We classify all sky images from 4 seasons, transform the classified information into time-series data to include information about the evolution of images and combine these with information on the onset of geomagnetic substorms. We train a lightweight classifier on this dataset to predict the onset of substorms within a 15 minute interval after being shown information of 30 minutes of aurora.

In the accompanying publication we describe our methods and show the results that we obtained.

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/SOP/