As a data scientist at BGS I collaborate with scientists across all challenge areas, and with external partners to QA and visualise data sets, produce machine learning models which can be used to predict and classify data, as well as provide uncertainty on the modelled results. I am particularly interested in producing “explainable” models which can help BGS scientists lead to new understanding.
Prior to joining BGS I worked in a start-up MedTech company, helping to develop diagnostic and predictive algorithms for those with suspected, or long-term respiratory conditions. I have also worked on developing turbulent inlet conditions for incompressible flow, to model thunderstorm downburst outflow, and developed experimental lab-based techniques for modelling downburst outflow.
Matthew Paice’s Biography
- 2021 – ongoing: Data Scientist, BGS
- 2020 – 2021: Data Scientist, TidalSense (formerly Cambridge Respiratory Innovations)
- 2016 – 2019: Data Analyst, TidalSense (formerly Cambridge Respiratory Innovations)
- 2014 – 2016: Postdoctoral Researcher (fluid dynamics), University of Strathclyde
- 2010 – 2014: PhD Civil Engineering (wind engineering), University of Birmingham
- 2009 – 2010: MSc Atmosphere, Ocean and Climate, University of Reading
- 2006 – 2009: BSc Physics, University of Bristol
- Environmental and geospatial data science
- Data engineering / data pipelines
- Time series analysis / modelling for environmental processes
- Machine and deep learning
ORCID: 0000-0002-8610-1448
NERC Open Research Archive: Dr Matthew Paice
Google Scholar profile: Dr Matthew Paice
Research Gate: Dr Matthew Paice
- Programming in Julia, C++, Python, MATLAB/ Octave, FORTRAN 90, VBA
- Geospatial analytics and programming (Python)
- Machine learning and deep learning
- Computational Fluid Dynamics modelling