Artificial intelligence techniques to speed up the realistic simulation and full waveform inversion of ground penetrating radar data.

Ground penetrating radars (GPR) are used in a many diverse applications. These range from near-surface geophysics investigations, concrete inspection, utility network detections, landmine detection and even planetary exploration using rovers on the Moon and Mars that utilise GPR technology. All these applications rely upon the same physical principles that govern the complex interplay of ultrawideband electromagnetic energy with diverse media.

Previous explorations and innovative research at Edinburgh have significantly shaped the development of gprMax, an advanced open-source GPR simulation package, furthering the advancement of algorithms essential for interpreting and visualising intricate GPR data. Recently, the creation of realistic synthetic GPR labelled data through a surrogate numerical model of a GPR transducer has led to a promising use of machine learning methodologies. By employing suitably trained algorithms, the machine learning approaches swiftly calculate simulated GPR responses, eliminating the dependency on direct resolution of the full 3D problem traditionally achieved through the application of the full wave 3D numerical model.

This exciting new research project will delve into the development and expansion of precise and efficient GPR simulation. Leveraging cutting-edge artificial intelligence technologies, we aim to innovate and improve generally applicable surrogate modelling to expedite full waveform inversion techniques. The overarching goal is to facilitate automated GPR processing, ushering in the ability to interpret GPR data in near-real-time.

You will work closely with the researchers that have created and continue to lead the development of gprMax and as the project evolves you will be expected to contribute to the codebase and further its advancement and capabilities.

Given the interdisciplinary nature of this research project, we do not anticipate that candidates will already have significant expertise in every pertinent field. You will be however expected to be able programme, preferably in Python, or be willing to develop such skills at an advanced level as the project has a strong computational focus. Concepts formulated during this research project will also need to undergo laboratory evaluations to confirm their validity.

The position will be closed as soon as a suitable candidate has been found

Further Information: 

The University of Edinburgh is committed to equality of opportunity for all its staff and students, and promotes a culture of inclusivity. Please see details here: https://www.ed.ac.uk/equality-diversity

Closing Date: 

Wednesday, January 31, 2024

Principal Supervisor: 

Assistant Supervisor: 

TBC

Eligibility: 

Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree. Further information on English language requirements for EU/Overseas applicants.

Funding: 

Tuition fees + stipend are available for Home/EU and International students

Informal Enquiries: