Dr Donald Cummins
- Position: Software Development Scientist with Machine Learning Specialisation
- Areas of expertise: statistical climatology; turbulence parametrizations; machine learning
- Email: D.Cummins@leeds.ac.uk
- Website: GitHub | Googlescholar | ORCID
Profile
I joined the Centre for Environmental Modelling and Computation (CEMAC) in February 2024 as a Software Development Scientist with Machine Learning Specialisation. My role at CEMAC will be to bridge the domains of Machine Learning (ML) and environmental science in the School of Earth and Environment. Topics I will be working on include weather forecasting, climate modelling, crop modelling, seismic data processing and satellite imagery analysis.
My academic background is originally in mathematics. During my MMath at the University of St Andrews, I developed a keen interest in probability and statistics, which subsequently led to me to pursue a PhD at the University of Exeter. My PhD project critically examined the theoretical underpinnings of optimal fingerprinting, a widely used statistical methodology for detection and attribution of climate change trends. After completing the PhD, I was invited to stay on at Exeter as a Postdoctoral Research Fellow on two projects: the first looking at storm severity indices as predictors of insured loss from extratropical cyclones; the second at scaling of extreme precipitation with temperature over Europe in a warming climate. In 2022, I began a postdoc at the Centre National de Recherches Météorologiques (CNRM) in Toulouse, France. There I used ML to develop performant boundary-layer turbulence parametrizations over sea ice in the Arctic.
<h4>Research projects</h4> <p>Any research projects I'm currently working on will be listed below. Our list of all <a href="https://environment.leeds.ac.uk/dir/research-projects">research projects</a> allows you to view and search the full list of projects in the faculty.</p>Qualifications
- PhD, Mathematics, University of Exeter
- MMath, Mathematics, University of St Andrews