We show that transfer learning can be easily applied to all sky images for the purpose of classifying images, filtering images and predicting magnetic disturbance from auroral images. In the accompanying publication we describe our methods and show the results that we obtained. Version 1 of the dataset corresponds to the preprint, Version 2 to the peer reviewed version of the article.

This dataset contains the processed files that can be used to replicate our results. Instructions how to apply the data and on the accompanying code can be found here: http://tid.uio.no/TAME/