Radio sources segmentation and classification with deep learning

Lao, Baoqiang; Jaiswal, Sumit; Zhao, Zixu; Lin, L.; Wang, Jing; Sun, Xiaohui; Qin, Sheng-Li

doi:10.1016/j.ascom.2023.100728

Cited by 3 publications

(4 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FIRST-14dec17 catalog records the components of radio galaxies, and the association and classification of these components in radio galaxies need to be done either manually or automatically during the post-processing step (Banfield et al 2015;Slijepcevic et al 2022;Lou et al 2023). We utilize HeTu (Lao et al 2021(Lao et al , 2023, a deep learning-based radio source-detector, to automatically locate and classify extended radio galaxies within the FIRST images based on their morphology. The latest version of HeTu (HeTu-v2; Lao et al 2023) has the capability to classify extended radio galaxies into four categories: FR-I, FR-II, HT and Core-Jet (CJ).…”

Section: Search Strategymentioning

confidence: 99%

“…We utilize HeTu (Lao et al 2021(Lao et al , 2023, a deep learning-based radio source-detector, to automatically locate and classify extended radio galaxies within the FIRST images based on their morphology. The latest version of HeTu (HeTu-v2; Lao et al 2023) has the capability to classify extended radio galaxies into four categories: FR-I, FR-II, HT and Core-Jet (CJ). In this morphological classification scheme, we have redefined the morphology of FR-II galaxies.…”

Section: Search Strategymentioning

confidence: 99%

“…Among them, 45,241 FR-IIs have been chosen for inclusion in this study. These galaxies have undergone a thorough evaluation and have been shown to have a high level of reliability with an average accuracy of 93% (Lao et al 2023). This paper investigates the further physical properties of the selected FR-IIs to build the definitive catalog (called FRIIRGCat).…”

Section: Search Strategymentioning

confidence: 99%

See 2 more Smart Citations

A Machine Learning Made Catalog of FR-II Radio Galaxies from the FIRST Survey

Lao,

Yang,

Jaiswal

et al. 2024

Res. Astron. Astrophys.

Self Cite

View full text Add to dashboard Cite

We present an independent catalog (FRIIRGcat) of 45,241 Fanaroff-Riley Type II (FR-II) radio galaxies compiled from the VLA FIRST Survey (Very Large Array Faint Images of the Radio Sky at Twenty-centimeter) and employed the deep learning method. Among them, optical and/or infrared counterparts are identified for 41,425 FR-IIs. This catalog spans luminosities $2.63\times10^{22}\leq L_{\rm rad}\leq6.76\times10^{29}\,{\rm W}\,{\rm Hz}^{-1}$ and redshifts up to $z=5.01$. The spectroscopic classification indicates that there are 1,431 low-excitation radio galaxies (LERGs) and 260 high-excitation radio galaxies (HERGs). Among the spectroscopically identified sources, black hole masses are estimated for 4,837 FR-IIs, which are in $10^{7.5}\lesssim M_{\rm BH}\lesssim 10^{9.5}$\,$M_{\odot}$. Interestingly, this catalog reveals a couple of giant radio galaxies (GRGs), those of which are already in the existing GRG catalog confirming the efficiency of this FR-II catalog. Furthermore, 284 new GRGs are unveiled in this new FR-II sample, they have the largest projected sizes ranging from 701 to 1,209\,kpc and are located at redshifts $0.31<z<2.42$. Finally, we explore the distribution of the jet position angle and it shows that the FIRST images are significantly affected by the systematic effect (the observing beams). The method presented in this work is expected to be applicable to the currently conducting radio sky surveys because they have finely refined telescope arrays. On the other hand, we are expecting that further new methods will be dedicated to solving this problem.

show abstract

Section: Search Strategymentioning

confidence: 99%

Section: Search Strategymentioning

confidence: 99%

Section: Search Strategymentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning Made Catalog of FR-II Radio Galaxies from the FIRST Survey

Lao,

Yang,

Jaiswal

et al. 2024

Res. Astron. Astrophys.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In supervised learning, the model undergoes training using image-label pairs, where these labels provide complete information required for the model to make specific predictions. Recently, machine learning (ML) techniques, as exemplified by studies, such as Lukic et al (2018), Alger et al (2018), Wu et al (2019), Bowles et al (2020), Maslej-Krešňáková et al (2021), Becker et al (2021), Brand et al (2023), Riggi et al (2023), Sortino et al (2023), Lao et al (2023), and Gupta et al (2024), have found application in the morphological classification and detection of radio galaxies.…”

Section: Introductionmentioning

confidence: 99%

RG-CAT: Detection pipeline and catalogue of radio galaxies in the EMU pilot survey

Gupta,

Norris,

Hayder

et al. 2024

Publ. Astron. Soc. Aust.

View full text Add to dashboard Cite

We present source detection and catalogue construction pipelines to build the first catalogue of radio galaxies from the 270 deg2 pilot survey of the Evolutionary Map of the Universe (EMU-PS) conducted with the Australian Square Kilometre Array Pathfinder (ASKAP) telescope. The detection pipeline uses Gal-DINO computer-vision networks (Gupta et al., 2024) to predict the categories of radio morphology and bounding boxes for radio sources, as well as their potential infrared host positions. The Gal-DINO network is trained and evaluated on approximately 5,000 visually inspected radio galaxies and their infrared hosts, encompassing both compact and extended radio morphologies.We find that the Intersection over Union (IoU) for the predicted and ground truth bounding boxes is larger than 0.5 for 99% of the radio sources, and 98% of predicted host positions are within 3″ of the ground truth infrared host in the evaluation set. The catalogue construction pipeline uses the predictions of the trained network on the radio and infrared image cutouts based on the catalogue of radio components identified using the Selavy source finder algorithm. Confidence scores of the predictions are then used to prioritize Selavy components with higher scores and incorporate them first into the catalogue. This results in identifications for a total of 211,625 radio sources, with 201,211 classified as compact and unresolved. The remaining 10,414 are categorized as extended radio morphologies, including 582 FR-I, 5,602 FR-II, 1,494 FR-x (uncertain whether FR-I or FR-II), 2,375 R (single-peak resolved) radio galaxies, and 361 with peculiar and other rare morphologies. Each source in the catalogue includes a confidence score.We cross-match the radio sources in the catalogue with the infrared and optical catalogues, finding infrared cross-matches for 73% and photometric redshifts for 36% of the radio galaxies. The EMU-PS catalogue and the detection pipelines presented here will be used towards constructing catalogues for the main EMU survey covering the full southern sky.

show abstract