Geological Modelling using Deep-learning Techniques

The School of Energy, Geoscience, Infrastructure and Society (EGIS) at Heriot-Watt University, UK is looking for an excellent PhD candidate to work on an industrially funded project titled "Geological model generation using deep-learning techniques". In this project, generative machine learning models (e.g. GANs among other techniques) will be adapted to generate geologically consistent subsurface models while accounting for model uncertainties. The project will build on our recent work on the topic [1, 2, 3] and aims to address the questions of learning using limited training data and handling spatial non-stationary geological models.

Essential skills:
• Master’s degree in machine-learning, computational mathematics, physics or in a relevant engineering discipline with strong computational skills.
• Programming skills preferably in Python and/or C++
• Ability to write reports, collate information and present it in a clear and engaging manner.
• Excellent communication skills

Desirable skills:
• Machine learning techniques (theory and applications)
• Computer assisted geological modelling (Object-based, surface-based modelling, etc.)
• Background in computational statistics (Spatial Geo-statistics, Bayesian techniques)
• Numerical optimization and nonlinear PDE solvers

You should complete an online application form and provide a detailed CV, a covering letter including areas of expertise and research interests, degree certificates and relevant transcripts, a verifiable list of programming skills and one academic reference. If you are an overseas applicant, you must also provide proof of your ability in the English language (if English is not your mother tongue or if you have not already studied for a degree that was taught in English). We require an IELTS certificate showing an overall score of at least 6.5 with no component scoring less than 6.0.