Recent advances in algorithms and computing power have produced new methods which, for some problems, can outperform human expertise in data analysis, image processing and pattern recognition. These techniques have been used to examine and analyse features in single and multiple images, as well as video footage. These machine learning approaches are beginning to revolutionise many areas including astronomy, medicine and machine vision. However, they require careful use. At the moment there are issues in the reproducibility and reliability of many of these applications, with calls from leading groups for a more physical understanding and Physics-like model approach to using these techniques.
This project aims to apply some of these new techniques to rapidly and accurately examine experimental data generated by the Semiconductor and Spectroscopy (SSD) Group in Strathclyde. We use nanoscale scanning electron probe and microscopy measurements of semiconductor nano-structures, particularly GaN and related materials. These are now extensively used for solid state lighting and lasers, having had massive impacts on world wide energy use (partly recognised by the 2014 Nobel Prize in Physics). But in order to expand their use into areas like high power electronics and ultra-violet light sources requires robust wide area microscopy and analysis of data. Its here that machine learning methods can have a substantial impact, if used carefully.
For details contact Dr Ben Hourahine or Dr Paul Edwards.
Updated May 2018