Where and when
Genoa, Italy – June 9th, 2022
speaker: Shane Maloney
affiliation: Dublin Institute for Advanced Studies
date: June 9th 2022, 3pm (Italian time)
venue: Genoa (Italy), Polo Valletta Puggia – Università di Genova: DIBRIS-DIMA and Google Meet
Leaving Deep learning to produce physically-motivated super-resolved and cross-calibrated solar magnetograms
abstract: Super-resolution techniques aim to increase the resolution of images by recovering detail. Compared to upsampling techniques reliant on interpolation, deep learning-based approaches learn features and their relationships across the training data set to leverage prior knowledge on what low resolution patterns look like in higher resolution images. As an added benefit, deep neural networks can learn the systematic properties of the target images (i.e. texture), combining super-resolution with instrument cross-calibration. While the successful use of super-resolution algorithms for natural images is rooted in creating perceptually convincing results, super-resolution applied to scientific data requires careful quantitative evaluation of performances. Deep learning can increase the resolution and calibrate space- and ground-based imagers from to different instrumental generations. The performance of scientific applications of deep learning-based super-resolution and calibration was benchmarked.