Machine Interpretation of Radar Displays

Cote, A. J.

doi:10.1007/978-1-4684-1716-6_37

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…E-mail: oliver.muller@astro.unistra.fr by confusion with background galaxies, foreground galactic cirrus, or instrumental noise (Chiboucas et al 2013;Merritt et al 2016;Müller et al 2018Müller et al , 2019Bennet et al 2019). A prime example is the galaxy Cen 8/KK 198, which has been regarded as dwarf galaxy associated with the Centaurus group for more than two decades (Cote 1996;Jerjen et al 2000;Karachentsev et al 2013;Müller et al 2017), until VLT observations have uncovered it as a low-surface brightness spiral galaxy (Müller et al 2019(Müller et al , 2021. Once high-resolution imaging was available to study the morphology of the galaxy in detail, the spiral pattern in the older imaging becomes quite apparent, in other words, this spiral galaxy could have been spotted as an interloper in the dwarf galaxy catalogs before the costly follow-up observations.…”

Section: Introductionmentioning

confidence: 99%

Dwarfs from the Dark (Energy Survey): a machine learning approach to classify dwarf galaxies from multi-band images

Müller¹,

Schnider²

2021

TheOJA

View full text Add to dashboard Cite

Countless low-surface brightness objects-including spiral galaxies, dwarf galaxies, and noise patterns-have been detected in recent large surveys. Classically, astronomers visually inspect those detections to distinguish between real low-surface brightness galaxies and artefacts. Employing the Dark Energy Survey (DES) and machine learning techniques, Tanoglidis et al. (2020) have shown how this task can be automatically performed by computers. Here, we build upon their pioneering work and further separate the detected low-surface brightness galaxies into spirals, dwarf ellipticals, and dwarf irregular galaxies. For this purpose we have manually classified 5567 detections from multi-band images from DES and searched for a neural network architecture capable of this task. Employing a hyperparameter search, we find a family of convolutional neural networks achieving similar results as with the manual classification, with an accuracy of 85% for spiral galaxies, 94% for dwarf ellipticals, and 52% for dwarf irregulars. For dwarf irregulars-due to their diversity in morphology-the task is difficult for humans and machines alike. Our simple architecture shows that machine learning can reduce the workload of astronomers studying large data sets by orders of magnitudes, as will be available in the near future with missions such as Euclid.

show abstract