PhD in Automated assessment of chicken welfare
The aim of this PhD project is to create a vision-based system for the automated assessment of chicken welfare for use in poultry farms. The welfare of broiler chickens is a key ethical and economic challenge for the sustainability of chicken meat production. The presentation of natural, positive behaviour is important to ensure a “good life” for livestock species as well as being an expectation for many consumers. At present there are no ways to measure this, with good welfare habitually defined as the absence of negative experience. In addition, automated tracking of individual birds is very challenging due to occlusion and complexity. In this project the student will instead harness and develop novel deep learning approaches that consider individual animals and their behaviours probabilistically within the context of local and general activity within the barn and wider flock. The inferred behaviour rates amongst the flock will then be integrated with on-farm production, health and environmental data through Bayesian time series modelling to identify risk factors for positive welfare, predict farms at risk of poor welfare, and suggest interventions that avoid this scenario.
The PhD will be supervised by statistical data scientist Prof Andrew Dowsey and deep learning experts Dr John Fennell and Dr Laszlo Talas, who together have extensive experience in animal biometrics and agri-tech applications, and animal welfare and veterinary ethics specialist Prof Siobhan Mullan. Industrial co-supervisors at FAI, Annie Rayner and Ralf Onken have long been involved in developing systems for big-data analysis of welfare and monitoring environmental outputs in livestock supply chains.
The studentship would suit a student with a computational or mathematical background, or with a behavioural science or biological background that included a strong computational element.
Salary: Four years of tuition fees at the UK student rate, a tax-free stipend of £19,285 per year
Closing date: 09/04/2021
Further information can be found here.
