Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties
This addresses the need for error and uncertainty estimation in scientific domains like solar physics, where visual quality alone is insufficient, representing an incremental improvement over existing super-resolution methods.
The paper tackled the problem of super-resolution for scientific images, specifically solar magnetograms, by proposing a Bayesian framework to generate multiple high-resolution explanations and quantify uncertainties, achieving maps that measure the range of compatible high-resolution outputs.
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.