The UK Government has set an ambitious target to meet Net-Zero greenhouse gas (GHG) emissions by 2050, has pledged to reduce methane emissions by 30% by 2030, and has legal requirements to reduce ammonia emissions. Greenhouse gases pose a threat to our environment by driving climate change. Ammonia reacts with other substances in the air to form particulate matter, which is damaging to human and animal health, causes damage to vulnerable habitats through acidification, and the nitrogen in ammonia can be re-emitted as nitrous oxide (a potent GHG), also contributing to climate change. In the UK, agriculture is responsible for 11% of GHGs and 87% of ammonia emissions. Around 50% of GHGs and 75% of ammonia emissions from agriculture are associated with livestock or their wastes. Therefore, reducing emissions of these gases from agriculture is vital to meeting these ambitious commitments. However, there is a real risk that implementing a mitigation measure to reduce one particular gas could lead to increases in one or more of the others. It is important to identify, quantify, and optimise these potential trade-offs to ensure that a net reduction in all emissions is achieved. Currently there are very few facilities with the capability to measure emissions of all these gases (methane, nitrous oxide, carbon dioxide and ammonia) simultaneously from individual animals, which is apparent in the very low number of studies reporting all of them. The addition of ammonia and nitrous oxide emission measurement capability to our current respiration chamber facility (GreenCow - measuring methane and carbon dioxide), alongside upgrades to the current system to improve reliability and energy efficiency, would create an ultra-modern, state-of-the-art research facility allowing the comprehensive assessment of the net environmental impact of mitigation measures. The facility is designed to meet the requirements for beef cattle, but methods for measuring non-lactating dairy cattle, small ruminants (e.g., sheep and goats) poultry, pigs and for slurry studies will be developed to vastly expand the user-base for the new equipment. The aim for the new equipment will be to provide new knowledge on impacts on the key pollutants of nitrous oxide and ammonia. Gaining comprehensive underpinning data supporting reductions in all emissions when mitigation measures are applied, or quantifying and optimising trade-offs between gases, will improve cohesion between different policy objectives and will help improve farmer and consumer confidence leading to greater uptake.

This project addresses the key challenges facing dairy goat milk production by using new genetic and genomic technologies to improve the quality of milk production and disease management. The main challenge is to breed healthy goats with resistance to bacterial infections leading to mastitis, and to identify sires with daughters that have lower susceptibility to mastitis and generate genomic predictions of merit for this trait. The wider goat industry in the UK and abroad will access genomic predictions of enhanced mastitis resistance via new molecular technology from the creatipon of a low density (LD), lower cost customised single nucleotide polymorphism (SNP) array for UK goats. This allows for the use of more cost-effective molecular technology to predict ('impute') the information that was previously generated by the more expensive, more comprehensive SNP array and enabling more animals to be genotyped. The project will ensure sustainable breeding objectives for dairy goats in the long-term, by including routine collection of mastitis records as indicators of health and longevity, thereby helping to translate previous TSB-funded research into practice. It is estimated that mastitis affects up to a third of all UK dairy goats during their reproductive life. Even thoughthis hasn't been formally quantified in the UK, we anticipate that YDG loses around £286K p.a. in lost productivity and additional replacement costs. Mastitis is termed a 'complex trait' in animal breeding terms, i.e. whereby many genes are involved in determining whether or not animals succumb to clinical (or subclinical) disease. For this reason, using well recorded goats, the overall aim of the project is to generate genetic (EBV) and genomic (GEBV) breeding values that will identify genetically more resistant animals to mastitis, irrespective of the causative organisms. Such approach is in line with the EU regulations, which are aiming to restrict the use of active compounds to control agricultural diseases, which increases the risk of pathogens developing resistance to current biological and chemical control measures. Breeding of animals with increased disease resistance and thus improved health will allow the animals to better realise their genetic potential for milk production. The use of EBVs and GEBVs will allow for accurate elimination of animals with high susceptibility to mastitis, thus acting as a measure of early identification of potential disease. This proposal is a collaborative project that will stimulate the production of high quality goat milk in the UK. This will be done through the exploitation of new genomic technology (a low-density (LD), single nucleotide polymorphism, (SNP) array that is tailored to UK goat breeds), to identify high genetic and genomic merit dairy goats for mastitis resistance, functional fitness, health, and longevity, whilst attaining high levels of milk production. This will result in a balanced breeding programme, which is necessary for sustainable intensification of goat milk production. The challenge is for the UK goat milk industry to become a leading international player in the supply of high genetic merit livestock for milk production, whilst building a reputation for the supply of animals of high disease resistance. The identification of sires with daughters with high mastitis resistance will greatly reduce losses due to veterinary costs and decreased milk supply. Breeding of goats with increased resistance for mastitis will become a unique selling point for the industrial partner. The routine inclusion of mastitis phenotyping for the goat selection index is likely to improve mastitis resistance, in a similar way to that which has recently occurred for fertility in the dairy cattle, initiated by the uptake of the new dairy fertility index.

Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.

Livestock farmers are turning to agri-technology to respond to the challenges of climate change, sustainability, anti-microbial resistance and food security while efficiently producing animals with good health and welfare. Machine vision technology, where software uses 'deep learning' neural networks to automatically process video images, could provide unique insights: 24/7 live data on growth/production and behavioural change as a measure of individual animal health and welfare. Problems such as disease, lameness or harmful behaviours such as aggression and tail-biting could be automatically detected. Continuous tracking in a farm environment is challenging as pigs change shape and can lie next to or on top of each other, and the best available systems can only track pigs for minutes unless they are marked somehow (which commercial growing pigs are not). The Pig ID project represents a step-change in capability by continuously monitoring individual unmarked pigs over weeks and months as they grow. We previously developed a system which can identify (ID) individual pigs from their faces. Face ID is accurate but positioning cameras to capture pig faces is hard and does not capture whole-pen behaviour. Here we plan to develop a deep learning system using the latest neural networks to learn to recognise individual pigs, updating as they grow and continuously track their movements. First, building on our face recognition system, we will develop a remote overhead biometric ID system based on head and body features. Only when confidence in the ID of a pig is lost will frame-to-frame tracking be used as a backup until biometric ID can re-acquire the pig. In this way, continuous accurate pig identity and location will be established. Pigs grow rapidly, so their size and appearance change a lot over time. So next, we will determine how robust our trained ID and tracking system is to this change by testing it on images of the same pigs from different weeks. We will establish how robust it is to changing pig appearance and implement automatic retraining of biometric ID at regular intervals, enabling continued tracking over weeks. To date, machine vision pig tracking has only been demonstrated with one or a few groups of pigs that it has been trained on. Another crucial innovation of this project is that we will take our trained system and work to develop automated enrolment using 'open set recognition', clustering the images of a new group of pigs by similarity to learn about those new individuals. To achieve a large volume of training and validation data needed for this project, we will semi-automate by combining machine vision to find pigs in each image, with humans to confirm and label them with ID. Alongside in-person identification of pigs as a failsafe, we will develop a novel way of validating ID using visible colour and ultraviolet (UV) cameras side by side, while pigs have distinctive sun-cream markings, invisible except to the UV camera. These parallel UV images will enable human manual ground-truthing of pig ID in every frame, to check against biometric ID results from colour images where the sun-cream is invisible. Once the biometric ID system is complete, it will also be used with the UV images. It should easily learn to recognise these marked pigs providing further validation data. This project builds on our proven Face ID technology and we are continuing our previous successful collaboration, bringing together expertise in animal behaviour and welfare, and in agri-technology, particularly in applying cutting-edge machine learning techniques in machine vision/learning to real-word problems. The project has considerable commercial support, with co-funding from animal health company Zoetis under an Industrial Partnership Award. Agri Tech company Innovent Technology Ltd, pig farming and pork processing company Karro, and breeding company PIC are ready to be involved in the next stage of commercialisation.

Tail biting in pigs is a serious and unpredictable animal welfare problem for farmers worldwide. It results in losses for farmers of £10.4M a year in the UK alone, mainly from carcass condemnation. Before damaging tail biting begins, pigs hold their tails down. This project will develop a system to detect these tail posture changes using a 3D video system giving farmers advance warning of tail biting in time to intervene. We will 1) Collect continuous 3D video from pigs at a high risk of tail biting to capture the changes in tail posture pre-tail biting, 2) Provide a detailed behaviour analysis of tail posture changes and 3) Develop software algorithms to automate this. The project partners provide expertise in pig behaviour (SRUC), a route to market and algorithms for automated 3D video analysis (Innovent Technology Ltd), pork supply chain knowledge (Sainsbury's) video expertise and access to a network of expertise in engineering and precision agriculture (Agri-EPI centre).