Search

The increasing demand for providing an animal-friendly environment that ensures animal well-being and economic efficiency in animal farming leads to more advanced and efficient animal farming methods. Precision livestock farming (PLF) can simultaneously remove time-consuming tasks and extra labor for a farmer and improve animal well-being and welfare. In this review, we describe the PLF concept with a focus on recently born pigs (piglets) which require extra care and attention due to their vulnerability and sensibility. To do so, we identify the top five mortality causes in newborn piglets: low vitality, hypothermia, starvation, crushing, and hypoxia. Furthermore, the correlation and interconnections among these mortality causes are explored. Then, the most relevant health indicators (HIs), which can be early indicators of an animal issues, are also introduced. Each mortality cause can be recognised through some symptoms, which can then be used as indicators. Considering these indicators, we can improve the animals' well-being and avoid unforeseen losses. Novel sensing and communication technologies in PLF can be utilized to monitor these HIs to give an early warning to the farmer in case something is wrong. Different novel sensing and communication technologies, whether tested on animals or not, are investigated in this review to give the researcher a better idea of available technologies that can be used in PLF implementation.

The combination of computer vision with deep learning has become a popular tool for automation of labor-intensive monitoring tasks in modern livestock farming. However, uncontrolled and varying environmental conditions, which usually prevail in farmhouses, influence the performance of vision-based applications. Image quality can be reduced, for instance by occlusions, illumination or motions of the animals, which can influence the reliability of those applications. To address this issue, this study proposes an approach for the identification of uncertain neural-network predictions to improve the overall prediction quality. It proposes the direct quantification of aleatoric and epistemic uncertainty on the one hand and indirect estimation of uncertainty through the prediction of occlusions on the other hand. Our approach simultaneously integrates the different methods into an end-to-end trainable instance segmentation and regression model. The objective of this study was to first investigate how well the different measures can quantify the uncertainty of a prediction by comparing them to human uncertainty assessments. Then, it was analyzed whether the uncertainty estimations are capable to identify and reject erroneous predictions by evaluating the correlation between the predictive error and the uncertainty estimations. Finally, individual predictions were rejected based on the estimated uncertainties to analyze the effect on the overall accuracy. As a use-case, the developed methods were applied to the prediction of plumage conditions of chickens but also examined in a separate domain. The results showed that the outputs of our approaches for the estimation of aleatoric and epistemic uncertainty correlate to the predictive error of the model, and lead to increased performance when uncertain predictions are rejected. In contrast, the indirect method to identify occluded samples did not serve as a reliable indicator for uncertainty and could therefore not be used to improve the accuracy of the model outputs.

The Bhutanese government initiated a highland development programme in the year 2016 to promote yak farming because the number of yak farming families is declining. However, there are several cross-cutting policies and issues that affect successful implementation of interventions to support yak farming in transition. We studied the challenges and opportunities to sustain yak farming and related trade-offs around problems and solutions through individual and focus group interviews with six stakeholder groups (i.e. herders from two regions, extensionists, park rangers, livestock officials, and forest officials). Overall the herders rated forage availability and yak mortality as the main threats to yak farming, while government officials rated labour availability as the main threats. Most problems and solutions that were identified in the focus group interviews had diverging views among the stakeholder groups. There is clearly a need for a multi-stakeholder dialogue aiming to discuss problems and solutions together. This should take away misleading and disputed claims, and provide understanding about the approach to cope with risks and uncertainty around transhumance yak-based communities. A strong collaboration should lead to appropriate policy, which would reduce challenges and barriers, and simultaneously give opportunities to herders and their children to stay in yak farming in future.

Clinical mastitis (CM) is an important production disease in dairy cows, but much of the knowledge required to effectively control CM is lacking, specifically in low-income countries where most farms are small and have specific dairy management, such as regular udder cleaning and practicing hand milking. Therefore, we conducted a 6-month-long cohort study to (a) estimate the incidence rate of clinical mastitis (IRCM) at the cow and quarter level, (b) identify risk factors for the occurrence of CM, (c) describe the etiology of CM, and (d) quantify antimicrobial susceptibility (AMS) against commonly used antimicrobial agents in S. aureus and non-aureus Staphylococcus spp. (NAS) in dairy farms in the Chattogram region of Bangladesh. On 24 farms, all cows were monitored for CM during a 6-month period. Cases of CM were identified by trained farmers and milk samples were collected aseptically before administering any antimicrobial therapy. In total, 1383 lactating cows were enrolled, which totaled 446 cow-years at risk. During the study period, 196 new cases of CM occurred, resulting in an estimated crude IRCM of 43.9 cases per 100 cow-years, though this varied substantially between farms. Among the tested CM quarter samples, Streptococci (22.9%) followed by non-aureus staphylococci (20.3%) were the most frequently isolated pathogens and resistance of S. aureus and NAS against penicillin (2 out of 3 and 27 out of 39 isolates, respectively) and oxacillin (2 out of 3 and 38 out of 39 isolates, respectively) was common. The IRCM was associated with a high milk yield, 28 to 90 days in milk, and a higher body condition score. Our results show that there is substantial room for udder health improvement on most farms.