My research background is mostly in molecular and computational biology with a strong focus on artificial intelligence and genomics. Currently my research aims to build software tools to improve the efficiency at which bark, and ambrosia beetles are studied. As part of my PhD, I have three main projects to achieve this. 

The first of these is an artificial intelligence model built to identify bark beetle species based on their morphology. This model makes use of current state of the art computer vision techniques to speed up and standardize visual identification which is often a bottleneck in early detection of invasive species programs. A first prototype of our model can be found here.  

The second project is still in early development and aims to streamline the process of digesting scientific literature for research purposes. The process of working through literature and building up the required background for scientific innovation could take years for specialized fields such as bark and ambrosia beetle research. This large learning curve also limits the ability for other people to contribute effectively from other fields. The objective of this project is to automate the process of literature digestion by building a machine learning model capable of recommending essential literature and identifying gaps in the literature that could benefit from further investigation.

The third project is more molecular in nature and focusses on the genomic and transcriptomic analyses of mycangia-associated fungi in bark and ambrosia beetles. My role in this project is to perform the required genome assemblies and bioinformatic analyses to highlight which genes allow fungi to survive in the mycangia of beetles.

Even though these projects may seem unrelated at first glance, the overarching aim is to use the information generated in the literature model and the genomics study to enhance the bark and ambrosia beetle identification tool.