Photo of Mr Charlie Kirkwood

Mr Charlie Kirkwood

Postgraduate Researcher


Telephone: 01392 726403

Extension: (Streatham) 6403

I'm a scientist with a keen interest in statistical methods and computational technology. I believe that statistical modelling, machine learning, and artificial intelligence (concepts with significant overlap) will become increasingly important in the future as technology progresses. Already these tools are allowing us to better understand the world we live in and the systems we interact with, meaning better decisions can be made - and these abilities will only improve. Within this progression is a tension between top-down and bottom-up design - should we instill our beliefs about the world into our decision making tools, or allow these tools to decipher the complexities of the world for themselves, with the potential to learn beyond what we thought we knew?

I'm currently a postgraduate researcher on an EPSRC and Met Office CASE funded PhD studentship entitled 'Using cutting edge statistical and data science techniques to optimise and improve weather forecasts' - the project aims to develop a hybrid approach between top-down numerical weather prediction models and bottom-up statistical learning to generate more accurate probabilistic weather forecasts.

Prior to starting this PhD, I originally graduated with a masters degree in Exploration and Resource Geology from Cardiff University and started out working in the mineral exploration industry, where geostatistical methods form the basis of (good) decision making. I then moved into a NERC funded research position at the British Geological Survey where I developed more advanced statistical and machine learning methods for geological mapping (see publications, and website). From there I took a job as a commercial data scientist at Walgreens Boots Alliance (parent company of Boots on the UK high street), where I developed machine learning methods to improve targeting of offers to loyalty card customers, and a natural language processing system for prioritising response to customer feedback.

Grants and Awards:

2018 - Exeter University Researcher-Led Initiative grant, awarded the maximum amount on offer to organise my proposed training course 'How to share your code: an introduction to the Git ecosystem for early career researchers'

2018 - WBA Global Brands 'Makers' award, for advancing data science at Boots UK. I had developed a system for item and customer embeddings which more than tripled the incremental sales generated by new product launch advertisements by making personalisation significantly more precise.

2017 - Elsevier Outstanding Reviewer award in recognition of contributions made to the quality of the Journal of Geochemical Exploration.

2016 - NVIDIA GPU grant, awarded a Titan X Pascal GPU to accelerate my research into how neural networks could be used for geological mapping and mineral exploration (for example see poster here).