Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties
Machine Learning
2019-11-06 v1 Solar and Stellar Astrophysics
Image and Video Processing
Machine Learning
Abstract
Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimations of errors and uncertainties are crucial. To address this issue we propose a Bayesian framework that decomposes uncertainties into epistemic and aleatoric uncertainties. We test the validity of our approach by super-resolving images of the Sun's magnetic field and by generating maps measuring the range of possible high resolution explanations compatible with a given low resolution magnetogram.
Keywords
Cite
@article{arxiv.1911.01486,
title = {Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties},
author = {Xavier Gitiaux and Shane A. Maloney and Anna Jungbluth and Carl Shneider and Paul J. Wright and Atılım Güneş Baydin and Michel Deudon and Yarin Gal and Alfredo Kalaitzis and Andrés Muñoz-Jaramillo},
journal= {arXiv preprint arXiv:1911.01486},
year = {2019}
}