Review: Precision Livestock Farming technologies in pasture-based livestock systems

Precision Livestock Farming (PLF) encompasses the combined application of single technologies or multiple tools in integrated systems for real-time and individual monitoring of livestock. In grazing systems, some PLF applications could substantially improve farmers' control of livestock by overcoming issues related to pasture utilisation and management, and animal monitoring and control. A focused literature review was carried out to identify technologies already applied or at an advanced stage of development for livestock management in pastures, specifically cattle, sheep, goats, pigs, poultry. Applications of PLF in pasture-based systems were examined for cattle, sheep, goats, pigs, and poultry. The earliest technology applied to livestock was the radio frequency identification tag, allowing the identification of individuals, but also for retrieving important information such as maternal pedigree. Walk-over-weigh platforms were used to record individual and flock weights. Coupled with automatic drafting systems, they were tested to divide the animals according to their needs. Few studies have dealt with remote body temperature assessment, although the use of thermography is spreading to monitor both intensively reared and wild animals. Global positioning system and accelerometers are among the most applied technologies, with several solutions available on the market. These tools are used for several purposes, such as animal location, theft prevention, assessment of activity budget, behaviour, and feed intake of grazing animals, as well as for reproduction monitoring (i.e., oestrus, calving, or lambing). Remote sensing by satellite images or unmanned aerial vehicles (UAVs) seems promising for biomass assessment and herd management based on pasture availability, and some attempts to use UAVs to monitor, track, or even muster animals have been reported recently. Virtual fencing is among the upcoming technologies aimed at grazing management. This system allows the management of animals at pasture without physical fences but relies on associative learning between audio cues and an electric shock delivered if the animal does not change direction after the acoustic warning. Regardless of the different technologies applied, some common constraints have been reported on the application of PLF in grazing systems, especially when compared with indoor or confined livestock systems. Battery lifespan, transmission range, service coverage, storage capacity, and economic affordability were the main factors. However, even if the awareness of the existence and the potential of these upcoming tools are still limited, farmers' and researchers' demands are increasing, and positive outcomes in terms of rangeland conservation, animal welfare, and labour optimisation are expected from the spread of PLF in grazing systems.

Calf Birth Weight Predicted Remotely Using Automated in-Paddock Weighing Technology

The present study aimed to develop predictive models of calf birth weight (CBW) from liveweight (LW) data collected remotely and individually using an automated in-paddock walk-over-weighing scale (WOW). Twenty-eight multiparous Charolais cows were mated with two Brahman bulls. The WOW was installed at the only watering point to capture LW over five months. Calf birth date and weight were manually recorded, and the liveweight change experienced by a dam at calving (ΔLWC) was calculated as pre-LW minus post-LW calving. Cow non-foetal weight loss at calving (NFW) was calculated as ΔLWC minus CBW. Pearson's correlational analysis and simple linear regressions were used to identify associations between all variables measured. No correlations were found between ΔLWC and pre-LW (p = 0.52), or post-LW (p = 0.14). However, positive associations were observed between ΔLWC and CBW (p < 0.001, R2 = 0.56) and NFW (p < 0.001, R2 = 0.90). Thus, the results suggest that 56% of the variation in ΔLWC is attributed to the calf weight, and consequently could be used as an indicator of CBW. Remote, in-paddock weighing systems have the potential to provide timely and accurate LW data of breeding cows to improve calving management and productivity.

Measuring liveweight changes in lactating dairy ewes with an automated walk-over-weighing system

Monitoring liveweight (LW) is an important part of sound management practices at the individual and flock level (e.g., controlling for nutritional status based on body condition, reproduction, and health-related issues), but it is time consuming and stressful. To our knowledge, no literature has reported on the evaluation of automated weighing systems in dairy sheep as an alternative to conventional static scales. The objective of this research was to evaluate the practical feasibility of using an automated walk-over-weighing (WoW) prototype to measure daily LW changes in dairy ewes without human intervention. We used adult Lacaune dairy ewes in 2 complementary trials conducted indoors. Trial 1 aimed at evaluating the repeatability, precision, and accuracy of LW measures recorded using WoW scales compared with a static scale (the gold standard). Forty-two adult ewes (LW ± standard deviation = 71.3 ± 10.4 kg) were randomly drafted from the main flock and used in a 1-day session. The trial included 3 passages. In each passage, ewes were weighed first on a static scale; once a static position was achieved and LW recorded, they continued the circuit and immediately traversed the WoW scale for an automated LW record. Trial 2 aimed to demonstrate the feasibility of using the WoW device under real-world conditions in a dairy sheep-farming system. The WoW scale was installed in the exit race of the milking parlor and evaluated over 7 wk with adult ewes in mid lactation (n = 93; LW 78.5 ± 8.1 kg). Once the ewes were acclimated to the WoW system, 1 group of ewes (n = 48) continued to receive the same feeding regimen (controls), and the other group (n = 45) underwent a nutritional challenge [challenged; 2 wk of undernutrition and then back to control regimen (refeeding) for 1 wk]. We evaluated the ability of the WoW to detect small changes in LW. We collected LW data (2 weighings per ewe per day) from the WoW after each of the 2 milking sessions (morning and evening). We also obtained LW values by weighing the ewes using a static scale once a week. The automated WoW system showed substantial agreement with the gold standard when assessed using Lin's concordance correlation coefficient and Bland and Altman's method, largely due to high repeatability. The WoW system was adequate for detecting small daily variations in LW during undernutrition and refeeding periods. Misbehaviors resulted in spurious WoW values in trial 2, requiring us to use filtration methods to exclude outlier weights and allow meaningful assessment of small LW changes. The WoW system evaluated here is an alternative to the static scales conventionally used on dairy sheep farms. If sound filtration of raw data is applied, WoW could contribute to the close (daily) monitoring of individual LW without operator intervention (i.e., voluntary weighing) and taking animal welfare into account (i.e., no stress related to the weighing session on static scales).

Advancements in sensor technology and decision support intelligent tools to assist smart livestock farming

Remote monitoring, modern data collection through sensors, rapid data transfer, and vast data storage through the Internet of Things (IoT) have advanced precision livestock farming (PLF) in the last 20 yr. PLF is relevant to many fields of livestock production, including aerial- and satellite-based measurement of pasture’s forage quantity and quality; body weight and composition and physiological assessments; on-animal devices to monitor location, activity, and behaviors in grazing and foraging environments; early detection of lameness and other diseases; milk yield and composition; reproductive measurements and calving diseases; and feed intake and greenhouse gas emissions, to name just a few. There are many possibilities to improve animal production through PLF, but the combination of PLF and computer modeling is necessary to facilitate on-farm applicability. Concept- or knowledge-driven (mechanistic) models are established on scientific knowledge, and they are based on the conceptualization of hypotheses about variable interrelationships. Artificial intelligence (AI), on the other hand, is a data-driven approach that can manipulate and represent the big data accumulated by sensors and IoT. Still, it cannot explicitly explain the underlying assumptions of the intrinsic relationships in the data core because it lacks the wisdom that confers understanding and principles. The lack of wisdom in AI is because everything revolves around numbers. The associations among the numbers are obtained through the “automatized” learning process of mathematical correlations and covariances, not through “human causation” and abstract conceptualization of physiological or production principles. AI starts with comparative analogies to establish concepts and provides memory for future comparisons. Then, the learning process evolves from seeking wisdom through the systematic use of reasoning. AI is a relatively novel concept in many science fields. It may well be “the missing link” to expedite the transition of the traditional maximizing output mentality to a more mindful purpose of optimizing production efficiency while alleviating resource allocation for production. The integration between concept- and data-driven modeling through parallel hybridization of mechanistic and AI models will yield a hybrid intelligent mechanistic model that, along with data collection through PLF, is paramount to transcend the current status of livestock production in achieving sustainability.

Research on a Dynamic Algorithm for Cow Weighing Based on an SVM and Empirical Wavelet Transform

Weight is an important indicator of the growth and development of dairy cows. The traditional static weighing methods require considerable human and financial resources, and the existing dynamic weighing algorithms do not consider the influence of the cow motion state on the weight curve. In this paper, a dynamic weighing algorithm for cows based on a support vector machine (SVM) and empirical wavelet transform (EWT) is proposed for classification and analysis. First, the dynamic weight curve is obtained by using a weighing device placed along a cow travel corridor. Next, the data are preprocessed through valid signal acquisition, feature extraction, and normalization, and the results are divided into three active degrees during motion for low, medium, and high grade using the SVM algorithm. Finally, a mean filtering algorithm, the EWT algorithm, and a combined periodic continuation-EWT algorithm are used to obtain the dynamic weight values. Weight data were collected for 910 cows, and the experimental results displayed a classification accuracy of 98.6928%. The three algorithms were used to calculate the dynamic weight values for comparison with real values, and the average error rates were 0.1838%, 0.6724%, and 0.9462%. This method can be widely used at farms and expand the current knowledgebase regarding the dynamic weighing of cows.

Using Walk-over-Weighing technology for parturition date determination in beef cattle

The northern Australian beef industry is dominated by cow-calf operations where reproductive efficiency is a major profit driver. The postpartum anoestrus interval is a major contributor to an animal’s reproductive efficiency and is influenced by genetic selection. The genetic trait that measures an animal’s postpartum anoestrus interval is the days to calving estimated breeding value and a key requirement is knowledge of the cow’s calving date. Traditionally calving date is recorded using laborious and costly methods that are impeding the recording and hence the accuracy of genetic predictions for this trait by the northern Australian seedstock industry. The present experiment used Walk-over-Weighing technology to automatically record animal weights as cattle enter a restricted area where they access water. With the use of a novel method to accurately assess weights, the growth paths of cows were tracked from late gestation to post-calving. The calving date was visualised in the growth paths of most cows (78.3%) and a custom algorithm was able to automatically detect the calving date within 10 days of the observed calving period for 63% of cows. The use of Walk-over-Weighing to record calving date provides the opportunity to increase the recording of the days to calving estimated breeding value in the northern seedstock industry, thereby increasing reproductive efficiency and improving the profitability of northern beef producers.