Solar Flare Predictions (SA)
Initial position
Solar flares are intense bursts of radiation which can disrupt the power grids of a continent, shut down the GPS system or irradiate people exposed in space. Developing systems for predicting solar flares would allow us to precisely aim our observation instruments at upcoming events, and eventually allow countermeasures to be taken in time against worst-case scenarios.
Objective
The Institute for Data Science (I4DS) curated a machine learning dataset and benchmark for the prediction of solar flares. The benchmark includes an implementation of a simple baseline algorithm (e.g. Zero-rule). In this project, you will create and train better
machine learning models which make use of this dataset.
Problem statement
A single sample of this dataset consists of images of multiple wavelengths over four time steps. If you use of all the available data, your model’s input is an image cube, consisting of four wavelengths, plus some metadata. The model output would be a single scalar prediction, the maximum emission to be expected in the following 24 hours.
