English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The volume of data being collected in solar physics has exponentiallyincreased over the past decade and with the introduction of the $\textit{DanielK. Inouye Solar Telescope}$ (DKIST) we will be entering the age of petabytesolar data. Automated feature detection will be an invaluable tool forpost-processing of solar images to create catalogues of data ready forresearchers to use. We propose a deep learning model to accomplish this; a deepconvolutional neural network is adept at feature extraction and processingimages quickly. We train our network using data from $\textit{Hinode/SolarOptical Telescope}$ (SOT) H$\alpha$ images of a small subset of solar featureswith different geometries: filaments, prominences, flare ribbons, sunspots andthe quiet Sun ($\textit{i.e.}$ the absence of any of the other four features).We achieve near perfect performance on classifying unseen images from SOT($\approx$99.9\%) in 4.66 seconds. We also for the first time explore transferlearning in a solar context. Transfer learning uses pre-trained deep neuralnetworks to help train new deep learning models $\textit{i.e.}$ it teaches anew model. We show that our network is robust to changes in resolution bydegrading images from SOT resolution ($\approx$0.33$^{\prime \prime}$ at$\lambda$=6563\AA{}) to $\textit{Solar Dynamics Observatory/Atmospheric ImagingAssembly}$ (SDO/AIA) resolution ($\approx$1.2$^{\prime \prime}$) without achange in performance of our network. However, we also observe where thenetwork fails to generalise to sunspots from SDO/AIA bands 1600/1700\AA{} dueto small-scale brightenings around the sunspots and prominences in SDO/AIA304\AA{} due to coronal emission.

Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics