Crop Care

Our Research

Using technology to care for crops involves deployment of novel sensing systems, data collection, and real time data analysis to help understand the micro-environment of individual plants within a crop. Precision agriculture requires applied data. Our robotic, machine learning, AI, and vision or sensing based solutions allow targeted selection or intervention, to support the grower or the farmer in caring for crops.

Research Projects

An assessment of the viability of inter row cultivations for weed control in commercial narrow row crops in the UK

This project aims to explore how effective inter-row cultivation is in reducing long-term weed populations; whether they can be used to support the use of herbicides, and how the application of this machinery can be maximised within the principles of conservation agriculture.

Project Lead: Dr Shaun Coutts

Funder: Chadacre Agricultural Trust and Felix Thornley Cobbold Agricultural Trust

Hyper-NUE (EO4AgroClimate): Using hyperspectral imaging to estimate NUE in wheat

This project lays the foundations for next generation remote sensing of crops to determine nitrogen use efficiency (NUE) and associated canopy photosynthetic potential. We will develop a high-throughput novel hyperspectral (HS) analysis technique that directly extracts biological meaningful data from leaves and canopies at different scales, from leaf clip-on sensors, cameras mounted on field robots, and/or drones and satellite earth observation.

Project Lead: Dr Oorbessy Gaju

Co-Investigator: Simon Pearson

Funder: Science and Technologies Facilities Council

UKRI AI Centre for Doctoral Training in Sustainable Understandable agri-food Systems Transformed by Artificial INtelligence (SUSTAIN)

SUSTAIN imagines a system where data-driven AI transforms the production of crops (selective harvesting and weeding through precision agriculture) and raising of animals (livestock monitoring, reducing animal GHG emissions and improving animal welfare); enhances plant and animal breeding (AI informed genomics); stabilises supply chains (mechanism design and agent-based modelling); reduces food waste and loss (supply and demand matching) and enables fairer sharing of economic gains and understanding of environmental impacts (ethical and trustworthy AI). All the underlying methods need to be understandable by people so that decisions are trusted (explainable AI).

Project Lead: Professor Simon Parsons

Co-Director: Professor Elizabeth Sklar

Co-Investigator: Louise Manning

Funder: Engineering and Physical Sciences Research Council

Agri-Robotics Unleashed (ARU)

Agri-Robotics Unleashed (ARU) is a whole systems approach that drives soft fruit sustainable productivity by integrating robotic harvesting solutions into greenhouse design and novel canopy architectures.

Project Lead: Dr Marcello Calisti

Co-Investigators: Grzegorz Cielniak, Leonidas Rempelos, Simon Pearson

Funder: Biotechnology and Biological Sciences Research Council

Alleviating nutritional stress for wider environmental rewards in sustainable UK protein crop production

The project has one overall aim: to optimize nutrient management for faba bean improvement. Applying optimal nutrient doses is important for achieving higher crop yields while keeping farm production costs minimal and reducing environmental impacts.

Project Lead: Dr Ravi Valluru

Co-Investigator: Professor Simon Pearson

Funder: Innovate UK

FinerForecasts – Biologically Driven Soft-Fruit Resource Optimisation, Labour and Yield Forecasts at Plant Granularity

FinerForecasts will leverage FruitCast's ability to quickly and cheaply measure crop state from videos to make plant-level forecasts possible at commercial scales.

Project Lead: Dr Shaun Coutts

Co-Investigator: Grzegorz Cielniak

Funder: Innovate UK