Yvette Everingham

Enhanced risk management and decision-making capability across the sugarcane industry value chain based on seasonal climate forecasts

Sugarcane industries worldwide are exposed to uncertainty associated with variable climate. This variability produces impacts across an integrated value chain comprising of the following industry sectors: cane growing, harvesting and transport, milling, and marketing. The purpose of this paper is to advocate a comprehensive systems approach for using seasonal climate forecast systems to improve risk management and decision-making capability across all sugarcane industry sectors. The application of this approach is outlined for decisions relating to yield forecasting, harvest management, and the use of irrigation. Key lessons learnt from this approach include the need for a participative R&D approach with stakeholders and the need to consider the whole industry value chain. Additionally, there is the need for climate forecast systems to target the varying needs of sugarcane industries.

Agricultural decision support systems facilitating co-learning: a case study on environmental impacts of sugarcane production

Decision support systems (DSSs) are one of the ways in which agricultural scientists have attempted to make agricultural systems science more accessible to farmers and to foster innovation. Recently, there has been a shift towards more participatory processes in development and application of DSSs to enhance their end-user use. Apart from increasing adoption, these participatory processes are also likely to enhance co-learning resulting from development/application of DSSs. Learning is a valuable process in increasing sustainability of natural resource management, so the application of DSSs in a learning context can make a contribution to the global challenges faced by agriculture. We developed a framework, using concepts drawn from social studies of science and technology, describing the phases of the participatory DSS development/application process and its likely outcomes. We analysed experiences of participants in a case study exploring more sustainable management of nitrogen fertilizer in sugarcane production in an environmentally sensitive area of northeastern Australia. The data illustrate theoretical constructs underpinning the framework and learning processes within the case study. The framework and case study results demonstrate the value of participatory DSS development/application as a co-learning process, an outcome not traditionally valued by agricultural DSS developers and one that is likely to help address the challenges faced by agricultural sustainability.

Advanced satellite imagery to classify sugarcane crop characteristics

Techniques that provide a rapid and widespread assessment of crop properties equip industry decision makers with knowledge to improve their farming environment, both tactically and strategically. An interdisciplinary approach that links the fields of hyperspectral remote sensing, statistical data mining and sugarcane systems was undertaken to establish new relationships to determine variety type and crop age of sugarcane plants. In contrast to commonly used sensors such as those occupied by Landsat satellites, images captured by hyperspectral sensors can provide a more detailed assessment of crop status. Appropriate statistical analysis methods are needed to decode the multifaceted information recorded in these hyperspectral images. A range of statistical approaches have been applied for analysis of an EO-1 hyperion hyperspectral image from a major sugarcane growing region in Australia. Two relatively new classification methods — support vector machines and random forests — demonstrated superior performance in classifying sugarcane variety and crop cycle, e.g. the number of times that the plant has grown back after harvest, when compared against traditional statistical methods. Assignment results were further enhanced when classifications of pixels within sugarcane paddocks were aggregated to paddock classifications using paddock boundary information. Whilst the analysis methods of the hyperspectral data have been tested for the classification of variety and crop cycle, the potential application arenas for this type of imagery is both extensive and relatively unexplored. This type of data coupled with appropriate analysis methods will play a vital role in futuristic sustainable agriculture practices as this imagery becomes more accessible and as land managers and researchers become more aware of the types of decisions that hyperspectral remote sensing data can aid.

Clustering noisy data in a reduced dimension space via multivariate regression trees

Cluster analysis is sensitive to noise variables intrinsically contained within high dimensional data sets. As the size of data sets increases, clustering techniques robust to noise variables must be identified. This investigation gauges the capabilities of recent clustering algorithms applied to two real data sets increasingly perturbed by superfluous noise variables. The recent techniques include mixture models of factor analysers and auto-associative multivariate regression trees. Statistical techniques are integrated to create two approaches useful for clustering noisy data: multivariate regression trees with principal component scores and multivariate regression trees with factor scores. The tree techniques generate the superior clustering results.

The human dimensions of wildlife tourism in a developing country: watching spinner dolphins at Lovina, Bali, Indonesia

The number of cetacean watching tourism operations in developing countries has doubled in the past decade. Practices are typically unregulated and not informed by research, especially research into the human dimensions of the tourist experience. Dolphin watching tourism at Lovina, Bali, started in the late 1980s when local fishers formed self-regulating cooperatives. Up to 180 dedicated operators use small fishing vessels to carry passengers to watch dolphins close to shore. Most tourists come from western countries, although the industry also attracts Asian visitors. Most visitors are tertiary-educated. Tourist satisfaction ranges from low to medium. While there was no significant difference between the average satisfaction of western and Asian tourists, the associated variables were different. The satisfaction of western tourists was associated with encounter management, preferred number of boats and the number of dolphins seen. Encounter management was the only variable associated with the satisfaction of Asian tourists. Satisfaction was positively associated with willingness to recommend the tour: western respondents who felt neutral to very comfortable with their dolphin encounters were more likely to promote the tour. Better understanding of the tourist experience is crucial in designing sustainable marine wildlife tourism in developing countries; such research appears to be rare.

Discriminating between the vocalizations of Indo-Pacific humpback and Australian snubfin dolphins in Queensland, Australia

Australian snubfin and Indo-Pacific humpback dolphins co-occur throughout most of their range in coastal waters of tropical Australia. Little is known of their ecology or acoustic repertoires. Vocalizations from humpback and snubfin dolphins were recorded in two locations along the Queensland coast during 2008 and 2010 to describe their vocalizations and evaluate the acoustic differences between these two species. Broad vocalization types were categorized qualitatively. Both species produced click trains burst pulses and whistles. Principal component analysis of the nine acoustic variables extracted from the whistles produced nine principal components that were input into discriminant function analyses to classify 96% of humpback dolphin whistles and about 78% of snubfin dolphin calls correctly. Results indicate clear acoustic differences between the vocal whistle repertoires of these two species. A stepwise routine identified two principal components as significantly distinguishable between whistles of each species: frequency parameters and frequency trend ratio. The capacity to identify these species using acoustic monitoring techniques has the potential to provide information on presence/absence, habitat use and relative abundance for each species.

Nitrogen Management Guidelines for Sugarcane Production in Australia: Can These Be Modified for Wet Tropical Conditions Using Seasonal Climate Forecasting?

Sugarcane is a highly valuable crop grown in tropical and subtropical climates worldwide primarily for the production of sucrose-based products. The Australian sugarcane industry is located in close proximity to sensitive environments and the apparent declining health of the Great Barrier Reef has been linked to damaging levels of land-based pollutants entering reef waters as a result of sugarcane cultivation undertaken in adjacent catchments. Unprecedented environmental scrutiny of N fertiliser application rates is necessitating improved N fertiliser management strategies in sugarcane. Over time the focus of N fertiliser management has shifted from maximising production to optimising profitability and most recently to improved environmental sustainability. However, current N calculations are limited in their ability to match N fertiliser inputs to forthcoming crop requirements. Seasonal climate forecasts are being used to improve decision-making capabilities across different sectors of the sugarcane value chain. Climate is a key driver of crop growth, N demand and N loss processes, but climate forecasts are not being used to guide N management strategies. Seasonal climate forecasts could be used to develop N management strategies for ‘wet’ and ‘dry’ years by guiding application rate, timing and/or frequency of N inputs and the benefit of using alternative forms of N fertiliser. The use of seasonal climate forecasts may allow more environmentally sensitive yet profitable N management strategies to be developed for the Australian sugarcane industry.

A Bayesian modelling approach for long lead sugarcane yield forecasts for the Australian sugar industry

For marketers, advance knowledge on sugarcane crop size permits more confidence in implementing forward selling, pricing, and logistics activities. In Australia, marketing plans tend to be initialised in December, approximately 7 months prior to commencement of the next harvest. Improved knowledge about crop size at such an early lead time allows marketers to develop and implement a more advanced marketing plan earlier in the season. Producing accurate crop size forecasts at such an early lead time is an on-going challenge for industry. Rather than trying to predict the exact size of the crop, a Bayesian discriminant analysis procedure was applied to determine the likelihood of a small, medium, or large crop across 4 major sugarcane-growing regions in Australia: Ingham, Ayr, Mackay, and Bundaberg. The Bayesian model considers simulated potential yields, climate forecasting indices, and the size of the crop from the previous year. Compared with the current industry approach, the discriminant procedure provided a substantial improvement for Ayr and a moderate improvement over current forecasting methods for the remaining regions, with the added advantage of providing probabilistic forecasts of crop categories.

Measuring and modelling CO2 effects on sugarcane

In order to fully capture the benefits of rising CO2 in adapting agriculture to climate change, we first need to understand how CO2 affects crop growth. Several recent studies reported unexpected increases in sugarcane (C4) yields under elevated CO2, but it is difficult to distinguish direct leaf-level effects of rising CO2 on photosynthesis from indirect water-related responses. A simulation model of CO2 effects, based purely on changes in stomatal conductance (indirect mechanism), showed transpiration was reduced by 30% (initially) to 10% (closed canopy) and yield increased by 3% even in a well-irrigated crop. The model incorporated the results of a field experiment, and a glasshouse experiment designed to disentangle the mechanisms of CO2 response: whole-plant transpiration and stomatal conductance were both 28% lower for plants growing with high-frequency demand-based watering at 720 vs 390?ppm CO2, but there was no increase in biomass, indicating that indirect mechanisms dominate CO2 responses in sugarcane. Novel glasshouse method separates direct and indirect effects of CO2 on crop growth.Novel modelling technique scales CO2 effects from glasshouse to field environments.Reduced transpiration under elevated CO2 accounts for sugarcane responses.Direct effects of elevated CO2 on sugarcane photosynthesis, if any, are small.Effect of CO2 on transpiration of field crops declines as canopy develops.

Calibration, Bridging, and Merging to Improve GCM Seasonal Temperature Forecasts in Australia

AbstractThere are a number of challenges that must be overcome if GCM forecasts are to be widely adopted in climate-sensitive industries such as agriculture and water management. GCM outputs are frequently biased relative to observations and their ensembles are unreliable in conveying uncertainty through appropriate spread. The calibration, bridging, and merging (CBaM) method has been shown to be an effective tool for postprocessing GCM rainfall forecasts to improve ensemble forecast attributes. In this study, CBaM is modified and extended to postprocess seasonal minimum and maximum temperature forecasts from the POAMA GCM in Australia. Calibration is postprocessing GCM forecasts using a statistical model. Bridging is producing additional forecasts using statistical models that have other GCM output variables (e.g., SST) as predictors. It is demonstrated that merging calibration and bridging forecasts through CBaM effectively improves the skill of POAMA seasonal minimum and maximum temperature forecasts f...