine learning and deep learning
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Active Galactic Nuclei: what's in a name?
• Science with ASKAP - the Australian Square Kilometre Array Pathfinder
• The Last of FIRST: The Final Catalog and Source Identifications
• Radio galaxies and feedback from AGN jets
• An Empirical Analysis of Feature Engineering for Predictive Modeling
• 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
• FRII{\sl{CAT}}: A FIRST catalog of FR~II radio galaxies
• FR0CAT: a FIRST catalog of FR0 radio galaxies
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• FRICAT: A FIRST catalog of FRI radio galaxies
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Radio Galaxy Zoo: Compact and extended radio source classification with deep learning
• Morphological Annotations for Groups in the FIRST Database
• A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
• Radio Galaxy Zoo: Machine learning for radio source host galaxy cross-identification
• CNN Architecture Comparison for Radio Galaxy Classification
• The FIRST Classifier: Compact and Extended Radio Galaxy Classification using Deep Convolutional Neural Networks
• Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness
• The CoNFIG Catalogue - II. Comparison of Space Densities in the FR Dichotomy
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Attention-gating for improved radio galaxy classification
• WATCAT: a tale of wide-angle tailed radio galaxies
• Science with the Murchison Widefield Array: Phase I Results and Phase II Opportunities
• Comparing Pattern Recognition Feature Sets for Sorting Triples in the FIRST Database
• The Combined NVSS-FIRST Galaxies (CoNFIG) Sample - I. Sample Definition, Classification and Evolution
• EnsembleNet: End-to-End Optimization of Multi-headed Models

Cited by in corpus (5)

• A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
• Classification of Radio Sources Through Self-Supervised Learning
• 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
• Quantifying Radio Source Morphology