Search

Highlights • Novel transport model with unprecedented large number of variables affecting cost and time. • High flexibility to accommodate a variety of transport supply chains. • Strong link to GIS allowing for spatial mapping of transport movements. • National scale application for entire industry sectors. • Tested in various case studies which analyse road upgrades, flood events and use of rail. Abstract Transport infrastructure is essential to moving over 85 million tonnes of agricultural products and 30 million cubic metres of timber from farms and production areas to domestic and international markets each year in Australia. Agriculture supply chains in Australia are characterised by long distances with transport costs accounting for up to 40 percent of the market price. Targeted infrastructure investment and/or regulatory changes can substantially reduce transport-related logistics costs. To provide a comprehensive view of transport logistics costs and benefits due to infrastructure investments and regulatory changes in agriculture and forestry supply chains, CSIRO developed a computer-based tool – the Transport Network Strategic Investment Tool (TraNSIT). TraNSIT optimises transport routes for upto hundreds of thousands of enterprises and millions of vehicle trips between farms and their markets, providing information on routing to maximise cost efficiencies. Through an Australian Government initiative, TraNSIT was applied to over 30 commodities representing 98% of Australian agricultural and plantation forestry volume transported by road and rail. TraNSIT is now a comprehensive logistics tool that has been applied to the largest agricultural supply chain dataset ever assembled in Australia. This paper provides an overview of TraNSIT, its adaptation to agriculture and forestry logistics as part of the project, and its application to several case studies in Australia including new road links, rail versus road and flooding. [ABSTRACT FROM AUTHOR]

Queensland grazing industries operate in one of the world’s most variable climates and face enormous challenges to achieve profitability and sustainability. To assist grazing enterprises, the Queensland Government has developed an operational online information system – FORAGE, to facilitate best management practice for grazing land. The FORAGE system provides land managers with property-scale information relating to rainfall, ground cover, soil erodibility, land types, tree density, seasonal climate outlooks and pasture growth simulated using the GRASP grazing system model. This information is site-specific and tailored to facilitate on-ground management decisions common to Queensland grazing enterprises. The FORAGE system makes complex remotely-sensed data, information from a range of databases and pasture growth models more accessible and relevant to land managers. This paper describes the structure, resources (e.g. software, databases and models), information generating processes, delivery mechanisms and information products of the FORAGE system. [ABSTRACT FROM AUTHOR]

Australia’s agriculture industry, particularly in the north, is characterised by supply chains of long travel distances, often in excess of 2500 km and costing up to 35% of farm gate price. Such travel distances increase the vulnerability of the industry to climatic variability and extreme events. Infrastructure investments in roads, bridges, processors and storage, along with changes in policy, have the potential to substantially reduce costs and increase resilience of the agriculture industries. In this paper, we outline the model, TRAnsport Network Strategic Investment Tool (TRANSIT) which is based on ArcGIS, and utilizes the Origin to Destination Cost Matrix solver within the Network Analyst toolkit. TRANSIT estimates the transport costs for all movements between enterprises, accommodating road conditions, vehicle types, vehicle access restrictions and regulatory requirements. TRANSIT was applied to the northern Australia livestock industry, consisting of 12 million cattle across 10,000 enterprises and 89,000 unique trips between these enterprises. Its ability to estimate the transport benefits from road upgrades, new processing facilities and biosecurity changes are shown using three priority case studies identified by industry and government. [ABSTRACT FROM AUTHOR]

• Blockchain-enabled traceability prototype, including texts, messages and a one-minute video is developed with Australian producers and processors with the aim of improving consumer trust in the cross-border beef supply chain between Australia and China. • The initial traceability prototype is empirically tested with Chinese consumers using focus group discussion methodology. • Empirical evidence from the prototype testing and the insights from supply chain stakeholder are integrated to propose a new feature for trust strength. • A human-machine reconcile mechanism is developed to enable readably chain-wide shared responsibilities in delivering credentialed traceability data to consumers so as to increase consumer trust because just blockchain itself will not cut-it. This study aimed to strengthen trust in the cross-border beef supply chain between Australia and China from a consumer perspective based on a blockchain-based supply chain implementation. Using a design science approach, this study's initial prototype was developed to strength consumer trust. The study was conducted in partnership with Australian agricultural producers and processors, and empirically tested with Chinese consumers using an exploratory, qualitative methodology comprising focus groups. Based on the empirical evidence from prototype testing and the insights from supply chain stakeholders, this paper explores new features for a human-machine reconcile mechanism that enables shared responsibilities between agriculture and supply chain actors in delivering credentialed traceability data to consumers along the Australia-China beef supply chain. [ABSTRACT FROM AUTHOR]

This paper aims to assess the performance of generalized aboveground biomass (AGB) allometric models in the Australian context by investigating the correlation between the AGB estimates and the lidar-based individual tree parameters. A hybrid tree segmentation algorithm is proposed to segment an airborne lidar point cloud into individual trees. Although the diameter at breast height (DBH) of a tree is a crucial parameter for the AGB estimation, a typical airborne lidar data contains only a few points representing partial DBH, hence a localized DBH regression model is proposed. Principal component analysis is applied to examine the multicollinearity in the input variables and ridge regression is applied to remove the less important variables. Four machine learning techniques, namely random forest, support vector regression, multilayer perceptron and radial basis function, are applied to generate AGB regression models. The qualities of the calibrated AGB models are assessed by calculating the adjusted-coefficient-of-determination, leave-one-out cross-validation, the Akaike information criterion, normalized-mean-square-error and the model efficiency index. The test results indicate that the random forest-based AGB model outperforms other machine learning techniques. It is concluded that, if the environmental conditions of tree samples resemble the study region, the generalized AGB allometric model would perform well with the tree samples regardless of their geographical context. [ABSTRACT FROM AUTHOR]

• Data-driven approaches to study physiological response of sentinel oysters to environmental condition. • Predicting heart rate and shell gape of oysters from environmental water quality variables. • Predicting water quality variables from heart rate and shell gape of oysters. • Application of machine learning models to provide a biological perspective of environmental changes. The research presented in this paper was conducted as part of a project that aimed at using biosensors on sentinel oysters to provide a biological perspective of environmental changes. The physiological response patterns (e.g. heart rate variability, shell gape) of sentinel oysters can provide valuable insight into their exposure to environmental stressors. Sensors were attached to measure both heart rate and shell gape (physiological behaviour) of oysters placed at different depths in the water column. Sensors were also deployed to measure water quality that represents the environmental condition the oysters were in. The objective of this study is to utilise the data from different sensors to investigate how environmental conditions modulate physiological response of oysters. We have utilised a set of machine learning models to develop data-driven approaches that can predict heart rate and shell gape (opening and closing action) of oysters from water quality variables, and vice-versa. The level of prediction accuracy indicates how well environmental conditions influence the physiological response of oysters. The effectiveness of the developed approaches is evaluated using data collected from two different deployments of sensors in South East Tasmania, Australia. Experimental results demonstrate that the presented data-driven approaches can provide accurate predictions of physiological and water quality variables, for the data set considered in this study. The prediction error (in terms of MAPE) for HR and water quality is in the range of 3.17%-8.21% and 0.72%–2.48%, respectively, and classification accuracy (F-Score) for shell gape varies between 0.96 and 0.99. [ABSTRACT FROM AUTHOR]

• Ultrasound technique detects the internal defects such as branch traces and knots. • Ultrasound signals are affected more by defects in billets compared to clear wood. • Ultrasound signals also affected by high moisture content in billets. • Higher moisture content in billet with defect is detected compared to clear wood. • Ultrasound technique is an effective method for internal defect detection. Effective non-destructive methods for identifying poor quality and knotty timber in standing trees can contribute to higher quality timber reaching the appropriate processing mills and to a reduction in transport costs of harvested timber. Eucalyptus nitens is a major temperate plantation hardwood species primarily used in paper production. More recently it has also been considered as a potentially suitable source to produce high quality sawlogs. One important aspect of the economic viability of this sawlog business is being able to differentiate between pruned (higher quality) and unpruned (lower quality) plantation eucalyptus. Low quality stems contain higher percentages of features such as knots and/or branch traces that lessen the quality and value of logs that can be produced. Unfortunately, it is not possible to visually discriminate between pruned and unpruned standing trees and while wood processors do use large x-ray image machines during processing, finding ways to reduce transportation costs by enhancing timber quality remains a major challenge. This research presents results from ultrasonic and thermal testing to non-destructively detect internal defects in 17 year old E. nitens grown in Tasmania, Australia. For the investigation, 12 samples (billets) from different parts of the trunk of an E. nitens tree were selected and conditioned to levels of forest moisture content of 120% (70% water content). The samples were scanned by two ultrasonic techniques through-transmission and pulse-echo. In the through-transmission method, the waves were propagated at 10 cm intervals in the longitudinal direction and at 45 degree angle spacing in the circumferential direction. In the pulse-eco method, the surface of the billets were scanned in 10cms intervals around the billets. Unpruned billets were also evaluated for moisture content using a thermal camera to examine the effect on ultrasonic wave propagation. The ultrasound revealed significant differences between recorded ultrasonic waveforms propagated through unpruned billets and pruned ones. Unpruned billets produce a much larger effect on ultrasonic waves when compared with the waves propagated by the pruned billets tested. The thermal camera highlighted that wet knotty wood tends to have higher moisture content than clear wood except when the timber is air dried which produces a slightly lower moisture content being detected in knotty timber over clear wood. Results provide evidence that in-field non-destructive techniques for standing trees internal structural assessment are viable and could be operationalised within Tasmanian E. nitens plantations. [ABSTRACT FROM AUTHOR]