Higher Degree by Research Application Portal

The project deals with the development of workflows enabling the inversion of large gravity and/or magnetic datasets (scalar or tensor data) using geological information at spatial scales or resolutions that remain challenging with the current approaches. This may be achieved by quantifying and preserving signal content to maximize the value of information of the data. One of the goals is for the proposed methodologies to achieve higher resolutions while reducing the size of the inverted datasets, for single domain or joint inversion. This is to be carried out through the development and use of: 

- implicit neural representation of the data and/or models (a form of neural network allowing multiscale, memory-efficient and differentiable geological models) or other neural networks.

- data reduction approaches (maintaining information content with fewer samples using e.g. ergodic sampling, compressive sensing);

Geological constraints to inversion are crucial in many scenarios, however data selection and scaling for both geophysical and geological data are usually treated independently. Methods will also be developed to ensure efficient sampling of the constraining geological data, consistently with the geophysical and petrophysical data used for inversion. 

It is expected that the methods will be tested for both property and geometrical inversion, with the possibility of comparing traditional inversion techniques with neural networks. 

Application cases may be carried out in collaboration with project partners: CSIRO and GSWA. Besides validation of the methods, the objective of the field applications will be to address some longstanding geological questions through the inversion of: 

- Data at regional and continental scales in Australia and/or Antarctica to infer the information about the structure and thermal state of the crust;

- Smaller scale, dense, high-resolution data collected from critical metal deposits in Western Australia to gain insights into their mineral system.

Please apply through for a Research and Training Program scholarship on the UWA website. $5000 top up per year will be provided for three years.

jeremie.giraud@uwa.edu.au

Willingness to learn and to take on challenging tasks.
Knowledge of geophysics, python coding, geology, signal processing and statistics, artificial intelligence.

This project is organised in the context of a collaboration between the MinEx CRC consortium and an ARC Industry Fellowship. Travelling to conference is expected. 

The Doctor of Philosophy (PhD) is a program of independent, supervised research that is assessed solely on the basis of a thesis, sometimes including a creative work component, that is examined externally. The work presented for a PhD must be a substantial and original contribution to scholarship, demonstrating mastery of the subject of interest as well as an advance in that field of knowledge. 

Visit the course webpage for full details of this course including admission requirements, course rules and the relevant CRICOS code/s.