Search

The European Food Safety Authority (EFSA) strives to develop new methodologies (quantitative and qualitative) for assessing animal welfare of food-producing animals by 2027 and start collecting standardised and good quality animal welfare (AW) data by 2030. In light of its vision, EFSA identified the need to develop an action Roadmap for the More Welfare project: towards new risk assessment methodologies and harmonised animal welfare data in the EU. This Roadmap maps existing animal welfare assessment methods, tools, and data collection activities for different species of food-producing animals through literature review, desk research, online surveys, and workshops. It identifies data and knowledge gaps as well as challenges and blockers prevalent in AW assessment. In doing so, the roadmap points towards research areas that require further development (i.e., working areas), but also highlights collaboration opportunities and priority strategies (actions and project proposals) necessary for achieving EFSA's vision. Seven working areas for animal welfare assessment were identified and discussed with EFSA and external AW experts during virtual workshops, touching upon the definition of animal welfare, indicators and tools for welfare assessment, and the development of frameworks to assess and/or prioritise animal welfare issues. Finally, the Roadmap formulates five project proposals, each of them presenting high-level recommendations on multi-annual and multi-partner projects that were identified in collaboration with EFSA and AW experts, each supported by a SWOT analysis.

Digital agriculture offers opportunities for improved monitoring and precision phenotyping of farm animals, crucial to achieving a more sustainable livestock production sector. Video-based analysis enables the quantification of animal behaviour in a non-invasive, automated way with few sensors. To unlock its full potential, appropriate computer vision techniques are needed. In this study, we propose an algorithm to detect lying-down and standing-up behaviour in dairy cows based on changes in bounding box properties detected via YOLOv5 and tracked with DeepSORT. We analysed 86 videos with a standing-up or lying-down event. With different criteria applied to the bounding box time series, we could detect up to respectively 92.3 and 80% for standing-up and lying-down events, respectively, with an accuracy of less than 2 seconds. Using bounding box properties as proxy for body shape and location, a general cow detection algorithm can serve multiple behavioural analyses simultaneously, whilst interpretability of the algorithms is maintained.

This study investigated the automated tracking of multiple cows simultaneously using computer vision and deep learning. Video clips were collected in 2019 at Dairy Campus, where cows were housed in small groups (n=16). A systematic approach covering the true variability of barn circumstances eventually resulted in the selection of 159 frames that were annotated by drawing bounding boxes around each cow. These frames were used to retrain and test four You Only Look Once version 5 (YOLOv5) models to automatically detect cows. The weights of the best performing YOLOv5 model were used to parametrize the deep learning algorithm DeepSORT to track multiple cows simultaneously. This algorithm was applied to a 10 min timeframe of a randomly selected video clip and evaluated by computing the multi-object tracking accuracy, which was 92.8%. This outcome is a promising and essential step towards automated monitoring of individual behaviour of group-housed cows.

This report details the activities carried out in 2019 in the KB DDHT project 8 “Exploring the potential of non-destructive and non-invasive sensor technologies in food supply chains”. It compiles all four deliverables of this project as a single narrative. There are five case studies at the core of this project which address animal welfare, indoor farming, inspection of fresh food products, personalized nutrition advise and food fraud detection. Multiple activities were planned in these case studies with main focus on sensor technologies for non-destructive and non-invasive sensing. One of the key activities was to conduct a survey of sensor technologies applicable and potentially suitable for each case study. In addition, for each case study, one or more experiments were conducted which involved data acquisition using novel sensors as well as building knowledge on data analysis of data from the new sensors. Furthermore, as one of the goal of this project is to explore new sensor technologies, it is expected that this project will generate valuable data. Therefore, focus was also on FAIR data sharing and management. A workshop was organized in collaboration with WDCC on this topic. Most of the case studies also aligned with OnePlanet Research centre, and as a result multiple experiments are in planning for 2020 in cooperation with OnePlanet.

Digestibility of nutrients in pig diets is an important component of overall feed efficiency. Targeted improvement of digestibility is currently mainly achieved by optimization of pig diets, based on information generated from digestibility trials that aim to establish fecal digestibility coefficients of different nutrients across a variety of ingredients. Genetic selection for nutrient digestibility is hampered by shortage of data on individual digestibility, but might help to further improve efficiency of pork production. The present study aimed to estimate the repeatability of fecal digestibility in pigs, as a first step to judge the perspectives for a breeding approach of nutrient digestibility. To achieve this, data was accumulated across nine digestibility trials, containing 1150 digestibility records of 416 growing pigs, measured across the trials. The data was analyzed with a model estimating variances for trial, diet, common litter, and individual animal effect for digestibility of Dry Matter, Ash, Organic Matter, Crude Protein, Crude fat and Non-Starch Polysaccharides. The factors diet and trial together explained the majority of the phenotypic variance, due to the design of the trials. Within diet and trial, common litter and individual animal effect contributed 0–10% of the phenotypic variance. The repeatability estimates ranged from 7% for Ash to 16% for Crude Protein, which suggests there may be genetic variation between pigs in digestibility. In conclusion, the repeatability estimates indicate it is worthwhile to collect phenotypic data that enable the estimation of genetic parameters for digestibility, if these data can be obtained at reasonable cost.

As input for the TEEBAgriFood study, TEEB asked for a series of studies on livestock, rice, palm oil, inland fisheries and agro-forestry. This report deals with livestock production and aims to improve decision-making in livestock production policies, to enhance its viability, not just economically but also socially and environmentally. Livestock sector is important because they have high externalities and it is expected that livestock consumption will be 76% higher in 2050 compared to 2005 (Alexandratos and Bruisma, 2012) because of population growth, income growth, urbanization and preference shifts. This report aims to provide evidence that will help to identify policy options for the transition towards increased food security with sustainable livestock production systems, with particular emphasis on the role of smallholder farmers.