Automated 3D Data Analysis using Artificial Intelligence - (studied by Distance Learning)

The oil & gas sector and health sector has massive data sets in the form of seismic data and the health sector in MRI data that it needs to analyse in order to identify the location of hydrocarbons and also to assess the risk for drilling operations in a particular area, or to diagnose underlying health conditions.

Integrating recently developed technology in the form of 3D visualisation tools (developed at the University of Aberdeen) with optimisation techniques would result in an integrated and interactive tool that would massively speed up the understanding of the huge amounts of 3D data in the form of geophys data or MRI data that companies hold. The software tool would allow an analyst to review the results of analysis in real-time by manipulating the 3D environment using intuitive hand gestures.

The software would therefore be in the form of a fully interactive 3D analysis tool that would automatically identify features of interest. The use of the 3D engine would allow commodity hardware such as HTC Vive or other 3D viewers to be used, which would greatly enhance the user experience. For seismic data analysis, this will be similar to current analysis tools, with the main difference being that the analysis will be truly in 3D rather than 2D slices like other currently available tools.
In essence, the project would look at developing new technologies in the areas of:
• Optimising and analysing data in 3D (not 2D slices)
• A modern 3D volume visualizer capable of real-time animation and interaction.
• Integration into commodity VR such as HTC Vive or any other 3D hardware.

The aims of this project are to fine tune existing automated methods based on image and signal processing to recognize, track, visualize and manipulate specific geobodies or MRI objects using and transferring alternative optimisation methods and visualisation technologies originally developed through the DynamO project at the University of Aberdeen which has been optimised for the real time visualisation and simulation of 3D data, originally for Chemical Engineering problems. The methods will rely on novel data-visualisation techniques by borrowing techniques from the game industry and protein industry to render large data-sets interactively and in real-time. These techniques can be used to reveal hidden relationships between data-sets as well as providing visually pleasing renderings of simulations. We will also explore different automated data optimisation methods to perform a better and more complete pattern of classification, based on work undertaken at the University of Aberdeen in a number of fields.

Candidates should have (or expect to achieve) a UK honours degree at 2.1 or above (or equivalent) in Engineering, Physics, Computing Science, Geosciences, Bioinformatics with an essential background in computer coding, algorithms, mathematics, data analysis.

APPLICATION PROCEDURE:

• Apply for Degree of Doctor of Philosophy in Engineering
• State name of the lead supervisor as the Name of Proposed Supervisor
• State ‘Self-funded’ as Intended Source of Funding
• State the exact project title on the application form

When applying please ensure all required documents are attached:

• All degree certificates and transcripts (Undergraduate AND Postgraduate MSc-officially translated into English where necessary)
• Detailed CV

Informal inquiries can be made to Dr A Starkey ([Email Address Removed]), with a copy of your curriculum vitae and cover letter. All general enquiries should be directed to the Postgraduate Research School ([Email Address Removed].

It is possible to undertake this project at a distance. Interested parties should contact Dr Starkey to discuss this.