Ashutosh K. Mishra, Emma Tolley, Shreyam Parth Krishna, Jean-Paul Kneib
Nov 23, 2024·astro-ph.GA·PDF Detecting diffuse radio emission, such as from halos, in galaxy clusters is crucial for understanding large-scale structure formation in the universe. Traditional methods, which rely on X-ray and Sunyaev-Zeldovich (SZ) cluster pre-selection, introduce biases that limit our understanding of the full population of diffuse radio sources. In this work, we provide a possible resolution for this astrophysical tension by developing a machine learning (ML) framework capable of unbiased detection of diffuse emission, using a limited real dataset like those from the Murchison Widefield Array (MWA). We generate for the first time radio halo images using Wasserstein Generative Adversarial Networks (WGANs) and Denoising Diffusion Probabilistic Models (DDPMs), and apply them to train a neural network classifier independent of pre-selection methods. The halo images generated by DDPMs are of higher quality than those produced by WGANs. The diffusion-supported classifier with a multi-head attention block achieved the best average validation accuracy of 95.93% over 10 runs, using 36 clusters for training and 10 for testing, without further hyperparameter tuning. Using our classifier, we rediscovered 9/12 halos (75% detection rate) from the MeerKAT Galaxy Cluster Legacy Survey (MGCLS) Catalogue, and 5/8 halos (63% detection rate) from the Planck Sunyaev-Zeldovich Catalogue 2 (PSZ2) within the GaLactic and Extragalactic All-sky MWA (GLEAM) survey. In addition, we identify 11 potential new halos, minihalos, or candidates in the COSMOS field using XMM-chandra-detected clusters in GLEAM data. This work demonstrates the potential of ML for unbiased detection of diffuse emission and provides labeled datasets for further study.
Michel Morales, Emma Tolley, Remi Poitevineau
Jan 22, 2026·astro-ph.IM·PDF Reconstructing images of the radio sky from incomplete Fourier information is a key challenge in radio astronomy. In this work, we present a method for radio interferometric image reconstruction using a data-driven prior for the radio sky based on denoising diffusion probabilistic models (DDPMs). We train a DDPM on radio galaxy observations from the VLA FIRST survey, then create simulated VLA, EHT, and ALMA observations of radio galaxies. We use an unsupervised posterior sampling method called Denoising Diffusion Restoration Models (DDRM) to reconstruct the corresponding images using our DDPM as a prior. Our approach is agnostic to the measured radio interferometric data and naturally incorporates the physics of the measurement process. We are able to reconstruct images with very high fidelity and demonstrate a marked improvement over image reconstruction techniques that work on gridded visibilities like CLEAN.
Emma Tolley, Simon Frasch, Etienne Orliac, Shreyam Krishna, Michele Bianco, Sepand Kashani, Paul Hurley, Matthieu Simeoni, Jean-Paul Kneib
Oct 13, 2023·astro-ph.IM·PDF The Bluebild algorithm is a new technique for image synthesis in radio astronomy which decomposes the sky into distinct energy levels using functional principal component analysis. These levels can be linearly combined to construct a least-squares estimate of the radio sky, i.e. minimizing the residuals between measured and predicted visibilities. This approach is particularly useful for deconvolution-free imaging or for scientific applications that need to filter specific energy levels. We present an HPC implementation of the Bluebild algorithm for radio-interferometric imaging: Bluebild Imaging++ (BIPP). The library features interfaces to C++, C and Python and is designed with seamless GPU acceleration in mind. We evaluate the accuracy and performance of BIPP on simulated observations of the upcoming Square Kilometer Array Observatory and real data from the Low-Frequency Array (LOFAR) telescope. We find that BIPP offers accurate wide-field imaging and has competitive execution time with respect to the interferometric imaging libraries CASA and WSClean for images with $\leq 10^6$ pixels. Furthermore, due to the energy level decomposition, images produced with BIPP can reveal information about faint and diffuse structures before any cleaning iterations. BIPP does not perform any regularization, but we suggest methods to integrate the output of BIPP with CLEAN. The source code of BIPP is publicly released.
Thomas Brunet, Emma Tolley, Stefano Corda, Roman Ilic, P. Chris Broekema, Jean-Paul Kneib
Oct 18, 2023·astro-ph.IM·PDF We explore applications of quantum computing for radio interferometry and astronomy using recent developments in quantum image processing. We evaluate the suitability of different quantum image representations using a toy quantum computing image reconstruction pipeline, and compare its performance to the classical computing counterpart. For identifying and locating bright radio sources, quantum computing can offer an exponential speedup over classical algorithms, even when accounting for data encoding cost and repeated circuit evaluations. We also propose a novel variational quantum computing algorithm for self-calibration of interferometer visibilities, and discuss future developments and research that would be necessary to make quantum computing for radio astronomy a reality.
Emma Tolley, Damien Korber, Aymeric Galan, Austin Peel, Mark T. Sargent, Jean-Paul Kneib, Frederic Courbin, Jean-Luc Starck
Apr 20, 2022·astro-ph.IM·PDF Future deep HI surveys will be essential for understanding the nature of galaxies and the content of the Universe. However, the large volume of these data will require distributed and automated processing techniques. We introduce LiSA, a set of python modules for the denoising, detection and characterization of HI sources in 3D spectral data. LiSA was developed and tested on the Square Kilometer Array Science Data Challenge 2 dataset, and contains modules and pipelines for easy domain decomposition and parallel execution. LiSA contains algorithms for 2D-1D wavelet denoising using the starlet transform and flexible source finding using null-hypothesis testing. These algorithms are lightweight and portable, needing only a few user-defined parameters reflecting the resolution of the data. LiSA also includes two convolutional neural networks developed to analyse data cubes which separate HI sources from artifacts and predict the HI source properties. All of these components are designed to be as modular as possible, allowing users to mix and match different components to create their ideal pipeline. We demonstrate the performance of the different components of LiSA on the SDC2 dataset, which is able to find 95% of HI sources with SNR > 3 and accurately predict their properties.
Emma Tolley
Classifying the morphologies of radio galaxies is important to understand their physical properties and evolutionary histories. A galaxy's morphology is often determined by visual inspection, but as survey size increases robust automated techniques will be needed. Deep neural networks are an attractive method for automated classification, but have many free parameters and therefore require extensive training data and are subject to overfitting and generalization issues. We explore hybrid classification methods using the scattering transform, the recursive wavelet decomposition of an input image. We analyse the performance of the scattering transform for the Fanaroff-Riley classification of radio galaxies with respect to CNNs and other machine learning algorithms. We test the robustness of the different classification methods with training data truncation and noise injection, and find that the scattering transform can offer competitive performance with the most accurate CNNs.
Rémi Potevineau, Emma Tolley, Verlon Etsebeth
Jan 12, 2026·astro-ph.GA·PDF We present a masked guided approach for a denoising diffusion probabilistic model (DDPM) trained to generate and inpaint realistic radio galaxy images. We train the DDPM using the FIRST radio galaxy catalog, the Radio Galaxies Zoo and cutouts of the MGCLS catalog. We compared different statistical distributions to make sure that our unconditional approach produces morphologically realistic galaxies, offering a data-driven method to supplement existing radio datasets and support the development of machine learning applications in radio astronomy.
A. Tajja, A. Aghabiglou, E. Tolley, J-P. Kneib, J-P. Thiran, Y. Wiaux
Recently, the R2D2 paradigm, standing for ''Residual-to-Residual DNN series for high-Dynamic-range imaging'', was introduced for image formation in Radio Interferometry (RI) as a learned version of the traditional algorithm CLEAN. The first incarnations of R2D2 are limited to planar imaging on small fields of view, failing to meet the spherical-imaging requirement of modern telescopes observing wide fields. To address this limitation, we propose the spherical-imaging extension S-R2D2. Firstly, as R2D2, S-R2D2 encapsulates its minor cycles in existing 2D-Euclidean deep neural network (DNN) architectures, but adapts its iterative scheme to incorporate the wide-field measurement model mapping a spherical image to visibility data. We implemented this model as the composition of an efficient Fourier-based interpolator mapping the spherical image onto the equatorial plane, with the standard RI operator mapping the equatorial-plane image to visibility data. Importantly, the interpolation step must inevitably be performed at a lower-than-optimal resolution on the plane, to meet the high-resolution requirement on the sphere of wide-field imaging while preserving scalability. Therefore, secondly, we design S-R2D2's DNN training loss to jointly learn to correct the interpolation approximations and identify residual image structures on the sphere, ensuring consistency with the spherical ground truth using the adjoint plane-to-sphere interpolator. Finally, we demonstrate through simulations S-R2D2's capability to perform fast and accurate reconstructions of spherical monochromatic intensity images, across high-resolution, high-dynamic-range settings.
Damien Korber, Michele Bianco, Emma Tolley, Jean-Paul Kneib
Aug 29, 2022·astro-ph.CO·PDF With the advent of the Square Kilometre Array Observatory (SKAO), scientists will be able to directly observe the Epoch of Reionization by mapping the distribution of neutral hydrogen at different redshifts. While physically motivated results can be simulated with radiative transfer codes, these simulations are computationally expensive and can not readily produce the required scale and resolution simultaneously. Here we introduce the Physics-Informed neural Network for reIONization (PINION), which can accurately and swiftly predict the complete 4-D hydrogen fraction evolution from the smoothed gas and mass density fields from pre-computed N-body simulation. We trained PINION on the C$^2$-Ray simulation outputs and a physics constraint on the reionization chemistry equation is enforced. With only five redshift snapshots and a propagation mask as a simplistic approximation of the ionizing photon mean free path, PINION can accurately predict the entire reionization history between $z=6$ and $12$. We evaluate the accuracy of our predictions by analysing the dimensionless power spectra and morphology statistics estimations against C$^2$-Ray results. We show that while the network's predictions are in good agreement with simulation to redshift $z>7$, the network's accuracy suffers for $z<7$ primarily due to the oversimplified propagation mask. We motivate how PINION performance can be drastically improved and potentially generalized to large-scale simulations.
Verlon Etsebeth, Michelle Lochner, Konstantinos Kolokythas, Kenda Knowles, Emma Tolley
Feb 17, 2026·astro-ph.IM·PDF Diffuse radio emission in galaxy clusters, such as radio halos, relics, and mini halos, is a key tracer of non-thermal processes, turbulence, and magnetic fields within the intra-cluster medium. However, their low surface brightness, as well as contamination from compact sources and imaging artefacts, makes their detection challenging. The sheer volume of data from instruments such as the Square Kilometre Array will render traditional manual-inspection based detection methods infeasible. This paper introduces a novel machine learning approach that uses active learning to rapidly identify diffuse emission candidates from a small, optimally-selected subset of data. We apply the self-supervised deep learning algorithm Bootstrap Your Own Latent to extract features from source cutouts in the MeerKAT Galaxy Cluster Legacy Survey (MGCLS). We then pass these features through the Astronomaly: Protege anomaly detection framework to identify the final candidates. Using a human-labelled set, we evaluate our pipeline on high-resolution (~7''), convolved (15''), and combined-feature MGCLS datasets. Interestingly, the high-resolution features identify diffuse sources more efficiently than the convolved resolution, which are in turn outperformed by the combined features. Of the top 100 sources ranked by Protege, 99% exhibit diffuse characteristics, with 55% confirmed as cluster-related emission. Our work shows that Protege can identify diffuse emission with minimal human labelling effort, offering a powerful, scalable tool capable of detecting both known and novel diffuse radio sources.
Ashutosh Kumar Mishra, Emma Tolley
Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for solving differential equations by integrating physical laws into the learning process. This work leverages PINNs to simulate gravitational collapse, a critical phenomenon in astrophysics and cosmology. We introduce the Schrödinger-Poisson informed neural network (SPINN) which solve nonlinear Schrödinger-Poisson (SP) equations to simulate the gravitational collapse of Fuzzy Dark Matter (FDM) in both 1D and 3D settings. Results demonstrate accurate predictions of key metrics such as mass conservation, density profiles, and structure suppression, validating against known analytical or numerical benchmarks. This work highlights the potential of PINNs for efficient, possibly scalable modeling of FDM and other astrophysical systems, overcoming the challenges faced by traditional numerical solvers due to the non-linearity of the involved equations and the necessity to resolve multi-scale phenomena especially resolving the fine wave features of FDM on cosmological scales.
Nicolas Cerardi, Emma Tolley, Ashutosh Mishra
Dec 12, 2025·astro-ph.CO·PDF Cold dark matter (CDM) evolves as a collisionless fluid under the Vlasov-Poisson equations, but N-body simulations approximate this evolution by discretising the distribution function into particles, introducing discreteness effects at small scales. We present a physics-informed neural network approach that evolves CDM fields without any use of N-body data or methods, using a Kolmogorov-Arnold network (KAN) to model the continuous displacement field for one-dimensional halo collapse. Physical constraints derived from the Vlasov-Poisson equations are embedded directly into the loss function, enabling accurate evolution beyond the first shell crossing. The trained model achieves sub-percent errors on the residuals even after seven shell crossings and matches N-body results while providing a resolution-free representation of the displacement field. In addition, displacement errors do not grow over time, a very interesting feature with respect to N-body methods. It can also reconstruct initial conditions through backward evolution when sufficient final-state information is available. Although current runtimes exceed those of N-body methods, this framework offers a new route to high-fidelity CDM evolution without particle discretisation, with prospects for extension to higher dimensions.
Stefano Corda, Bram Veenboer, Emma Tolley
Efficient use of energy is essential for today's supercomputing systems, as energy cost is generally a major component of their operational cost. Research into "green computing" is needed to reduce the environmental impact of running these systems. As such, several scientific communities are evaluating the trade-off between time-to-solution and energy-to-solution. While the runtime of an application is typically easy to measure, power consumption is not. Therefore, we present the Power Measurement Toolkit (PMT), a high-level software library capable of collecting power consumption measurements on various hardware. The library provides a standard interface to easily measure the energy use of devices such as CPUs and GPUs in critical application sections.
Michele Bianco, Sambit. K. Giri, David Prelogović, Tianyue Chen, Florent G. Mertens, Emma Tolley, Andrei Mesinger, Jean-Paul Kneib
The upcoming Square Kilometre Array Observatory (SKAO) will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as noise and galactic foreground contamination which pose a challenge for accurate detection. In this study, we present the SegU-Net v2 framework, an enhanced version of our convolutional neural network, built to identify neutral and ionized regions in the 21-cm signal contaminated with foreground emission. We trained our neural network on 21-cm image data processed by a foreground removal method based on Principal Component Analysis achieving an average classification accuracy of 71 per cent between redshift $z=7$ to $11$. We tested SegU-Net v2 against various foreground removal methods, including Gaussian Process Regression, Polynomial Fitting, and Foreground-Wedge Removal. Results show comparable performance, highlighting SegU-Net v2's independence on these pre-processing methods. Statistical analysis shows that a perfect classification score with $AUC=95\%$ is possible for $8<z<10$. While the network prediction lacks the ability to correctly identify ionized regions at higher redshift and differentiate well the few remaining neutral regions at lower redshift due to low contrast between 21-cm signal, noise and foreground residual in images. Moreover, as the photon sources driving reionization are expected to be located inside ionised regions, we show that SegU-Net v2 can be used to correctly identify and measure the volume of isolated bubbles with $V_{\rm ion}>(10\, {\rm cMpc})^3$ at $z>9$, for follow-up studies with infrared/optical telescopes to detect these sources.
Antonio Boveia, Linda M. Carpenter, Boyu Gao, Taylor Murphy, Emma Tolley
We present DarkFlux, a software tool designed to analyze indirect-detection signatures for next-generation models of dark matter (DM) with multiple annihilation channels. Version 1.0 of this tool accepts user-generated models with $2\to 2$ tree-level dark matter annihilation to pairs of Standard Model (SM) particles and analyzes DM annihilation to $γ$ rays. The tool consists of three modules -- the annihilation fraction module, the flux module, and the analysis module -- which can be run in a loop in order to scan over DM mass if desired. [A description of each module is available in the full abstract.] DarkFlux v1.0 compares the total $γ$-ray flux to a joint-likelihood analysis of fifteen dwarf spheroidal galaxies (dSphs) analyzed by the $Fermi$-LAT collaboration. DarkFlux automatically provides data tables and can plot the output of the three modules. In this manual, we briefly motivate this indirect-detection computer tool and review the essential DM physics. We then describe the several modules of DarkFlux in greater detail. Finally, we show how to install and run DarkFlux and provide two worked examples demonstrating its capabilities.
Andreas Albert, Mihailo Backovic, Antonio Boveia, Oliver Buchmueller, Giorgio Busoni, Albert De Roeck, Caterina Doglioni, Tristan DuPree, Malcolm Fairbairn, Marie-Helene Genest, Stefania Gori, Giuliano Gustavino, Kristian Hahn, Ulrich Haisch, Philip C. Harris, Dan Hayden, Valerio Ippolito, Isabelle John, Felix Kahlhoefer, Suchita Kulkarni, Greg Landsberg, Steven Lowette, Kentarou Mawatari, Antonio Riotto, William Shepherd, Tim M. P. Tait, Emma Tolley, Patrick Tunney, Bryan Zaldivar, Markus Zinser
Weakly-coupled TeV-scale particles may mediate the interactions between normal matter and dark matter. If so, the LHC would produce dark matter through these mediators, leading to the familiar "mono-X" search signatures, but the mediators would also produce signals without missing momentum via the same vertices involved in their production. This document from the LHC Dark Matter Working Group suggests how to compare searches for these two types of signals in case of vector and axial-vector mediators, based on a workshop that took place on September 19/20, 2016 and subsequent discussions. These suggestions include how to extend the spin-1 mediated simplified models already in widespread use to include lepton couplings. This document also provides analytic calculations of the relic density in the simplified models and reports an issue that arose when ATLAS and CMS first began to use preliminary numerical calculations of the dark matter relic density in these models.
Devin Crichton, Moumita Aich, Adam Amara, Kevin Bandura, Bruce A. Bassett, Carlos Bengaly, Pascale Berner, Shruti Bhatporia, Martin Bucher, Tzu-Ching Chang, H. Cynthia Chiang, Jean-Francois Cliche, Carolyn Crichton, Romeel Dave, Dirk I. L. de Villiers, Matt A. Dobbs, Aaron M. Ewall-Wice, Scott Eyono, Christopher Finlay, Sindhu Gaddam, Ken Ganga, Kevin G. Gayley, Kit Gerodias, Tim Gibbon, Austin Gumba, Neeraj Gupta, Maile Harris, Heiko Heilgendorf, Matt Hilton, Adam D. Hincks, Pascal Hitz, Mona Jalilvand, Roufurd Julie, Zahra Kader, Joseph Kania, Dionysios Karagiannis, Aris Karastergiou, Kabelo Kesebonye, Piyanat Kittiwisit, Jean-Paul Kneib, Kenda Knowles, Emily R. Kuhn, Martin Kunz, Roy Maartens, Vincent MacKay, Stuart MacPherson, Christian Monstein, Kavilan Moodley, V. Mugundhan, Warren Naidoo, Arun Naidu, Laura B. Newburgh, Viraj Nistane, Amanda Di Nitto, Deniz Ölçek, Xinyu Pan, Sourabh Paul, Jeffrey B. Peterson, Elizabeth Pieters, Carla Pieterse, Aritha Pillay, Anna R. Polish, Liantsoa Randrianjanahary, Alexandre Refregier, Andre Renard, Edwin Retana-Montenegro, Ian H. Rout, Cyndie Russeeawon, Alireza Vafaei Sadr, Benjamin R. B. Saliwanchik, Ajith Sampath, Pranav Sanghavi, Mario G. Santos, Onkabetse Sengate, J. Richard Shaw, Jonathan L. Sievers, Oleg M. Smirnov, Kendrick M. Smith, Ulrich Armel Mbou Sob, Raghunathan Srianand, Pieter Stronkhorst, Dhaneshwar D. Sunder, Simon Tartakovsky, Russ Taylor, Peter Timbie, Emma E. Tolley, Junaid Townsend, Will Tyndall, Cornelius Ungerer, Jacques van Dyk, Gary van Vuuren, Keith Vanderlinde, Thierry Viant, Anthony Walters, Jingying Wang, Amanda Weltman, Patrick Woudt, Dallas Wulf, Anatoly Zavyalov, Zheng Zhang
Sep 28, 2021·astro-ph.IM·PDF The Hydrogen Intensity and Real-time Analysis eXperiment (HIRAX) is a radio interferometer array currently in development, with an initial 256-element array to be deployed at the South African Radio Astronomy Observatory (SARAO) Square Kilometer Array (SKA) site in South Africa. Each of the 6m, $f/0.23$ dishes will be instrumented with dual-polarisation feeds operating over a frequency range of 400-800 MHz. Through intensity mapping of the 21 cm emission line of neutral hydrogen, HIRAX will provide a cosmological survey of the distribution of large-scale structure over the redshift range of $0.775 < z < 2.55$ over $\sim$15,000 square degrees of the southern sky. The statistical power of such a survey is sufficient to produce $\sim$7 percent constraints on the dark energy equation of state parameter when combined with measurements from the Planck satellite. Additionally, HIRAX will provide a highly competitive platform for radio transient and HI absorber science while enabling a multitude of cross-correlation studies. In this paper, we describe the science goals of the experiment, overview of the design and status of the sub-components of the telescope system, and describe the expected performance of the initial 256-element array as well as the planned future expansion to the final, 1024-element array.