Postgraduate research project

Understanding ionospheric dynamics with machine learning

Funding
Competition funded View fees and funding
Type of degree
Doctor of Philosophy
Entry requirements
2:1 honours degree View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date

About the project

The Earth’s magnetosphere-ionosphere (M-I) system is driven by its interaction with the solar wind through a coupling process called “reconnection”. You will use machine learning techniques to probe an extensive dataset of ionospheric dynamics to elucidate how the solar wind conditions control the size and rate of the coupling process.

Understanding the M-I system is important, as it provides the scientific basis of space weather (the harmful influence of our plasma environment on space- and ground-based technology). Ionospheric radar observations of reconnection are uniquely capable of inferring the global extent, and hence global rate, of the process that drives the magnetosphere. They therefore hold the key to understanding how the M-I system responds to solar wind driving. However, there are some key unknowns – in particular, fundamental dependencies such as how the upstream conditions control the spatial extent of the interaction process or the “size” of individual reconnection bursts.

Our recent work opens up an exciting opportunity to probe these questions. However, this requires large-scale statistical studies, and the challenge is one of data volume. This challenge can be addressed with data science techniques.

This project will develop automated algorithms to identify reconnection events in ionospheric radar data, which will allow transformative statistical studies into the nature of M-I driving. From a machine learning perspective, this task is challenging as it requires finding subtle spatial-temporal patterns involving many different scales in a noisy background. Over the last decade Deep Learning has made a step change in its ability to recognise such patterns.

We will develop and train Deep Learning techniques on existing radar data, validate the resulting algorithms and apply them to analyse the radar data statistically in order to determine the response of the M-I system to different modes of variability in the solar wind driving conditions.