Greg Bishop-Hurley

Transforming Agriculture through Pervasive Wireless Sensor Networks

A large-scale, outdoor pervasive computing system uses static and animal-borne nodes to measure the state of a complex system comprising climate, soil, pasture, and animals. Agriculture faces many challenges, such as climate change, water shortages, labor shortages due to an aging urbanized population, and increased societal concern about issues such as animal welfare, food safety, and environmental impact. Humanity depends on agriculture and water for survival, so optimal, profitable, and sustainable use of our land and water resources is critical.

Monitoring Animal Behaviour and Environmental Interactions Using Wireless Sensor Networks, GPS Collars and Satellite Remote Sensing

Remote monitoring of animal behaviour in the environment can assist in managing both the animal and its environmental impact. GPS collars which record animal locations with high temporal frequency allow researchers to monitor both animal behaviour and interactions with the environment. These ground-based sensors can be combined with remotely-sensed satellite images to understand animal-landscape interactions. The key to combining these technologies is communication methods such as wireless sensor networks (WSNs). We explore this concept using a case-study from an extensive cattle enterprise in northern Australia and demonstrate the potential for combining GPS collars and satellite images in a WSN to monitor behavioural preferences and social behaviour of cattle.

Wireless ad hoc sensor and actuator networks on the farm

Agriculture accounts for a significant portion of the GDP in most developed countries. However, managing farms, particularly large-scale extensive farming systems, is hindered by lack of data and increasing shortage of labour. We have deployed a large heterogeneous sensor network on a working farm to explore sensor network applications that can address some of the issues identified above. Our network is solar powered and has been running for over 6 months. The current deployment consists of over 40 moisture sensors that provide soil moisture profiles at varying depths, weight sensors to compute the amount of food and water consumed by animals, electronic tag readers, up to 40 sensors that can be used to track animal movement (consisting of GPS, compass and accelerometers), and 20 sensor/actuators that can be used to apply different stimuli (audio, vibration and mild electric shock) to the animal. The static part of the network is designed for 24/7 operation and is linked to the Internet via a dedicated high-gain radio link, also solar powered. The initial goals of the deployment are to provide a testbed for sensor network research in programmability and data handling while also being a vital tool for scientists to study animal behavior. Our longer term aim is to create a management system that completely transforms the way farms are managed

Animal Behaviour Understanding using Wireless Sensor Networks

This paper presents research that is being conducted by the Commonwealth Scientific and Industrial Research Organisation (CSIRO) with the aim of investigating the use of wireless sensor networks for automated livestock monitoring and control. It is difficult to achieve practical and reliable cattle monitoring with current conventional technologies due to challenges such as large grazing areas of cattle, long time periods of data sampling, and constantly varying physical environments. Wireless sensor networks bring a new level of possibilities into this area with the potential for greatly increased spatial and temporal resolution of measurement data. CSIRO has created a wireless sensor platform for animal behaviour monitoring where we are able to observe and collect information of animals without significantly interfering with them. Based on such monitoring information, we can identify each animals behaviour and activities successfully

Dynamic cattle behavioural classification using supervised ensemble classifiers

Cattle behavioural classification using cattle tag and supervised ensemble classifiers.Unsupervised hybrid clustering used to study inherent natural grouping in data set.Best classification accuracy was 96% using the bagging ensemble with Tree learner.A mechanism for the early detection and quantitative assessment of animal health. In this paper various supervised machine learning techniques were applied to classify cattle behaviour patterns recorded using collar systems with 3-axis accelerometer and magnetometer, fitted to individual dairy cows to infer their physical behaviours. Cattle collar data was collected at the Tasmanian Institute of Agriculture (TIA) Dairy Research Facility in Tasmania. In the first stage of analysis a novel hybrid unsupervised clustering framework, comprised of probabilistic principal component analysis, Fuzzy C Means, and Self Organizing Map network algorithms was developed and used to study the natural structure of the sensor data. Findings from this unsupervised clustering were used to guide the next stage of supervised machine learning. Five major behaviour classes, namely, Grazing, Ruminating, Resting, Walking, and other behaviour were identified for the classification trials. An ensemble of classifiers approach was used to learn models of cow behaviour using sensor data and ground truth behaviour observations acquired from the field. Ensemble classification using bagging, Random Subspace and AdaBoost methods along with conventional supervised classification methods, namely, Binary Tree, Linear Discriminant Analysis classifier, Naive Bayes classifier, k-Nearest Neighbour classifier, and Adaptive Neuro Fuzzy Inference System classifier were compared. The highest average correct classification accuracy of 96% was achieved using the bagging ensemble classification with Tree learner, which had 97% sensitivity, 89% specificity, 89% F1 score and 9% false discovery rate. This study has shown that cattle behaviours can be classified with a high accuracy using supervised machine learning technique. As dairy and beef systems become more intensive, the ability to identify the changes in the behaviours of individual livestock becomes increasingly difficult. Accurate behavioural monitoring through sensors provides a significant potential in providing a mechanism for the early detection and quantitative assessment of animal health issues such a lameness, informing key management events such as the identification of oestrus, or informing changes in supplementary feeding requirements.

Measuring Methane Production from Ruminants

Radiative forcing of methane (CH4) is significantly higher than carbon dioxide (CO2) and its enteric production by ruminant livestock is one of the major sources of greenhouse gas emissions. CH4 is also an important marker of farming productivity, because it is associated with the conversion of feed to product in livestock. Consequently, measurement of enteric CH4 is emerging as an important research topic. In this review, we briefly describe the conversion of carbohydrate to CH4 by the bacterial community within gut, and highlight some of the key host-microbiome interactions. We then provide a picture of current progress in techniques for measuring enteric CH4, the context in which these technologies are used, and the challenges faced. We also discuss solutions to existing problems and new approaches currently in development.

Determining the effect of stocking rate on the spatial distribution of cattle for the subtropical savannas

With the commercial development of the global positioning system (GPS), it is now possible to monitor the distribution of free ranging cattle and derive measures to describe landscape use. Animal GPS data can be integrated with a geographic information system (GIS) detailing topography, vegetation, soil type and other landscape features. Combining GPS and GIS information is useful for understanding how animals respond to spatial variability. This study quantified land-type preferences for Brahman cross steers over three time periods, from October 2004 to March 2006 in a replicated trial, under heavy (4 ha/AE; animal equivalent of ~450 kg steer) and light (8 ha/AE) stocking in four, ~105 ha paddocks of subtropical semi-arid savanna near Charters Towers, Queensland, Australia. The grazing trail was conducted at a scale much less than would be found in commercial situations. Consequently, the spatial pattern of cattle reported here may not represent what occurs at a commercial scale and implications are discussed. Results were analysed in terms of the spatial distribution of steers fitted with GPS devices in each of the four paddocks and for each stocking rate to provide insight into cattle distribution and land-type preferences. Steers walked in excess of 6 km per day, regardless of stocking rate, and exhibited diurnal patterns of movement, with peak activity around dawn (0500–0700 hours) and dusk (1800–2000 hours). The spatial distribution of the collared steers was not uniform and appeared to be strongly influenced by the prevailing drought conditions and location of water points within each paddock. A hierarchy of drivers for distribution was identified. With the exception of drinking water location, land subtype based on soil-vegetation associations influenced animal distribution. Preference indices (ŵi) indicated that steers selected sites associated with heavy clay and texture contrast soils dominated by Eucalyptus coolabah Blakely & Jacobs (ŵi = 5.33) and Eucalyptus brownii Maiden & Cambage (ŵi = 3.27), respectively, and avoiding Eucalyptus melanophloia F.Muell. ridges (ŵi = 0.26) and Eucalyptus cambageana Maiden (ŵi = 0.12) on sodosols. The results suggest that spatial variation in cattle distribution within a paddock may be more critical than overall stocking rate in influencing the pattern of biomass utilisation. However, to quantifying the effects of different grazing land management practices on animal distribution on a commercial scale, additional studies in extensive paddocks are required.

Bag of Class Posteriors, a new multivariate time series classifier applied to animal behaviour identification

A new multi-scale time series classifier is proposed using class posterior estimates.The classifier infers a large set of animal behaviour using motion based time series.The proposed classifier outperforms benchmark classifiers by between 43% and 77%.The proposed classifier is found to be more efficient than the Bag of Features model. In this paper, two new multivariate time series classifiers are introduced as the Bag of Class Posteriors (BOCP) and the Bag of Class Posterior with Ordering (BOCPO). The models propose a new multi-scale feature representation where the class posterior estimates of contiguous local patterns are aggregated over longer time scales. The models are employed as part of an animal behaviour monitoring system that are comprised of sensors, which are fitted to the animals, and a classifier that translates sensor data into knowledge of the animals behaviour.Animal monitoring systems are commonly developed to infer a small number of behaviours with relevance to a specific application. To investigate if a standard monitoring system with an Inertial Measurement Unit (IMU) can be reused for different management applications, a set of ten cattle behaviours relevant to different management applications were classified with the proposed models. Results indicate that the multi-scale BOCP and BOCPO models were far more capable of classifying the cow behaviours offering a 43% to 77% improvement over benchmark time interval classifiers with fixed time resolution. In addition, the BOCPO model was shown to offer a far more efficient feature representation than the related multi-scale Bag of Features (BOF) classifier (up to 200 times smaller) making it better suited to deploy upon monitoring devices fitted to animals in the field.

Evaluating dispersion modeling options to estimate methane emissions from grazing beef cattle.

Enteric methane (CH) emission from cattle is a source of greenhouse gas and is an energy loss that contributes to production inefficiency for cattle. Direct measurements of enteric CH emissions are useful to quantify the magnitude and variation and to evaluate mitigation of this important greenhouse gas source. The objectives of this study were to evaluate the impact of stocking density of cattle and source configuration (i.e., point source vs. area source and elevation of area source) on CH emissions from grazing beef cattle in Queensland, Australia. This was accomplished using nonintrusive atmospheric measurements and a gas dispersion model. The average measured CH emission for the point and area source was between 240 and 250 g animal d over the entire study. There was no difference ( > 0.05) in emission when using an elevated area source (0.5 m) or a ground area source (0 m). For the point-source configuration, there was a difference in CH emission due to stocking density; likewise, some differences existed for the area-source emissions. This study demonstrates the flexibility of the area-source configuration of the dispersion model to estimate CH emissions even at a low stocking density.

Detecting heat events in dairy cows using accelerometers and unsupervised learning

We developed a heat detection algorithm for pasture-based dairy cows.Our algorithm uses data from accelerometer attached to the cow collars.We present the overall accuracy of 82-100% with 100% sensitivity. This study was conducted to investigate the detection of heat events in pasture-based dairy cows fitted with on-animal sensors using unsupervised learning. Accelerometer data from the cow collars were used to identify increased activity levels in cows associated with recorded heat events. Time series data from the accelerometers were first segmented into windows before features were extracted. K-means clustering algorithm was then applied across the windows for grouping. The groups were labelled in terms of their activity intensity: high, medium and low. An activity index level (AIxL) was then derived from a count of activity intensity labels over time. Change detection techniques were then applied on AIxL to find very high activity events. Detected events in AIxL were compared with recorded heat events and observed significant associations between the increased activities through high AIxL values and the observed heat events. We achieved overall accuracy of 82-100% with 100% sensitivity when change detection technique is applied to activity index level.