Pen parameters for improving the performance of sheep imported from Australia to Persian Gulf feedlots

Summer in the Persian Gulf region presents physiological challenges for Australian sheep that are part of the live export supply chain coming from the Australian winter. Many feedlots throughout the Gulf have very high numbers of animals during June to August in order to cater for the increased demand for religious festivals. From an animal welfare perspective it is important to understand the necessary requirements of feed and water trough allowances, and the amount of pen space required, to cope with exposure to these types of climatic conditions. This study addresses parameters that are pertinent to the wellbeing of animals arriving in the Persian Gulf all year round. Three experiments were conducted in a feedlot in the Persian Gulf between March 2010 and February 2012, totalling 44 replicate pens each with 60 or 100 sheep. The applied treatments covered animal densities, feed-bunk lengths and water trough lengths. Weights, carcass attributes and health status were the key recorded variables. Weight change results showed superior performance for animal densities of ≥1.2 m2/head during hot conditions (24-h average temperatures greater than 33 °C, or a diurnal range of around 29–37 °C). However the space allowance for animals can be decreased, with no demonstrated detrimental effect, to 0.6 m2/head under milder conditions. A feed-bunk length of ≥5 cm/head is needed, as 2 cm/head showed significantly poorer animal performance. When feeding at 90% ad libitum 10 cm/head was optimal, however under a maintenance feeding regime (1 kg/head/day) 5 cm/head was adequate. A minimum water trough allowance of 1 cm/head is required. However, this experiment was conducted during milder conditions, and it may well be expected that larger water trough lengths would be needed in hotter conditions. Carcass weights were determined mainly by weights at feedlot entry and subsequent weight gains, while dressing percentage was not significantly affected by any of the applied treatments. There was no demonstrated effect of any of the treatments on the number of animals that died, or were classified as unwell. However, across all the treatments, these animals lost significantly more weight than the healthy animals, so the above recommendations, which are aimed at maintaining weight, should also be applicable for good animal health and welfare. Therefore, best practice guidelines for managing Australian sheep in Persian Gulf feedlots in the hottest months (June–August) which present the greatest environmental and physical challenge is to allow feed-bunk length 5 cm/head on a maintenance-feeding program and 10 cm/head for 90% ad libitum feeding, and the space allowance per animal should be ≥1.2 m2/head. Water trough allocation should be at least 1 cm/head with provision for more in the summer when water intake potentially doubles.

Automating Crop Damage Assessments with Unmanned Aerial Systems and Machine Learning

Agricultural pests are responsible for millions of dollars in crop losses and management costs every year. In order to implement optimal site-specific treatments and reduce control costs, new methods to accurately monitor and assess pest damage need to be investigated. In this paper we explore the combination of unmanned aerial vehicles (UAV), remote sensing and machine learning techniques as a promising methodology to address this challenge. The deployment of UAVs as a sensor platform is a rapidly growing field of study for biosecurity and precision agriculture applications. In this experiment, a data collection campaign is performed over a sorghum crop severely damaged by white grubs (Coleoptera: Scarabaeidae). The larvae of these scarab beetles feed on the roots of plants, which in turn impairs root exploration of the soil profile. In the field, crop health status could be classified according to three levels: bare soil where plants were decimated, transition zones of reduced plant density and healthy canopy areas. In this study, we describe the UAV platform deployed to collect high-resolution RGB imagery as well as the image processing pipeline implemented to create an orthoimage. An unsupervised machine learning approach is formulated in order to create a meaningful partition of the image into each of the crop levels. The aim of this approach is to simplify the image analysis step by minimizing user input requirements and avoiding the manual data labelling necessary in supervised learning approaches. The implemented algorithm is based on the K-means clustering algorithm. In order to control high-frequency components present in the feature space, a neighbourhood-oriented parameter is introduced by applying Gaussian convolution kernels prior to K-means clustering. The results show the algorithm delivers consistent decision boundaries that classify the field into three clusters, one for each crop health level as shown in Figure 1. The methodology presented in this paper represents a venue for further esearch towards automated crop damage assessments and biosecurity surveillance.