Intake estimation in dairy cows fed roughage-based diets: An approach based on chewing behaviour measurements

Monitoring Cattle Ruminating Behavior Based on an Improved Keypoint Detection Model

Cattle rumination behavior is strongly correlated with its health. Current methods often rely on manual observation or wearable devices to monitor ruminating behavior. However, the manual monitoring of cattle rumination is labor-intensive, and wearable devices often harm animals. Therefore, this study proposes a non-contact method for monitoring cattle rumination behavior, utilizing an improved YOLOv8-pose keypoint detection algorithm combined with multi-condition threshold peak detection to automatically identify chewing counts. First, we tracked and recorded the cattle's rumination behavior to build a dataset. Next, we used the improved model to capture keypoint information on the cattle. By constructing the rumination motion curve from the keypoint information and applying multi-condition threshold peak detection, we counted the chewing instances. Finally, we designed a comprehensive cattle rumination detection framework to track various rumination indicators, including chewing counts, rumination duration, and chewing frequency. In keypoint detection, our modified YOLOv8-pose achieved a 96% mAP, an improvement of 2.8%, with precision and recall increasing by 4.5% and 4.2%, enabling the more accurate capture of keypoint information. For rumination analysis, we tested ten video clips and compared the results with actual data. The experimental results showed an average chewing count error of 5.6% and a standard error of 2.23%, verifying the feasibility and effectiveness of using keypoint detection technology to analyze cattle rumination behavior. These physiological indicators of rumination behavior allow for the quicker detection of abnormalities in cattle's rumination activities, helping managers make informed decisions. Ultimately, the proposed method not only accurately monitors cattle rumination behavior but also provides technical support for precision management in animal husbandry, promoting the development of modern livestock farming.

On-farm evaluation of models to predict herbage intake of dairy cows grazing temperate semi-natural grasslands

The objective of the present on-farm study was to evaluate the adequacy of existing models in predicting the pasture herbage DM intake (PDMI) of lactating dairy cows grazing semi-natural grasslands. The prediction adequacy of 13 empirical and semi-mechanistic models, which were predominantly developed to represent stall-fed cows or cows grazing high-quality pastures, were evaluated using the mean bias, relative prediction error (RPE), and partitioning of mean square error of prediction, where models with an RPE ≤ 20% were considered adequate. The reference dataset comprised n = 233 individual animal observations from nine commercial farms in South Germany with a mean milk production, DM intake, and PDMI (arithmetic means ± one SD) of 24 kg/d, (±5.6), 21 kg/d (±3.2), and 12 kg/d (±5.1), respectively. Despite their adaptation to grazing conditions, the behaviour-based and semi-mechanistic grazing-based models had the lowest prediction adequacy among the evaluated models. Their underlying empirical equations likely did not fit the grazing and production conditions of low-input farms using semi-natural grasslands for grazing. The semi-mechanistic stall-based model Mertens II with slight modifications achieved the highest and a satisfactory modelling performance (RPE = 13.4%) when evaluated based on the mean observed PDMI, i.e., averaged across animals per farm and period (n = 28). It also allowed for the adequate prediction of PDMI on individual cows (RPE = 18.5%) that were fed < 4.8 kg DM of supplement feed per day. Nevertheless, when used to predict PDMI of individual animals receiving a high supplementation level, the model Mertens II also did not meet the threshold for an acceptable adequacy (RPE = 24.7%). It was concluded that this lack of prediction adequacy for animals receiving greater levels of supplementation was due to a lack of modelling precision, which mainly could be related to inter-animal and methodological limitations such as the lack of individually measured supplement feed intake for some cows. The latter limitation is a trade-off of the on-farm research approach of the present study, which was chosen to represent the range in feed intake of dairy cows across the diverse low-input farming systems using semi-natural grasslands for grazing.

Welfare Quality® for dairy cows: towards a sensor-based assessment

This Research Reflection addresses the possibilities for Welfare Quality® to evolve from an assessment method based on data gathered on punctual visits to the farm to an assessment method based on sensor data. This approach could provide continuous and objective data, while being less costly and time consuming. Precision Livestock Farming (PLF) technologies enabling the monitorisation of Welfare Quality® measures are reviewed and discussed. For those measures that cannot be assessed by current technologies, some options to be developed are proposed. Picturing future dairy farms, the need for multipurpose and non-invasive PLF technologies is stated, in order to avoid an excessive artificialisation of the production system. Social concerns regarding digitalisation are also discussed.

Review: Precision nutrition of ruminants: approaches, challenges and potential gains

A plethora of sensors and information technologies with applications to the precision nutrition of herbivores have been developed and continue to be developed. The nutritional processes start outside of the animal body with the available feed (quantity and quality) and continue inside it once the feed is consumed, degraded in the gastrointestinal tract and metabolised by organs and tissues. Finally, some nutrients are wasted via urination, defecation and gaseous emissions through breathing and belching whereas remaining nutrients ensure maintenance and production. Nowadays, several processes can be monitored in real-time using new technologies, but although these provide valuable data 'as is', further gains could be obtained using this information as inputs to nutrition simulation models to predict unmeasurable variables in real-time and to forecast outcomes of interest. Data provided by sensors can create synergies with simulation models and this approach has the potential to expand current applications. In addition, data provided by sensors could be used with advanced analytical techniques such as data fusion, optimisation techniques and machine learning to improve their value for applications in precision animal nutrition. The present paper reviews technologies that can monitor different nutritional processes relevant to animal production, profitability, environmental management and welfare. We discussed the model-data fusion approach in which data provided by sensor technologies can be used as input of nutrition simulation models in near-real time to produce more accurate, certain and timely predictions. We also discuss some examples that have taken this model-data fusion approach to complement the capabilities of both models and sensor data, and provided examples such as predicting feed intake and methane emissions. Challenges with automatising the nutritional management of individual animals include monitoring and predicting of the flow of nutrients including nutrient intake, quantity and composition of body growth and milk production, gestation, maintenance and physical activities at the individual animal level. We concluded that the livestock industries are already seeing benefits from the development of sensor and information technologies, and this benefit is expected to grow exponentially soon with the integration of nutrition simulation models and techniques for big data analysis. However, this approach may need re-evaluating or performing new empirical research in both fields of animal nutrition and simulation modelling to accommodate a new type of data provided by the sensor technologies.

Concentrate Supplement Modifies the Feeding Behavior of Simmental Cows Grazing in Two High Mountain Pastures

Simple Summary

Traditional Alpine husbandry systems require dairy cows to be grazing on mountain pasture during summer and kept indoors during the remaining part of the year. Nowadays, the pasture is not able to fully satisfy the nutritional requirements of cattle; therefore, the use of concentrates is frequently required. From their use, some issues arise: the cows tend to consume the concentrates at the expense of the grass; concentrates are competitive with human diets; concentrates decrease the environmental sustainability of farm. Therefore, in order to minimize their use, it is imperative to obtain data on the grazing behavior of cows. The aim of this study was to assess the effect of concentrate levels on the behavior of dairy cows during summer grazing in two pastures characterized by Poion alpinae and Seslerion caeruleae alliance. Cows were equipped with an electronic device to evaluate feeding behavior (grazing, rumination, and walking). In addition, the plant selection by animals was assessed. In Poion alpinae, a rich pasture, the increased supplement influenced the selectivity of the pasture species, while in Seslerion caeruleae, a poor pasture, supplementation resulted in a reduction in grazing times. The study highlights how the supplement level induced a different grazing behavior depending on pasture type.

Abstract

During grazing on Alpine pastures, the use of concentrates in dairy cows’ diet leads to a reduction of the environmental sustainability of farms, and influences the selective pressure on some plant species. In order to minimize the use of concentrates, it is imperative to obtain data on the grazing behavior of cows. The aim of this study was to assess the effect of concentrate levels on the behavior of dairy cows during grazing. One hundred and ten lactating Italian Simmental cows, that sequentially grazed two pastures characterized by Poion alpinae (Poion) and Seslerion caeruleae (Seslerion) alliance, were considered. For each pasture, eight cows were selected and assigned to two groups: High and Low, supplemented with 4 kg/head/d, and 1 kg/head/d of concentrate respectively. Cows were equipped with a noseband pressure sensor and a pedometer (RumiWatch system, ITIN-HOCH GmbH) to assess grazing, ruminating, and walking behavior. In addition, the plant selection of the animals was assessed. On Poion, increased supplement intake caused a more intense selection of legumes, without affecting feeding and walking times. On Seslerion, grazing time was higher in Low than High. Grazing management in alpine region must take into account the great variability of pastures that largely differ from a floristic and nutritional point of view.