arXiv subjects

Anna M. M. Scaife

Publications and source records attributed to Anna M. M. Scaife.

At least 19 recordsLinked to original sources

arXiv2026

Faraday Tomography with the SKA: A New Era of Cosmic Magnetism Studies

The Square Kilometre Array (SKA) represents a significant advancement in radio astronomy, enabling detailed study of cosmic magnetism through Faraday Rotation and Faraday Measurement Synthesis. This chapter provides a comprehensive review of these techniques, tracing their development and illustrating their crucial role in investigating magnetic fields across different cosmic environments. We focus on Array Assembly 4 (AA4), the final deployment stage, featuring 197 dishes (133 SKA, 64 MeerKAT) with 40 km maximum baselines and frequency coverage from 350 MHz to 15.4 GHz (goal: 24 GHz). These capabilities enable high-resolution Faraday tomography of magnetic structures in galaxies, clusters, and the cosmic web. We also highlight the earlier AA* stage with 144 dishes (80 SKA, 64 MeerKAT). Band 1 (350--1050 MHz) offers the finest Faraday depth resolution among the dish bands (full resolution $\sim$2.5 rad m$^{-2}$) with a maximum observable depth around 174,708 rad m$^{-2}$. Other bands (Band 2, Band 5a, Band 5b) enable multi-scale studies, probing larger structures with lower resolution but higher maximum depths. We discuss synergies between Faraday Measurement Synthesis and Image Synthesis techniques, showing how they complement each other in reconstructing magnetic field structures. Simulation results demonstrate the SKA's potential for high-resolution observations. We explore possible enhancements beyond the baseline configuration and synergies with other observatories, emphasizing multi-wavelength astronomy. This chapter aims to provide a thorough account of how the SKA's phased deployment from AA* to AA4 will transform our understanding of cosmic magnetic fields and drive new discoveries in astrophysics.

astro-ph.IM↗

arXiv2026

Variational views for self-supervised learning in radio astronomy

Modern astronomical surveys are producing progressively larger and more complex datasets, making traditional supervised approaches that rely on extensive labelled catalogues increasingly difficult. Consequently, pre-training using self-supervised learning (SSL), which offers a scalable route by extracting structure directly from unlabelled images, is becoming attractive for many downstream applications. In this work we consider the use of coupled self-supervised representation learning approaches for radio galaxy morphology pre-training. In order to account for the more nuanced variations in radio galaxy morphology than are typically included in the augmented views of view-based SSL algorithms, we use a pre-trained Variational Autoencoder (VAE) to generate views for training a larger view-based self-supervised model. To do this, a $β$-VAE was trained on the Radio Galaxy Zoo (RGZ) dataset, where moderate regularization ($β= 2.3$) was found to provide a good balance between reconstruction quality and disentanglement of generative factors such as source multiplicity and lobe asymmetry. An analysis of the $β$-VAE reveals that Fanaroff-Riley class identity manifests as a continuous transition across the latent space, rather than being associated to a single discrete dimension. $β$-VAE reconstructions were then incorporated as generative augmentations within a view-based SSL pipeline. Our experiments show that combining these generative views with standard image augmentations improves downstream classification performance, and we present ablation studies clarifying the relative contribution of each augmentation type. These results indicate that generative and contrastive approaches are complementary, and point toward disentanglement-aware self-supervised learning as a promising direction for future radio astronomy surveys.

astro-ph.IM↗

arXiv2026

Monte Carlo conformal prediction for quantifying uncertainty in radio galaxy classification under ambiguous ground truth

Dramatically increasing data volumes are forcing astronomers to adopt automated methods for the identification and classification of astronomical objects. Although deep-learning models are often well-suited to this task, obtaining a measure of uncertainty on their predictions is challenging. Here we consider the suitability of Monte Carlo conformal prediction (MCCP) set size and confidence as measures of model uncertainty for the astronomical classification of radio galaxies. We demonstrate this approach using model predictions from a pre-trained radio galaxy foundation model, fine-tuned on a smaller set of labelled radio galaxies. We calibrate the MCCP by obtaining annotator-derived soft label distributions, i.e. probability distributions over classes instead of single class assignments, for each of these labelled radio galaxies and compare the resulting set sizes and confidence scores to predictive entropy measures for each galaxy obtained using a supervised Bayesian deep-learning model trained using Hamiltonian Monte Carlo (HMC). The comparison reveals only a weak correlation between the measures.

astro-ph.IM↗

arXiv2025

Galaxy Zoo Evo: 1 million human-annotated images of galaxies

We introduce Galaxy Zoo Evo, a labeled dataset for building and evaluating foundation models on images of galaxies. GZ Evo includes 104M crowdsourced labels for 823k images from four telescopes. Each image is labeled with a series of fine-grained questions and answers (e.g. "featured galaxy, two spiral arms, tightly wound, merging with another galaxy"). These detailed labels are useful for pretraining or finetuning. We also include four smaller sets of labels (167k galaxies in total) for downstream tasks of specific interest to astronomers, including finding strong lenses and describing galaxies from the new space telescope Euclid. We hope GZ Evo will serve as a real-world benchmark for computer vision topics such as domain adaption (from terrestrial to astronomical, or between telescopes) or learning under uncertainty from crowdsourced labels. We also hope it will support a new generation of foundation models for astronomy; such models will be critical to future astronomers seeking to better understand our universe.

astro-ph.IM↗

arXiv2025

Natural gradient descent for improving variational inference based classification of radio galaxies

Bayesian neural networks (BNNs) are most commonly optimised with first-order optimisers such as stochastic gradient descent. However, when optimising for parameters of probabilistic models, incorporating second order information during optimisation can lead to a more direct path in the distribution space and faster convergence. In this work we examine whether using natural gradient descent can improve the performance of variational inference based classification of radio galaxies. We use the Improved Variational Online Newton (iVON) algorithm and compare its performance against a recent benchmark for BNNs for radio galaxy classification. We find that iVON results in better uncertainty calibration out of all the methods previously considered while providing similar predictive performance to the best performing inference methods such as Hamiltonian Monte Carlo and Bayes by Backprop based variational inference. Models trained with iVON can distinguish far out-of-distribution optical galaxy data, but they cannot reliably detect radio galaxy images from a telescope with different resolution and sensitivity. We find that the cold posterior effect persists in the models trained with iVON. Our results suggest that the choice of the optimiser can lead to qualitatively different solutions and future work using probabilistic neural network models should carefully consider the inductive biases being encoded through the optimisation process, in addition to the data, architecture and inference method.

astro-ph.IM↗

arXiv2025

Radio Galaxy Zoo: Morphological classification by Fanaroff-Riley designation using self-supervised pre-training

In this study, we examine over 14,000 radio galaxies finely selected from Radio Galaxy Zoo (RGZ) project and provide classifications for approximately 5,900 FRIs and 8,100 FRIIs. We present an analysis of these predicted radio galaxy morphologies for the RGZ catalogue, classified using a pre-trained radio galaxy foundation model that has been fine-tuned to predict Fanaroff-Riley (FR) morphology. As seen in previous studies, our results show overlap between morphologically classified FRI and FRII luminosity-size distributions and we find that the model's confidence in its predictions is lowest in this overlap region, suggesting that source morphologies are more ambiguous. We identify the presence of low-luminosity FRII sources, the proportion of which, with respect to the total number of FRIIs, is consistent with previous studies. However, a comparison of the low-luminosity FRII sources found in this work with those identified by previous studies reveals differences that may indicate their selection is influenced by the choice of classification methodology. We investigate the impacts of both pre-training and fine-tuning data selection on model performance for the downstream classification task, and show that while different pre-training data choices affect model confidence they do not appear to cause systematic generalisation biases for the range of physical and observational characteristics considered in this work; however, we note that the same is not necessarily true for fine-tuning. As automated approaches to astronomical source identification and classification become increasingly prevalent, we highlight training data choices that can affect the model outputs and propagate into downstream analyses.

astro-ph.GA↗

arXiv2024

E(2)-Equivariant Features in Machine Learning for Morphological Classification of Radio Galaxies

With the growth of data from new radio telescope facilities, machine-learning approaches to the morphological classification of radio galaxies are increasingly being utilised. However, while widely employed deep-learning models using convolutional neural networks (CNNs) are equivariant to translations within images, neither CNNs nor most other machine-learning approaches are equivariant to additional isometries of the Euclidean plane, such as rotations and reflections. Recent work has attempted to address this by using G-steerable CNNs, designed to be equivariant to a specified subset of 2-dimensional Euclidean, E(2), transformations. Although this approach improved model performance, the computational costs were a recognised drawback. Here we consider the use of directly extracted E(2)-equivariant features for the classification of radio galaxies. Specifically, we investigate the use of Minkowski functionals (MFs), Haralick features (HFs) and elliptical Fourier descriptors (EFDs). We show that, while these features do not perform equivalently well to CNNs in terms of accuracy, they are able to inform the classification of radio galaxies, requiring ~50 times less computational runtime. We demonstrate that MFs are the most informative, EFDs the least informative, and show that combinations of all three result in only incrementally improved performance, which we suggest is due to information overlap between feature sets.

astro-ph.IM↗

arXiv2024

Evaluating Bayesian deep learning for radio galaxy classification

The radio astronomy community is rapidly adopting deep learning techniques to deal with the huge data volumes expected from the next generation of radio observatories. Bayesian neural networks (BNNs) provide a principled way to model uncertainty in the predictions made by such deep learning models and will play an important role in extracting well-calibrated uncertainty estimates on their outputs. In this work, we evaluate the performance of different BNNs against the following criteria: predictive performance, uncertainty calibration and distribution-shift detection for the radio galaxy classification problem.

cs.LG↗

arXiv2024

Scaling Laws for Galaxy Images

We present the first systematic investigation of supervised scaling laws outside of an ImageNet-like context - on images of galaxies. We use 840k galaxy images and over 100M annotations by Galaxy Zoo volunteers, comparable in scale to Imagenet-1K. We find that adding annotated galaxy images provides a power law improvement in performance across all architectures and all tasks, while adding trainable parameters is effective only for some (typically more subjectively challenging) tasks. We then compare the downstream performance of finetuned models pretrained on either ImageNet-12k alone vs. additionally pretrained on our galaxy images. We achieve an average relative error rate reduction of 31% across 5 downstream tasks of scientific interest. Our finetuned models are more label-efficient and, unlike their ImageNet-12k-pretrained equivalents, often achieve linear transfer performance equal to that of end-to-end finetuning. We find relatively modest additional downstream benefits from scaling model size, implying that scaling alone is not sufficient to address our domain gap, and suggest that practitioners with qualitatively different images might benefit more from in-domain adaption followed by targeted downstream labelling.

cs.CV↗

arXiv2023

Rare Galaxy Classes Identified In Foundation Model Representations

We identify rare and visually distinctive galaxy populations by searching for structure within the learned representations of pretrained models. We show that these representations arrange galaxies by appearance in patterns beyond those needed to predict the pretraining labels. We design a clustering approach to isolate specific local patterns, revealing groups of galaxies with rare and scientifically-interesting morphologies.

astro-ph.GA↗

arXiv2023

Bayesian Imaging for Radio Interferometry with Score-Based Priors

The inverse imaging task in radio interferometry is a key limiting factor to retrieving Bayesian uncertainties in radio astronomy in a computationally effective manner. We use a score-based prior derived from optical images of galaxies to recover images of protoplanetary disks from the DSHARP survey. We demonstrate that our method produces plausible posterior samples despite the misspecified galaxy prior. We show that our approach produces results which are competitive with existing radio interferometry imaging algorithms.

astro-ph.IM↗

arXiv2023

Combining astrophysical datasets with CRUMB

At present, the field of astronomical machine learning lacks widely-used benchmarking datasets; most research employs custom-made datasets which are often not publicly released, making comparisons between models difficult. In this paper we present CRUMB, a publicly-available image dataset of Fanaroff-Riley galaxies constructed from four "parent" datasets extant in the literature. In addition to providing the largest image dataset of these galaxies, CRUMB uses a two-tier labelling system: a "basic" label for classification and a "complete" label which provides the original class labels used in the four parent datasets, allowing for disagreements in an image's class between different datasets to be preserved and selective access to sources from any desired combination of the parent datasets.

astro-ph.IM↗

arXiv2023

Radio Galaxy Zoo: Towards building the first multi-purpose foundation model for radio astronomy with self-supervised learning

In this work, we apply self-supervised learning with instance differentiation to learn a robust, multi-purpose representation for image analysis of resolved extragalactic continuum images. We train a multi-use model which compresses our unlabelled data into a structured, low dimensional representation which can be used for a variety of downstream tasks (e.g. classification, similarity search). We exceed baseline supervised Fanaroff-Riley classification performance by a statistically significant margin, with our model reducing the test set error by up to half. Our model is also able to maintain high classification accuracy with very few labels, with only 7.79% error when only using 145 labels. We further demonstrate that by using our foundation model, users can efficiently trade off compute, human labelling cost and test set accuracy according to their respective budgets, allowing for efficient classification in a wide variety of scenarios. We highlight the generalizability of our model by showing that it enables accurate classification in a label scarce regime with data from the new MIGHTEE survey without any hyper-parameter tuning, where it improves upon the baseline by ~8%. Visualizations of our labelled and un-labelled data show that our model's representation space is structured with respect to physical properties of the sources, such as angular source extent. We show that the learned representation is scientifically useful even if no labels are available by performing a similarity search, finding hybrid sources in the RGZ DR1 data-set without any labels. We show that good augmentation design and hyper-parameter choice can help achieve peak performance, while emphasising that optimal hyper-parameters are not required to obtain benefits from self-supervised pre-training.

astro-ph.IM↗

arXiv2023

Galaxy Zoo DESI: Detailed Morphology Measurements for 8.7M Galaxies in the DESI Legacy Imaging Surveys

We present detailed morphology measurements for 8.67 million galaxies in the DESI Legacy Imaging Surveys (DECaLS, MzLS, and BASS, plus DES). These are automated measurements made by deep learning models trained on Galaxy Zoo volunteer votes. Our models typically predict the fraction of volunteers selecting each answer to within 5-10\% for every answer to every GZ question. The models are trained on newly-collected votes for DESI-LS DR8 images as well as historical votes from GZ DECaLS. We also release the newly-collected votes. Extending our morphology measurements outside of the previously-released DECaLS/SDSS intersection increases our sky coverage by a factor of 4 (5,000 to 19,000 deg$^2$) and allows for full overlap with complementary surveys including ALFALFA and MaNGA.

astro-ph.GA↗

arXiv2023

MiraBest: A Dataset of Morphologically Classified Radio Galaxies for Machine Learning

The volume of data from current and future observatories has motivated the increased development and application of automated machine learning methodologies for astronomy. However, less attention has been given to the production of standardised datasets for assessing the performance of different machine learning algorithms within astronomy and astrophysics. Here we describe in detail the MiraBest dataset, a publicly available batched dataset of 1256 radio-loud AGN from NVSS and FIRST, filtered to $0.03 < z < 0.1$, manually labelled by Miraghaei and Best (2017) according to the Fanaroff-Riley morphological classification, created for machine learning applications and compatible for use with standard deep learning libraries. We outline the principles underlying the construction of the dataset, the sample selection and pre-processing methodology, dataset structure and composition, as well as a comparison of MiraBest to other datasets used in the literature. Existing applications that utilise the MiraBest dataset are reviewed, and an extended dataset of 2100 sources is created by cross-matching MiraBest with other catalogues of radio-loud AGN that have been used more widely in the literature for machine learning applications.

astro-ph.IM↗

arXiv2023

Radio Galaxy Zoo EMU: Towards a Semantic Radio Galaxy Morphology Taxonomy

We present a novel natural language processing (NLP) approach to deriving plain English descriptors for science cases otherwise restricted by obfuscating technical terminology. We address the limitations of common radio galaxy morphology classifications by applying this approach. We experimentally derive a set of semantic tags for the Radio Galaxy Zoo EMU (Evolutionary Map of the Universe) project and the wider astronomical community. We collect 8,486 plain English annotations of radio galaxy morphology, from which we derive a taxonomy of tags. The tags are plain English. The result is an extensible framework which is more flexible, more easily communicated, and more sensitive to rare feature combinations which are indescribable using the current framework of radio astronomy classifications.

astro-ph.GA↗

arXiv2022

A New Task: Deriving Semantic Class Targets for the Physical Sciences

We define deriving semantic class targets as a novel multi-modal task. By doing so, we aim to improve classification schemes in the physical sciences which can be severely abstracted and obfuscating. We address this task for upcoming radio astronomy surveys and present the derived semantic radio galaxy morphology class targets.

astro-ph.IM↗

arXiv2022

CS-ROMER: A novel compressed sensing framework for Faraday depth reconstruction

The reconstruction of Faraday depth structure from incomplete spectral polarization radio measurements using the RM Synthesis technique is an under-constrained problem requiring additional regularisation. In this paper we present cs-romer: a novel object-oriented compressed sensing framework to reconstruct Faraday depth signals from spectro-polarization radio data. Unlike previous compressed sensing applications, this framework is designed to work directly with data that are irregularly sampled in wavelength-squared space and to incorporate multiple forms of compressed sensing regularisation. We demonstrate the framework using simulated data for the VLA telescope under a variety of observing conditions, and we introduce a methodology for identifying the optimal basis function for reconstruction of these data, using an approach that can also be applied to datasets from other telescopes and over different frequency ranges. In this work we show that the delta basis function provides optimal reconstruction for VLA L-band data and we use this basis with observations of the low-mass galaxy cluster Abell 1314 in order to reconstruct the Faraday depth of its constituent cluster galaxies. We use the cs-romer framework to de-rotate the Galactic Faraday depth contribution directly from the wavelength-squared data and to handle the spectral behaviour of different radio sources in a direction-dependent manner. The results of this analysis show that individual galaxies within Abell 1314 deviate from the behaviour expected for a Faraday-thin screen such as the intra-cluster medium and instead suggest that the Faraday rotation exhibited by these galaxies is dominated by their local environments.

astro-ph.IM↗