Cambridge Centre for Research Associate in Machine Learning and Landscape Management (Fixed Term)
Department of Computer Science and Technology, West Cambridge
Applications are invited for a Research Associate position to work as part of the flagship Natural Environment Research Council (NERC) Centre for Landscape Regeneration (CLR).
https://www.clr.conservation.cam.ac.uk/
The successful candidate will be based in the Department of Computer Science and Technology and will join the research group of Prof Emily Shuckburgh, as well as being part of the Centre for Landscape Regeneration (CLR).
The Centre for Landscape Regeneration is an ambitious programme of research that aims to provide the knowledge and tools needed to regenerate the British countryside using cost-effective nature-based solutions that harness the power of ecosystems to provide broad societal benefits including biodiversity recovery and climate mitigation and adaptation. The focal landscapes for CLR are in the Fens (north of Cambridge), the Cairngorms National Park and the Lake District National Park. The Research Associate will work in partnership with colleagues from multiple departments within the University of Cambridge as well as a range of collaborating organisations.
The role holder will lead the research to develop machine learning based approaches to advance the core objectives of the project. The primary focus will be on identifying optimal land management solutions to delivering food production, nature conservation and greenhouse gas emissions reductions. This will involve deploying machine learning techniques to model a collection of objective functions (e.g. how the abundances of bird species are affected by agricultural yield). A statistical emulation approach will be used to infer optimal solutions and allow a wide range of scenarios to be explored to reveal trade-offs affecting decision-making. Data from remote and in situ sensor technologies will be utilised and the role holder will develop multi-fidelity approaches to synthesise different data sources. Comprehensive climate change risk assessments based on downscaled and bias-corrected climate simulations (also using machine learning) will be conducted for each landscape to assess resilience of landscape restoration solutions to climate change. The role holder could work in all three landscapes or could choose to focus on one.