Thomas Gernon is Associate Professor of Earth Science at the University of Southampton, based at the National Oceanography Centre. He gained his PhD in volcanology at the University of Bristol, focussing on multi-phase flows in volcanic environments. He is particularly interested in the application of machine learning to understand a wide range of geological phenomena (e.g., forecasting hazardous flows), and to inform regulation of manmade (induced) earthquakes associated with oil and gas operations. His pilot project with the Alan Turing Institute, with Dr Thea Hincks as Turing Researcher, uses Bayesian Networks to analyse the complex joint dependencies between operational and geological parameters and induced seismicity in hydraulic fracking and fluid injection regions. Partners include Energy Regulators and researchers in the UK, USA and Canada. The project will develop next generation geospatial data analysis tools to automatically identify changing susceptibility to induced earthquakes in space and time. His work has been published in leading journals including Science, PNAS, Nature Climate Change and Nature Geoscience.
Gernon’s research explores the complex interactions between geological processes operating on different spatial and temporal scales, and in different environments. Recent research has ranged from investigating the coupling between global tectonic and geochemical cycles deep in Earth history, to the regional controls on seismicity today. He applies a range of different techniques, including remote sensing, fieldwork, chemical analysis, analogue experiments, and modelling to address these problems.
He has recently been involved in developing advanced Bayesian networks to determine the interplay between operational and geological variables in triggering man-made earthquakes. He has also been involved in an exciting study that utilised NASA spacecraft data and applied approximate Bayesian computation methods to understand and interpret the impact cratering record of the Earth and Moon. In the spirit of the Turing Institute, he is keen to apply data science and artificial intelligence to tackle major scientific challenges—especially those at the interface between environment, energy, and the economy.