Related papers: SKATR: A Self-Supervised Summary Transformer for S…
We consider the problem of analyzing the structure of spectroscopic cubes using unsupervised machine learning techniques. We propose representing the target's signal as a homogeneous set of volumes through an iterative algorithm that…
We construct forecasts for cosmological parameter constraints from weak gravitational lensing surveys involving the Square Kilometre Array (SKA). Considering matter content, dark energy and modified gravity parameters, we show that the…
We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline convenient theoretical properties arising from the choice of basis including spatial…
This manuscript introduces SARFormer, a modified Vision Transformer (ViT) architecture designed for processing one or multiple synthetic aperture radar (SAR) images. Given the complex image geometry of SAR data, we propose an acquisition…
Modern radio telescope surveys, capable of detecting billions of galaxies in wide-field surveys, have made manual morphological classification impracticable. This applies in particular when the Square Kilometre Array Observatory (SKAO)…
We investigate the potential of the Square Kilometre Array (SKA) for measuring the magnetic fields in clusters of galaxies via Faraday rotation of background polarised sources. [...] We find that about 10 per cent of the sky is covered by a…
The Square Kilometre Array (SKA) will transform our understanding of the role of the cold, atomic gas in galaxy evolution. The interstellar medium (ISM) is the repository of stellar ejecta and the birthsite of new stars and, hence, a key…
This paper describes a programme to map large-scale cosmic structures on the largest possible scales by using the Five hundred metre Aperture Spherical Telescope (FAST) to make a 21 cm (red-shifted) intensity map of the sky for the range…
The advent of new observational facilities in the last two decades has allowed the rapid discovery and high-resolution optical imaging of many strong lens systems from galaxy to cluster scales, as well as their spectroscopic follow-up.…
The 21 cm signal from the Epoch of Reionization should be observed within the next decade. While a simple statistical detection is expected with SKA pathfinders, the SKA will hopefully produce a full 3D mapping of the signal. To extract…
The Square Kilometre Array Observatory (SKAO) is perhaps the most ambitious radio telescope envisaged yet. It will enable unprecedented studies of the Sun, the corona and the heliosphere and help to answer many of the outstanding questions…
Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly been developed and limited to be task-specific. We introduce…
New developments in data processing and visualization are being made in preparation for upcoming radioastronomical surveys planned with the Square Kilometre Array (SKA) and its precursors. A major goal is enabling extraction of science…
The Square Kilometre Array (SKA) will operate one of the world's largest continuous scientific data systems, sustaining petascale imaging under strict power envelopes. Current radio-interferometric pipelines typically achieve only 4-14% of…
In recent years cosmology has undergone a revolution, with precise measurements of the microwave background radiation, large galaxy redshift surveys, and the discovery of the recent accelerated expansion of the Universe using observations…
In this paper, we consider the problem of optimum multi-domain real-time beamforming and high-precision beam pattern positioning in application to very large wideband array antennas, particularly to the Square Kilometre Array (SKA) aperture…
We present a technique-led review of the progression of precise radio astrometry, from the first demonstrations, half a century ago, until to date and into the future. We cover the developments that have been fundamental to allow high…
The SKA will be a transformational instrument in the study of our local Universe. In particular, by virtue of its high sensitivity (both to point sources and diffuse low surface brightness emission), angular resolution and the frequency…
Low-frequency radio observations of neutral hydrogen during and before the epoch of cosmic reionization will provide hundreds of quasi-independent source planes, each of precisely known redshift, if a resolution of ~ 1 arcminutes or better…
Self-attention and transformer architectures have become foundational components in modern deep learning. Recent efforts have integrated transformer blocks into compact neural architectures for computer vision, giving rise to various…