About this role
The above full-time post is available immediately until 13 November 2026, in the Land, Environment, Economics and Policy (LEEP) Institute at the University of Exeter Business School. The LEEP Institute is a highly interdisciplinary centre bringing together natural, physical, economic, and social scientists to develop and apply data driven solutions to the major environmental, economic and wellbeing challenges facing humanity.
The LEEP institute is a thriving research centre with over 50 members and maintains partnerships with leading researchers and institutes worldwide. It contributes to leading research in environmental resource management, integrated environment-economy modelling, environmental valuation, biodiversity economics, natural capital accounting, sustainability and related decision making.
Main purpose of the job:
The LEEP team invite applications from candidates with strong programming, statistical modelling, data analysis and data visualisation skills to support the work of the LEEP Data Science and AI team (Professor Daniel Williamson, Professor Brett Day, Dr Amy Binner)
The successful applicant will work across a variety of research projects that focus on environmental decision-making affecting land use in Great Britain to provide a range of market and non-market goods and services including food production, greenhouse gas storage, biodiversity gains, water quality improvements, flood risk reduction and recreation benefits. Examples of these projects are:
NetZeroPlus (https://netzeroplus.ac.uk/), which aims to demonstrate the greenhouse gas removal potential of new woodlands in the UK; Contract Research Projects to investigate land use change, funded by government and third sector funders, for example Defra, Natural England, Forestry England.
About you
Applicants will possess a relevant PhD or equivalent qualification/experience in Statistics, Machine learning, AI or in a field of study involving complex statistical/machine learning modelling. The successful applicant will possess sufficient specialist knowledge in the discipline to develop methodology for research publication. The successful applicant will also be able to work collaboratively, supervise the work of others and act as team leader if required. Applicants will be able to communicate mathematics/statistics/machine learning effectively, with specialists and non-specialists alike. They will be able to design and implement (in R or Python) new statistical models and inferential algorithms at appropriate spatio-temporal scales to meet project needs and the needs of decision makers.
The successful applicant will:
Gain experience building surrogate models that underpin our decision support systems and analysis. Use emulators to accelerate and improve model calibration for models such as crop growth, tree growth, soil carbon emissions, livestock management, policy uptake, water quality and biodiversity, using both in situ observations and remote sensing Learn how to build and manage containerised software using docker. Ensure uncertainty from their modelling can be readily and effectively visualised.
Further information
For further information please see the full advert and job description on our website.