Lightweight HI source finding for next generation radio surveys

Tolley, E.; Korber, Damien; Galan, A.; Peel, Austin; Sargent, M.; Kneib, J.-P.; Courbin, F.; Starck, Jean-Luc

doi:10.1016/j.ascom.2022.100631

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The EPFL team used a variety of techniques developed specifically for the Challenge and which have been collected into the LiSA library (Tolley et al 2022 ) publicly available on GITHUB . 4 The pipeline (Fig.…”

Section: Epfl E Tolley D Korber a Peel A Galan M Sargent G Fourestey ...mentioning

confidence: 99%

SKA Science Data Challenge 2: analysis and results

Hartley

Braun

et al. 2023

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

The Square Kilometre Array Observatory (SKAO) will explore the radio sky to new depths in order to conduct transformational science. SKAO data products made available to astronomers will be correspondingly large and complex, requiring the application of advanced analysis techniques to extract key science findings. To this end, SKAO is conducting a series of Science Data Challenges, each designed to familiarise the scientific community with SKAO data and to drive the development of new analysis techniques. We present the results from Science Data Challenge 2 (SDC2), which invited participants to find and characterise 233245 neutral hydrogen (H i) sources in a simulated data product representing a 2000 h SKA-Mid spectral line observation from redshifts 0.25 to 0.5. Through the generous support of eight international supercomputing facilities, participants were able to undertake the Challenge using dedicated computational resources. Alongside the main challenge, ‘reproducibility awards’ were made in recognition of those pipelines which demonstrated Open Science best practice. The Challenge saw over 100 participants develop a range of new and existing techniques, with results that highlight the strengths of multidisciplinary and collaborative effort. The winning strategy – which combined predictions from two independent machine learning techniques to yield a 20 per cent improvement in overall performance – underscores one of the main Challenge outcomes: that of method complementarity. It is likely that the combination of methods in a so-called ensemble approach will be key to exploiting very large astronomical datasets.

show abstract

Section: Epfl E Tolley D Korber a Peel A Galan M Sargent G Fourestey ...mentioning

confidence: 99%

SKA Science Data Challenge 2: analysis and results

Hartley

Braun

et al. 2023

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

show abstract

“…In the coming decade, the next generation of radio telescope arrays, such as the Square Kilometre Array (SKA; Dewdney et al 2009), are anticipated to be completed. The study of neutral hydrogen is one of the primary scientific goals of these telescopes, and H I galaxy surveys are key observations of them (Tolley et al 2022). From the H I galaxy survey data, we can examine the H I content and mass function of the galaxies, gas accretion, the correlation between H I and star formation, and the influence of the environment on H I (Giovanelli & Haynes 2015).…”

Section: Introductionmentioning

confidence: 99%

Detecting H i Galaxies with Deep Neural Networks in the Presence of Radio Frequency Interference

Liang

Deng

Yang

et al. 2023

Res. Astron. Astrophys.

View full text Add to dashboard Cite

In neutral hydrogen (HI) galaxy survey, a significant challenge is to identify and extract the HI galaxy signal from observational data contaminated by radio frequency interference (RFI). For a drift-scan survey, or more generally a survey of a spatially continuous region, in the time-ordered spectral data, the HI galaxies and RFI all appear as regions which extends an area in the time-frequency waterfall plot, so the extraction of the HI galaxies and RFI from such data can be regarded as an image segmentation problem, and machine learning methods can be applied to solve such problems. In this study, we develop a method to effectively detect and extract signals of HI galaxies based on a Mask R-CNN network combined with the PointRend method. By simulating FAST-observed galaxy signals and potential RFI impacts, we created a realistic data set for the training and testing of our neural network. We compared five different architectures and selected the best-performing one. This architecture successfully performs instance segmentation of HI galaxy signals in the RFI-contaminated time-ordered data (TOD), achieving a precision of 98.64\% and a recall of 93.59\%.

show abstract

“…Convolutional neural networks (CNNs) are supervised deep learning algorithms which reduce input data into a set of features for classification or other analysis. While various studies have established the ability of CNNs in recognizing galaxy morphologies [1], identifying galaxy-scale strong gravitational lenses [2], or as source finders [3], these networks often suffer from generalizability and interoperability problems [4]. The networks must be trained on a dataset with sufficient statistics, often with thousands of instances of the different features or classes that the network must learn.…”

mentioning

confidence: 99%

Scattering Transform for Analysing Galactic Morphology

Tolley

2023

Proceedings of the XXXVth URSI General Assembly and Scientific Symposium – GASS 2023

View full text Add to dashboard Cite

Lightweight HI source finding for next generation radio surveys

Cited by 3 publications

References 26 publications

SKA Science Data Challenge 2: analysis and results

SKA Science Data Challenge 2: analysis and results

Detecting H i Galaxies with Deep Neural Networks in the Presence of Radio Frequency Interference

Scattering Transform for Analysing Galactic Morphology

Contact Info

Product

Resources

About