PhD Studentship: Evaluating the Role of Big Data in Understanding Livestock Impacts on the Upland Landscape

DoS: Dr Mark Whiteside (Email: mark.whiteside@plymouth.ac.uk)

2^nd Supervisor: Dr Katherine Herborn (Email: katherine.herborn@plymouth.ac.uk)

3^rd Supervisor: Dr Lauren Ansell (Email: lauren.adams@plymouth.ac.uk)

4^th Supervisor: Dr James Buckley (Email: james.buckley@plymouth.ac.uk)

Applications are invited for a 3.5 years PhD studentship within the Environmental Intelligence doctoral training programme at the University of Plymouth, starting 01 October 2024.

Project description

Scientific background

Upland farming plays a pivotal role in UK upland ecology through existing negative and positive impacts of traditional livestock management but increasingly through incentives to provide ecosystem services (such as improved soil health, biodiversity, carbon sequestration and natural flood management). To evaluate these impacts, fine-scale understanding of livestock movement and behaviour in this environment is essential. In more intensive farm systems, ‘Precision Livestock Farming’ (PLF), the application of Big Data and remote sensing in animal management, is revolutionising the way we understand animals, their interaction with the environment and, crucially, how we farm sustainably.  

In this multidisciplinary project we will explore the potential of cutting-edge sensor technology, data retrieval and computational approaches for understanding landscape-level interactions between livestock and the environment. The aim of the project is to bring the upland farm into the PLF framework by addressing the following objectives:

1. Validating and automating an array of animal-mounted and environmental sensors under controlled field conditions.
2. Ground-truthing these new methods for remotely monitoring animal-environment interactions in the heterogeneous upland landscape.
3. Determining how these data could inform current and emerging agricultural practice to better manage the complex interplay between livestock production and ecosystem services

Research methodology

Bespoke sensors (GPS and accelerometers) will be attached to livestock on Dartmoor. For validation, data will be collected from animals in controlled environments where we can manipulate behaviour (e.g. foraging heights, transitory paths), monitor welfare (e.g. limping) and determine fine-scale ecological impacts (e.g. biodiversity, soil health). Machine learning approaches will be used to automate behavioural classification, allowing for remote monitoring of habitat use and behaviour in animals ranging in larger areas (e.g. newtakes, common land), to explore ecological impacts. These impacts will be compared across livestock demographic (breeds, ages) and management practices (e.g. open flocks, worming protocol).

Training

The successful candidate will benefit from this interdisciplinary project, applying Big Data approaches to high-throughput movement and behaviour data to address challenges within production, sustainability, and ecology. The candidate will develop key skills in using relevant programming languages (R and/or Python), sensor technologies, ecological sampling, experimental design, welfare/production assessment, and animal handling and husbandry. They will be supported to develop a network of both academic collaborators and stakeholder contacts. On completion they will be well-placed to seek academic positions in e.g. animal data science, behavioural and welfare science, and industry positions in the growing field of PLF.

Person specification

We are looking for a candidate with a degree in biological sciences, computer science or data science (or similar) and an interest in agriculture and ecology. Enthusiasm to learn and develop a diverse set of skills and engage with different audiences is therefore important.

If you wish to discuss this project further informally, please contact Dr Mark Whiteside, email: mark.whiteside@plymouth.ac.uk.

For Eligibility, Funding and to Apply, please click on the links below: 

• Eligibility
• Funding

To apply, please click the 'Apply' button, above.

The closing date is on 26 April 2024.

Advert information