Machine Learning for Geophysical Hazard Sequences


Machine Learning for Geophysical Hazard Sequences


Project Description


Dr Jessica Johnson (School of Environmental Sciences, University of East Anglia) contact me

Dr Ben Milner (School of Computing Sciences, University of East Anglia)

Dr Jason Lines (School of Computing Sciences, University of East Anglia)

Dr Zoë Mildon (School of Geography, Earth and Environmental Sciences, University of Plymouth)

Project Background

Geophysical hazards, such as volcanic eruptions, large earthquakes and landslides, threaten millions of people around the world. Many of these hazards are unpredictable, but there are often precursors that may be used to forecast damaging events. These precursors could be in the form of monitoring observations such as seismicity, deformation and gas emissions (1), or from data processed after the event has occurred, recognised in hindsight (2).

In typical hazard forecasting, observations of pre-cursors are studied and researchers use their prior knowledge to estimate the probability of an event occurring (3). However Machine Learning (ML) tools are increasingly being applied to geosciences and hazard monitoring due to ML’s strength in identifying patterns (4,5). If patterns can be identified in hindsight, then they could be used as a precursor to forecast future events.

This project will use precursor sequences with ML techniques to investigate the relationship between datasets, answering questions like:

  • Which data are the most important for forecasting?
  • What is the minimum monitoring network required?
  • Which data would be needed to decrease uncertainty?
  • How does ML compare to expert elicitation?

The candidate will use geophysical, geological and geochemical data relating to specific geophysical hazards in New Zealand. Data will be obtained from online sources, published literature, and expert accounts. The candidate will train state-of-the-art time series classification algorithms on the precursor data, and devise performance measures for predictions. ML results will be quantitatively compared to existing methodologies using expert elicitation.


Training will be given in geoscientific methods, machine learning techniques, and geophysical hazard processes (including earthquakes, volcanoes and landslides). The candidate will spend time in New Zealand, learning about the hazards and datasets.

Person Specification

Applicants must hold, or expect to receive, a degree in a relevant geoscience, computing or physical sciences discipline. The candidate should be numerically literate and experience of using unix based operating systems and/or Python is desirable but not essential.


  • 1. Johnson, J. H., Prejean, S., Savage, M. K., & Townend, J. (2010). Anisotropy, repeating earthquakes, and seismicity associated with the 2008 eruption of Okmok volcano, Alaska. Journal of Geophysical Research: Solid Earth, 115(B9).
  • 2. Keats, B. S., Johnson, J. H., & Savage, M. K. (2011). The Erua earthquake cluster and seismic anisotropy in the Ruapehu region, New Zealand. Geophysical research letters, 38(16).
  • 3. Bebbington, M. S., Stirling, M. W., Cronin, S., Wang, T., & Jolly, G. (2018). National-level long-term eruption forecasts by expert elicitation. Bulletin of Volcanology, 80(6), 56.
  • 4. Dempsey, D. E., Cronin, S. J., Mei, S., & Kempa-Liehr, A. W. (2020). Automatic precursor recognition and real-time forecasting of sudden explosive volcanic eruptions at Whakaari, New Zealand. Nature Communications, 11(1), 1-8.
  • 5. Oastler, G., & Lines, J. (2019). A Significantly Faster Elastic-Ensemble for Time-Series Classification. In International Conference on Intelligent Data Engineering and Automated Learning (pp. 446-453). Springer, Cham.

Key Information

  • This project has been shortlisted for funding by the ARIES NERC DTP and will start on 1st October 2021. The closing date for applications is 23:59 on 12th January 2021.
  • Successful candidates who meet UKRI’s eligibility criteria will be awarded a NERC studentship, which covers fees, stipend (£15,285 p.a. for 2020-21) and research funding. For the first time in 2021/22 international applicants (EU and non-EU) will be eligible for fully-funded UKRI studentships. Please note ARIES funding does not cover visa costs (including immigration health surcharge) or other additional costs associated with relocation to the UK.
  • ARIES students benefit from bespoke graduate training and ARIES provides £2,500 to every student for access to external training, travel and conferences. Excellent applicants from quantitative disciplines with limited experience in environmental sciences may be considered for an additional 3-month stipend to take advanced-level courses in the subject area.
  • ARIES is committed to equality, diversity, widening participation and inclusion in all areas of its operation. We encourage enquiries and applications from all sections of the community regardless of gender, ethnicity, disability, age, sexual orientation and transgender status. Academic qualifications are considered alongside significant relevant non-academic experience.
  • All ARIES studentships may be undertaken on a part-time or full-time basis, visa requirements notwithstanding
  • For further information, please contact the supervisor. To apply for this Studentship click on the “Apply now” link below.

Get in Touch /