About the Project
Although the current rate of reversals is about 2-3 times per million years, the last global reversal took place some 780,000 years ago, meaning that planet Earth is now well “overdue” a reversal. True or not, it is certainly the case that change is afoot: a patch of weak field in the south Atlantic (the south Atlantic anomaly) is spreading; the global field (expressed by the dipole strength) is weakening at a rate of 5% per century; and very recent measurements over the last few decades have shown that the magnetic North Pole has begun a sprint away from its historical position over northern Canada towards Siberia. Does this indicate that a period of significant change for the global field is upon us?
Predicting the magnetic field is challenging, not the least because we do not yet have a complete representation that describes how the magnetic field changes. Although the basic physics is understood, the complexities and extreme conditions within the Earth’s core make it computationally difficult to model. The novel aspect of this project is to apply recent advances in Machine Learning or Deep Learning to the prediction of Earth’s magnetic field. The key idea behind the project is that a trained neural network may be able to spot patterns in the data that have so far either not been noticed or have been too complex to interpret; such networks may be able to supply accurate short-time forecasts of the internally generated magnetic field. One of the goals of the project is to assess the evidence for whether the geomagnetic field is likely to reverse and how fast it might do so.
Working with scientists at the British Geological Survey (BGS) in Edinburgh and DTU Space in Copenhagen, the project will begin with the investigation of the predictability of the magnetic field using a simple recurrent neural network. The project should appeal to those with geophysics, physics or a mathematical background interested in understanding the Earth’s mysterious magnetic field. As part of the project there is the opportunity to spend up to three months working with the BGS in Edinburgh and to visit DTU in Copenhagen. This project has an extra £7,000 (in addition to the usual research budget) to cover travel, accommodation and living expenses for this purpose.
- Begin the investigation of the predictability of the magnetic field using a simple recurrent neural network such as an “echo state” neural network, which has been shown to model and predict complex dynamical systems with surprising accuracy.
- Considering the observations now as a movie with many hundreds of frames, we will apply techniques based on learning algorithms, such as auto-encoders or other manifold learning and representation learning methods (such as Variational AutoEncoder or Generative Adversarial Networks) that can be used to guess the next few frames in the sequence and doing so predict the future structure.
- Is the present state-of-the-art in numerical models of the geomagnetic field consistent with the real observations? This can be assessed by training a neural network on the output of a numerical simulation of Earth’s magnetic field: for example, the coupled Earth model of Aubert et al., 2013 or the database of simulated magnetic reversals at Leeds.
The project will be based primarily at Leeds. There are project partners in both Edinburgh and Copenhagen who the student will visit to see how geomagnetism has an impact on everyday life from smartphone navigation to space weather impacts on the power grid. There will also be opportunities to attend international conferences (UK, Europe, US and elsewhere), and other possible collaborative visits within Europe.
We seek a highly motivated candidate with a strong background in mathematics, physics, computation, geophysics or another highly numerate discipline. Knowledge of geomagnetism is not required.
Why not add a message here
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.