Abstract/Summary

Animal welfare standards are used within the food industry to demonstrate efforts in reaching higher welfare on farms. To verify compliance with those standards, inspectors conduct regular on-farm animal welfare assessments. Conducting these welfare assessments can, however, be time-consuming and prone to human bias. The emergence of Digital Livestock Technologies (DLTs) offers new ways of monitoring farm animal welfare and can alleviate some of the challenges related to animal welfare assessments by collecting data automatically and more frequently. Whilst automating welfare assessments with DLTs may be promising, little attention has been paid to farmers’ perceptions of the challenges that could prevent successful implementation. This study aims to address this gap by focusing on the trial of a DLT (a 3D machine learning camera) to automate mobility and body condition scoring on 11 dairy cattle farms. Semi-structured, in-depth interviews were conducted with farmers, technology developers and a stakeholder involved in a farm assurance scheme (N=14). Findings suggest that stakeholders perceived important benefits to the use of the camera in this context, from building consumer trust by increasing transparency to improved management efficiency. There was also a potential for greater consistency in data collection and thus for enhanced fairness across the UK dairy sector, particularly on the issue of lameness prevalence. However, stakeholders also raised important concerns, such as a lack of clarity around data ownership, reliability, and use, and the possibility of some farmers being penalised (e.g., if the technology failed to work). Better clarity should thus be given to farmers in relation to data governance and evidence provided in terms of technical performance and accuracy. The findings of this study highlighted the need for more inclusive approaches to ensure farmers’ concerns are adequately identified and addressed. These approaches can help minimise negative consequences to farmers and animal welfare, whilst maximising the potential benefits of automating welfare-related data collection.