2 postdoc positions in weather prediction, seasonal climate prediction, and artificial intelligence/machine learning
Applications are invited for two Postdoctoral Research Assistants in the field of weather prediction, seasonal climate prediction and artificial intelligence/machine learning.
Two posts are available from October 1st 2023. The first is available for 30 months, the second for 24 months (subject to funding).
These positions will be part of a UN World Food Programme project funded by Google, to improve rainfall forecasts on timescales of days to seasons in East Africa, using state-of-the-art global Numerical Weather Prediction ensembles supplemented by a Generative Adversarial Network (GAN - trained on local observational data) to downscale and calibrate the ensembles. The successful candidates will work with the Intergovernmental Authority on Development’s Climate Prediction and Applications Centre (ICPAC) in Kenya to improve the prediction of heavy rains and drought in East Africa. If successful it is possible that further funding will become available at the end of the project.
Working with project scientists in Kenya, the successful candidates will
• Continue to develop an existing GAN trained on satellite proxy observations of rainfall and drought using ensemble forecast data from the European Centre for Medium-Range Weather Forecasts (ECMWF).
• Apply the GAN to downscale ECMWF forecast information on the medium range and seasonal timescales, to postcode scale.
• Assess the skill of the downscaled forecast information. Where possible, compare with the skill of limited area model ensembles.
• Work directly with project scientists in ICPAC Kenya, and collaborate where needed with scientists at ECMWF.
• Help set up an operational high-resolution forecast activity for East Africa.
• Be aware of developments in AI and assess whether the GAN model continues to be state of the art.
• Write up results for scientific journals and present results in international meetings. Manage own academic research and administrative activities.
• Help develop a generic AI-based protocol for downscaling operational global forecasts that could be used by national meteorological services around the world.
Applicants should hold a PhD, or be close to completion in physics or a related field and should have a strong background in meteorology, computer science and machine learning.
Previous experience in working with ensembles will be an advantage.
Candidates should demonstrate
• Sufficient specialist knowledge in the discipline to work within established research programmes
• Ability to manage own academic research and associated activities
• Previous experience of contributing to publications/presentations
• Ability to contribute ideas for new research projects and research income generation
• Excellent communication skills, including the ability to write for publication, present research proposals and results, and represent the research group at meetings
Desirables:
• Experience of independently managing a discrete area of a research project
• Experience of actively collaborating in the development of research articles for publication
Application deadline: midday (UK time) 25 August 2023. Interviews will take place on September 15th.
Please direct enquiries about the role to Antje.Weisheimer@physics.ox.ac.uk and Tim.Palmer@physics.ox.ac.uk.