TY - JOUR
T1 - Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps
AU - Mostert, Rafaël I.J.
AU - Duncan, Kenneth J.
AU - Röttgering, Huub J.A.
AU - Polsterer, Kai L.
AU - Best, Philip N.
AU - Brienza, Marisa
AU - Brüggen, Marcus
AU - Hardcastle, Martin J.
AU - Jurlin, Nika
AU - Mingo, Beatriz
AU - Morganti, Raffaella
AU - Shimwell, Tim
AU - Smith, Dan
AU - Williams, Wendy L.
N1 - Publisher Copyright:
© 2021 ESO.
PY - 2021/1/1
Y1 - 2021/1/1
N2 - Context. The Low Frequency Array (LOFAR) Two-metre Sky Survey (LoTSS) is a low-frequency radiocontinuum survey of the Northern sky at an unparalleled resolution and sensitivity. Aims. In order to fully exploit this huge dataset and those produced by the Square Kilometre Array in the next decade, automated methods in machine learning and data-mining will be increasingly essential both for morphological classifications and for identifying optical counterparts to the radio sources. Methods. Using self-organising maps (SOMs), a form of unsupervised machine learning, we created a dimensionality reduction of the radio morphologies for the ∼25k extended radio continuum sources in the LoTSS first data release, which is only ∼2 percent of the final LoTSS survey. We made use of PINK, a code which extends the SOM algorithm with rotation and flipping invariance, increasing its suitability and effectiveness for training on astronomical sources. Results. After training, the SOMs can be used for a wide range of science exploitation and we present an illustration of their potential by finding an arbitrary number of morphologically rare sources in our training data (424 square degrees) and subsequently in an area of the sky (∼5300 square degrees) outside the trainingdata. Objects found in this way span a wide range of morphological and physical categories: extended jets of radio active galactic nuclei, diffuse cluster haloes and relics, and nearby spiral galaxies. Finally, to enable accessible, interactive, and intuitive data exploration, we showcase the LOFAR-PyBDSF Visualisation Tool, which allows users to explore the LoTSS dataset through the trained SOMs.
AB - Context. The Low Frequency Array (LOFAR) Two-metre Sky Survey (LoTSS) is a low-frequency radiocontinuum survey of the Northern sky at an unparalleled resolution and sensitivity. Aims. In order to fully exploit this huge dataset and those produced by the Square Kilometre Array in the next decade, automated methods in machine learning and data-mining will be increasingly essential both for morphological classifications and for identifying optical counterparts to the radio sources. Methods. Using self-organising maps (SOMs), a form of unsupervised machine learning, we created a dimensionality reduction of the radio morphologies for the ∼25k extended radio continuum sources in the LoTSS first data release, which is only ∼2 percent of the final LoTSS survey. We made use of PINK, a code which extends the SOM algorithm with rotation and flipping invariance, increasing its suitability and effectiveness for training on astronomical sources. Results. After training, the SOMs can be used for a wide range of science exploitation and we present an illustration of their potential by finding an arbitrary number of morphologically rare sources in our training data (424 square degrees) and subsequently in an area of the sky (∼5300 square degrees) outside the trainingdata. Objects found in this way span a wide range of morphological and physical categories: extended jets of radio active galactic nuclei, diffuse cluster haloes and relics, and nearby spiral galaxies. Finally, to enable accessible, interactive, and intuitive data exploration, we showcase the LOFAR-PyBDSF Visualisation Tool, which allows users to explore the LoTSS dataset through the trained SOMs.
KW - Galaxies: active
KW - Galaxies: peculiar
KW - Methods: data analysis
KW - Methods: statistical
KW - Radio continuum: galaxies
KW - Techniques: image processing
UR - http://www.scopus.com/inward/record.url?scp=85099882184&partnerID=8YFLogxK
U2 - 10.1051/0004-6361/202038500
DO - 10.1051/0004-6361/202038500
M3 - Article
AN - SCOPUS:85099882184
SN - 0004-6361
VL - 645
JO - Astronomy and Astrophysics
JF - Astronomy and Astrophysics
M1 - A89
ER -