Nowcasting the IRF Auroral Index with Recurrent Neural Networks

Sammanfattning: There is a long history in Kiruna of conducting research on the physics of the aurora borealis. There is also a long history of providing tourists with great opportunities to see the auroras. Planning such tourist activities can be challenging since the auroras are hard to predict. Reliable forecasts would be a valuable tool for researchers as well as for tourists and tour guides. One tool that is already available for both researchers and tourists is the all-sky camera in Kiruna, which is operated by the Swedish Institute of Space Physics (IRF). There has been a digital all-sky camera in operation in Kiruna for over 20 years. From the images captured by this camera, the IRF has developed a numerical index - the auroral index.  Forecasting time series with neural network algorithms is a well studies subject. There are many examples from a wide range of felds, including space weather. A type of neural network that has often been successfully used for time series forecasting is the Recurrent Neural Network (RNN), and more specifcally the Long short-term memory (LSTM).  This thesis evaluates the auroral index - in combination with data from the solar wind - as training data for recurrent neural networks. Furthermore, it attempts to fnd a LSTM neural network model capable of making reliable forecasts of the auroral index. The Keras and TensorFlow software libraries are used to build and train the neural network model. Some challenges with the auroral index - when utilized as training data for neural networks - are identifed. The produced LSTM neural network models are not accurate enough for deployment as a production level service. Further development might improve on this. Finally, this thesis suggests future work that may contribute to better forecasting models for auroras in the Kiruna region.