Search

Water is an important nutrient, and its continuous provision is a critical welfare issue for cattle grazing arid and semiarid rangelands. Time and labor are needed to monitor water availability, and automated monitoring systems are a costly input on expansive rangeland pastures. The objective of this study was to evaluate the potential of detecting water system failures using Global Positioning System (GPS) tracking and accelerometers, assuming the data could be monitored in real or near-real time. Water system failure was simulated in a 1 096-ha pasture in Arizona by placing metal panels around the only drinker for 4 h (0800−1200) on three occasions in 2018 and two occasions in 2019. Randomly selected cows (10 in 2018 and 23 in 2019) of the 120 cows in the pasture were tracked with GPS collars, and 7 (2018) and 10 (2019) of the tracked cows were fitted with triaxial accelerometers. Movement intensity measured by accelerometers was greater (P = 0.03) on the day of simulated water failure than on control days with available water. During simulated water failure, cows remained closer to water (P = 0.01) after approaching the drinker (

Proper grazing management of arid and semi-arid rangelands requires experienced personnel and monitoring. Applications of GPS tracking and sensor technologies could help ranchers identify livestock well-being and grazing management issues so that they can promptly respond. The objective of this case study was to evaluate temporal changes in cattle association patterns using global positioning system (GPS) tracking in pastures with different stocking densities (low stocking density [LSD] = 0.123 animals ha−1, high stocking density [HSD] = 0.417 animals ha−1) at a ranch near Prescott, Arizona. Both pastures contained similar herd sizes (135 and 130 cows, respectively). A total of 32 cows in the HSD herd and 29 cows in the LSD herd were tracked using GPS collars at location fixes of 30 min during a 6-week trial in the summer of 2019. A half-weight index (HWI) value was calculated for each pair of GPS-tracked cattle (i.e., dyads) to determine the proportion of time that cattle were within 75 m and 500 m of each other. Forage mass of both pastures were relatively similar at the beginning of the study and forage utilization increased from 5 to 24% in the HSD pasture and increased from 10 to 20% in the LSD pasture. Cattle in both pastures exhibited relatively low mean association values (HWI &lt, 0.25) at both spatial scales. Near the end of the study, cattle began to disperse likely in search of forages (p &lt, 0.01) and travelled farther (p &lt, 0.01) from water than during earlier periods. Real-time GPS tracking has the potential to remotely detect changes in animal spatial association (e.g., HWI), and identify when cows disperse, likely searching for forage.

Livestock vocalisations have been shown to contain information related to animal welfare and behaviour. Automated sound detection has the potential to facilitate a continuous acoustic monitoring system, for use in a range Precision Livestock Farming (PLF) applications. There are few examples of automated livestock vocalisation classification algorithms, and we have found none capable of being easily adapted and applied to different species’ vocalisations. In this work, a multi-purpose livestock vocalisation classification algorithm is presented, utilising audio-specific feature extraction techniques, and machine learning models. To test the multi-purpose nature of the algorithm, three separate data sets were created targeting livestock-related vocalisations, namely sheep, cattle, and Maremma sheepdogs. Audio data was extracted from continuous recordings conducted on-site at three different operational farming enterprises, reflecting the conditions of real deployment. A comparison of Mel-Frequency Cepstral Coefficients (MFCCs) and Discrete Wavelet Transform-based (DWT) features was conducted. Classification was determined using a Support Vector Machine (SVM) model. High accuracy was achieved for all data sets (sheep: 99.29%, cattle: 95.78%, dogs: 99.67%). Classification performance alone was insufficient to determine the most suitable feature extraction method for each data set. Computational timing results revealed the DWT-based features to be markedly faster to produce (14.81 – 15.38% decrease in execution time). The results indicate the development of a highly accurate livestock vocalisation classification algorithm, which forms the foundation for an automated livestock vocalisation detection system.

Precision livestock management has become a new field of study as the result of recent advancements in real-time global positioning system (GPS) tracking, accelerometer and other sensor technologies. Real-time tracking and accelerometer monitoring has the potential to remotely detect livestock disease, animal well-being and grazing distribution issues and notify ranchers and graziers so that they can respond as soon as possible. On-going research has shown that accelerometers can remotely monitor livestock behavior and detect activity changes that are associated with disease and parturition. GPS tracking can also detect parturition by monitoring the distance between a ewe and the remainder of the flock. Tracking also has the potential to detect water system failures. Combinations of GPS tracking and accelerometer monitoring may be more accurate than either device used by itself. Real-time GPS tracking can identify when livestock congregate in environmental sensitive areas which may allow managers the chance to respond before resource degradation occurs. Identification of genetic markers associated with terrain use, decreased cost of GPS tracking and novel tracking data processing should facilitate development of tools needed for genetic selection for cattle grazing distribution. Precision livestock management has potential to improve welfare of livestock grazing rangelands and forested lands, reduce labor costs and improve ranch profitability and improve the condition and sustainability of riparian areas and other environmental sensitive areas on grazing lands around the world.

Livestock production in rangeland environments is often fraught with numerous challenges that can limit regular human-animal interaction. As such, cattle in these environments can remain unmonitored for days or months at a time. The integration of on-animal sensing systems in these environments could provide a means for producers to remotely monitor their animals without incurring the significant labour costs associated with manually checking on their livestock. These devices could be used to monitor critical times in a cow’s life, such as calving. Parturition represents a high-risk period in both a cow and calf’s life, where the risk of disease or death is greatly increased. Additional monitoring in this period is beneficial, such that any complications can be promptly detected and managed. On-animal sensing systems could be used to identify when or if calving has successfully occurred and to infer the status of the calf in the first few months of life. For a precise and well-integrated system to be developed, there needs to be a greater understanding of the data required at each stage. This study will provide a conceptual overview and systems design outlining how an on-animal sensor system could be used to detect calving and calf status and provide updates to the producer in the event of complications. This research is funded by Central Queensland University, Meat and Livestock Australia, and Telstra.

Behaviour is a useful indicator of an individual animal’s overall wellbeing. There is widespread agreement that measuring and monitoring individual behaviour autonomously can provide valuable opportunities to trigger and refine on-farm management decisions. Conventionally, this has required visual observation of animals across a set time period. Technological advancements, such as animal-borne accelerometers, are offering 24/7 monitoring capability. Accelerometers have been used in research to quantify animal behaviours for a number of years. Now, technology and software developers, and more recently decision support platform providers, are integrating to offer commercial solutions for the extensive livestock industries. For these systems to function commercially, data must be captured, processed and analysed in sync with data acquisition. Practically, this requires a continuous stream of data or a duty cycled data segment and, from an analytics perspective, the application of moving window algorithms to derive the required classification. The aim of this study was to evaluate the application of a ‘clean state’ moving window behaviour state classification algorithm applied to 3, 5 and 10 second duration segments of data (including behaviour transitions), to categorise data emanating from collar, leg and ear mounted accelerometers on five Merino ewes. The model was successful at categorising grazing, standing, walking and lying behaviour classes with varying sensitivity, and no significant difference in model accuracy was observed between the three moving window lengths. The accuracy in identifying behaviour classes was highest for the ear-mounted sensor (86%–95%), followed by the collar-mounted sensor (67%–88%) and leg-mounted sensor (48%–94%). Between-sheep variations in classification accuracy confirm the sensor orientation is an important source of variation in all deployment modes. This research suggests a moving window classifier is capable of segregating continuous accelerometer signals into exclusive behaviour classes and may provide an appropriate data processing framework for commercial deployments.

Over the last 20 yr, global positioning system (GPS) collars have greatly enhanced livestock grazing behavior research. Practices designed to improve livestock grazing distribution can now be accurately and cost effectively monitored with GPS tracking. For example, cattle use of feed supplement placed in areas far from water and on steep slopes can be measured with GPS tracking and corresponding impacts on distribution patterns estimated. Ongoing research has identified genetic markers that are associated with cattle spatial movement patterns. If the results can be validated, genetic selection for grazing distribution may become feasible. Tracking collars have become easier to develop and construct, making them significantly less expensive, which will likely increase their use in livestock grazing management research. Some research questions can be designed so that dependent variables are measured by spatial movements of livestock, and in such cases, GPS tracking is a practical tool for conducting studies on extensive and rugged rangeland pastures. Similarly, accelerometers are changing our ability to monitor livestock behavior. Today, accelerometers are sensitive and can record movements at fine temporal scales for periods of weeks to months. The combination of GPS tracking and accelerometers appears to be useful tools for identifying changes in livestock behavior that are associated with livestock diseases and other welfare concerns. Recent technological advancements may make real-time or near real-time tracking on rangelands feasible and cost-effective. This would allow development of applications that could remotely monitor livestock well-being on extensive rangeland and notify ranchers when animals require treatment or other management.

We investigated relationship between pasture biomass and measures of height and NDVI (normalised difference vegetation index). The pastures were tall fescue (Festuca arundinacea), perennial ryegrass (Lolium perenne), and phalaris (Phalaris aquatica) located in Tasmania, Victoria and in the Northern Tablelands of NSW, Australia. Using the Trimble® GreenSeeker® Handheld active optical sensor (AOS) to measure NDVI, and a rising plate meter, the optimal model to estimate green dry biomass (GDM) during two years was a combination of NDVI and falling plate height index. The combined index was significantly correlated with GDM in each region during winter and spring (r2=0.62–0.77, P

Whilst agriculture is Australia’s fastest growing industry, the negative perception of career opportunities by high school students and the lack of educator confidence in teaching about food and fibre concepts is a major issue currently faced by the sector. The Teacher Farm Experience (TeacherFX), a joint program of Rabobank’s Western Australia Client Council and CQUniversity Australia, aims to increase awareness, knowledge and appreciation of the agricultural industry. This free two-day program designed for teachers entailed visiting four farms in the Great Southern region of WA on the first day and professional learning on the second day. Pre- and post- event surveys were conducted to gain baseline information on the participants, their perceptions of agriculture, quality of learning materials and reaction to the experience. Additional support in the form of professional development and networking opportunities was identified as required to assist teachers to implement learnings from TeacherFX. Event survey results were overwhelmingly positive, with 100% of teachers recommending their colleagues attend a future event. However, whether this positive result will translate to change in the classroom is unknown. Additional research needs to be conducted to measure the long-term impact of the program.

Within the agriculture sector the use of digital technologies is rapidly expanding. There is a growing shortage of skilled people considering a career within this sector to support the uptake of agricultural technology. The GPS Cows program is designed to improve secondary school student’s knowledge and skills of emerging agricultural technologies. It highlights a range of opportunities and potential career options available to students in agriculture. This collaborative project combines the expertise and passion of researchers, industry professionals and educators in both Australia and the USA. A pilot workshop was run with ten teachers from nine Queensland and New South Wales secondary schools. Teachers participated in lectures and practical workshops, developed data analysis skills and took part in a World Café style focus group. The focus group findings highlighted that for the GPS Cows program to be implemented in secondary school classrooms, excellent resources from the GPS Cows team are needed, combined with ongoing support and guidance. Nevertheless, the participating teachers felt that their students would both engage and enjoy participating in the GPS Cows program and realise the opportunities the agricultural sector offers.

In the current study, a simulated online parturition detection model is developed and reported. Using a machine learning (ML)-based approach, the model incorporates data from Global Navigation Satellite System (GNSS) tracking collars, accelerometer ear tags and local weather data, with the aim of detecting parturition events in pasture-based sheep. The specific objectives were two-fold: (i) determine which sensor systems and features provide the most useful information for lambing detection, (ii) evaluate how these data might be integrated using ML classification to alert to a parturition event as it occurs. Two independent field trials were conducted during the 2017 and 2018 lambing seasons in New Zealand, with the data from each used for ML training and independent validation, respectively. Based on objective (i), four features were identified as exerting the greatest importance for lambing detection: mean distance to peers (MDP), MDP compared to the flock mean (MDP.Mean), closest peer (CP) and posture change (PC). Using these four features, the final ML was able to detect 27% and 55% of lambing events within ±3 h of birth with no prior false positives. If the model sensitivity was manipulated such that earlier false positives were permissible, this detection increased to 91% and 82% depending on the requirement for a single alert, or two consecutive alerts occurring. To identify the potential causes of model failure, the data of three animals were investigated further. Lambing detection appeared to rely on increased social isolation behaviour in addition to increased PC behaviour. The results of the study support the use of integrated sensor data for ML-based detection of parturition events in grazing sheep. This is the first known application of ML classification for the detection of lambing in pasture-based sheep. Application of this knowledge could have significant impacts on the ability to remotely monitor animals in commercial situations, with a logical extension of the information for remote monitoring of animal welfare.

Simple Summary Monitoring livestock farmed under extensive conditions is challenging and this is particularly difficult when observing animal behaviour at an individual level. Lameness is a disease symptom that has traditionally relied on visual inspection to detect those animals with an abnormal walking pattern. More recently, accelerometer sensors have been used in other livestock industries to detect lame animals. These devices are able to record changes in activity intensity, allowing us to differentiate between a grazing, walking, and resting animal. Using these on-animal sensors, grazing, standing, walking, and lame walking were accurately detected from an ear attached sensor. With further development, this classification algorithm could be linked with an automatic livestock monitoring system to provide real time information on individual health status, something that is practically not possible under current extensive livestock production systems. Abstract Lameness is a clinical symptom associated with a number of sheep diseases around the world, having adverse effects on weight gain, fertility, and lamb birth weight, and increasing the risk of secondary diseases. Current methods to identify lame animals rely on labour intensive visual inspection. The aim of this current study was to determine the ability of a collar, leg, and ear attached tri-axial accelerometer to discriminate between sound and lame gait movement in sheep. Data were separated into 10 s mutually exclusive behaviour epochs and subjected to Quadratic Discriminant Analysis (QDA). Initial analysis showed the high misclassification of lame grazing events with sound grazing and standing from all deployment modes. The final classification model, which included lame walking and all sound activity classes, yielded a prediction accuracy for lame locomotion of 82%, 35%, and 87% for the ear, collar, and leg deployments, respectively. Misclassification of sound walking with lame walking within the leg accelerometer dataset highlights the superiority of an ear mode of attachment for the classification of lame gait characteristics based on time series accelerometer data.

Here, a Web of Things case study for agriculture focuses on an experimental smart farm that uses a range of environmental sensors and livestock monitoring technologies. An ontology-enabled architecture that permits personal alert specification was applied on the farm and the results analyzed; the observations are published as a linked data cube, which supports longer-term analysis and data sharing from a local to national scale. This case study highlights the business opportunities for such technology for agriculture in the context of a national broadband rollout.

The predation of sheep (Ovis aries) by wild and domestic dogs (Canis lupis) is a major issue in Australia, causing serious welfare issues to inflicted animals. The estimated cost of sheep and cattle production losses caused by wild dogs when combined with an extensive range of control measures, costs the Australian economy AU$66 million annually. Spatio-temporal data derived from global navigation satellite system (GNSS) devices were used to quantify the behavioural responses of two flocks of 15 Merino ewes ranging from 2 to 8 years old (average 4.5 years) during simulated dog predation events. Each sheep was fitted with a GNSS collar, and the behavioural responses of the sheep were video recorded during six trials (three per flock). The behavioural data collated from video recordings were then compared with the movement metrics derived from the GNSS collars. Derived metrics include the spatial distribution of flock members, speed of animal movement and specific behavioural changes including centripetal rotation (circling behaviour of the flock, with individual sheep seeking the centre). While the spatial distribution data did not appear to be specific enough to enable identification of a predation event, the velocity of sheep was higher (P < 0.001) during compared with before and after a simulated dog predation event. Centripetal rotation occurred in 80% of the simulated predation events during this study, and may provide a means for identifying predation. The spatio-temporal data from GNSS devices have potential as a research tool to assist in understanding sheep movement patterns during a dog attack. While further research and mathematical modelling of predation events is clearly required, the application of remote sensing technology has the potential to improve future livestock monitoring.