SWAG合集

The project aims to develop, test, and refine, soil health metrics that offer actionable insights for sustainable land management. By integrating long-term monitoring with AI-driven approaches, this research looks to deliver scalable, data-driven solutions for assessing and improving soil health in agriculture.

This cross-industry study, based at SWAG合集 and NIAB, aims to advance the evaluation of soil health benchmarks using diverse, large-scale datasets and cutting-edge analytical techniques. The research will leverage NIAB’s and other industry long-term experiments and soil datasets, alongside SWAG合集’s national LandIS soil datasets, and BGS data, to develop a comprehensive understanding of soil health and how is measured across various arable agricultural systems and scales. Such metrics should account for productivity and hyper local environmental risk priorities (field level), advancing us from current regional or climate driven benchmarks.

The student will work closely with NIAB’s Soils and Farming Systems team, using these datasets (e.g. Fig 1) to assess existing soil health metrics and identify areas for targeted improvement. Where necessary, additional data will be collected to fill gaps and strengthen the analysis. Building on NIAB’s current AI-driven work in agriculture and Cranfield’s Environmental Informatics, the student will apply advanced methods such as machine learning, predictive modeling, and remote sensing to maximise the potential of these datasets.
 
Figure 1: Soil electrical conductivity and grid cell yield stability (standardised yield) across available years yield data for on-farm. Images show NIAB, Morley Experimental Station, Norfolk SWAG合集. Credit, D.Clarke

Methodology:
The project will use an integrated approach, including evaluating existing and emerging key properties and indicators in arable cropping systems to identify benchmarks for soil health. Determine a soil health indicator framework based on available data and expert knowledge. Review data available at different scales (national, farm and field) to apply within the framework to determine ranges in benchmark indicators. Use machine learning approaches to develop actionable assessments of soil health in case study areas. Finally, evaluate model outcomes using multiple approaches (statistics, expert evaluation).

Partners and collaboration:
This is a CASE project in collaboration with NIAB, the SWAG合集’s fastest growing crop science organisation, together with the British Geological Survey (BGS). Renowned internationally, these partners deliver evidence and scientific services to support sustainable agriculture and geoscience. The supervisory team will include Professor Stephen Hallett, SWAG合集 with strong academic background in environmental data science and impacts of future climate on land systems and Professor Jaqueline Hannam, Professor of Pedology at SWAG合集, together with Dr Elizabeth Stockdale (NIAB) and Dr Ben Marchant (BGS). 

Possible timeline:
This PhD project is expected to take 3.5 years to complete. The first year will be spent on literature review, data collection, and developing the research methods. The second year will be spent on data collection, collation and analysis, ML model development and testing, and investigating underlying factors. The third year will be spent on testing the models, analyse interlinked factors that collectively contribute to soil health and writing the thesis.