Data Scientist – Food Security and Climate Change

This is an excellent opportunity to join a growing team applying statistical and data science approaches to address current challenges in agricultural and food systems research, this post will contribute to a multi-institute project funded through the “AI for Science and Government” programme at the Alan Turing Institute (ATI) and involving partners at Cambridge University, Exeter University, the John Innes Centre and the Alan Turing Institute.  The focus of the project is on improving our understanding of the impact of climate change on agriculture, though the application of a range of data science approaches (including AI and machine learning approaches, statistical methods and mathematical modelling) to analyse and reconcile highly disparate data sets, such as climate records, crop development and yield data, phenotype images and transcriptome data, with the aim of better integrating models and data to predict the holistic impact of climate change on cropping systems.

This post will contribute to the project through two distinct components: (1) an exploration of Rothamsted long-term datasets to look for hidden interactions between factors influencing wheat yield, extending previous research at Rothamsted on the separation of agronomic and environmental (weather) influences on crop yield over time, which identified the influence of weather and climate variation on yield variability, and highlighted the importance of including weather temporal variation when evaluating the impacts of climate change on crops.  You will use ML and other approaches to investigate a wider range of direct and indirect interactions involving a wider range of environmental factors, in particular disease pressure, with the objective of developing a more accurate predictive model for the factors influencing yield that can be implemented in a forecasting tool; (2) an exploration of the linkages between crop performance and disease models, building on work completed as part of our strategic ASSIST collaborative programme with UKCEH to integrate multiple models with different temporal/spatial framework for modelling ecosystem services, and collaborating with the other partners in this project to develop new approaches to construct a framework for a more integrated approach to whole agricultural system modelling of crop performance.

You will need to have a strong background in statistics, applied mathematics or similarly quantitative sciences, computer programming skills in Python or R, and experience in multivariate statistical methods and machine learning methods.  Familiarity with mathematical or statistical models of crop and/or disease development would be a significant advantage, ideally based on several years of experience working in a research setting, preferably in agriculture or at least the life sciences.  As well as collaborating with the postdocs at our partner institutions, you will need to engage with members of our statistics group, our crop modelling community, and the broader Data Science Research Group at Rothamsted Research.