Eliminating artefacts in polarimetric images using deep learning
Artikel i vetenskaplig tidskrift, 2020

Polarization measurements done using Imaging Polarimeters such as the Robotic Polarimeter are very sensitive to the presence of artefacts in images. Artefacts can range from internal reflections in a telescope to satellite trails that could contaminate an area of interest in the image. With the advent of wide-field polarimetry surveys, it is imperative to develop methods that automatically flag artefacts in images. In this paper, we implement a Convolutional Neural Network to identify the most dominant artefacts in the images. We find that our model can successfully classify sources with 98 per cent true positive and 97 per cent true negative rates. Such models, combined with transfer learning, will give us a running start in artefact elimination for near-future surveys like WALOP.

image classication

artefect detection

Statistics - Machine Learning

polarmetry

Computer Science - Machine Learning

deep learning

Astrophysics - Instrumentation and Methods for Astrophysics

Författare

Dhruv Paranjpye

California Institute of Technology (Caltech)

et al.

Georgia Panopoulou

California Institute of Technology (Caltech)

Monthly Notices of the Royal Astronomical Society

0035-8711 (ISSN) 1365-2966 (eISSN)

Ämneskategorier

Astronomi, astrofysik och kosmologi

Datavetenskap (datalogi)

DOI

10.1093/mnras/stz3250

Mer information

Senast uppdaterat

2023-11-03