Topping the list of Australia's major crops, wheat is grown on more than half the country's cropland and is a key export commodity. With so much riding on wheat, accurate yield forecasting is necessary to predict regional and global food security and commodity markets. A new study published in Agricultural and Forest Meteorology shows machine-learning methods can accurately predict wheat yield for the country two months before the crop matures. "We tested various machine-learning approaches and integrated large-scale climate and satellite data to come up with a reliable and accurate prediction of wheat production for the whole of Australia," says Kaiyu Guan, assistant professor in the Department of Natural Resources and Environmental Sciences at the University of Illinois, Blue Waters professor at the National Center for Supercomputing Applications, and principal investigator on the study. "The incredible team of international collaborators contributing to this study has significantly advanced our ability to predict wheat yield for Australia."
European Journal of Operational Research
In an agricultural setting it is natural to consider yield risk in the context of a three level supply chain: with a small number of suppliers, large numbers of growers, and a small number of buyers. In the cereal growing case that is our focus, there is a supplier of fertiliser, a potentially large number of growers of cereal crops and a buyer, who purchases grain from the growers. The yield depends both on the input level of fertiliser and also on random weather-related factors. We study the impact of a new type of contract structure in which the grower purchases inputs at a discount, but agrees to a reduced price for the crop. The buyer makes a payment to the supplier to compensate for the discount offered. We show how this can coordinate the supply chain and demonstrate the potential advantages of this contract form when producers are risk averse. We look in detail at the implications of the use of these contracts by Australian wheat growers using data generated by APSIM, a growth simulation tool, to understand the connection between yields, fertiliser use and the weather. By using APSIM we can estimate the distribution of yields implied by the grower’s decision on fertiliser application and hence estimate optimal fertiliser use for risk averse growers.
Information Processing in Agriculture
This paper describes a quality-control supply-chain model using the “Internet +” paradigm. The model is based on principal-agent theory, which considers the reputational loss due to inferior products and external responsibility identification. After model analysis and simulation verification, the results show that the optimal quality-control level and market price of agricultural products can be achieved in the agricultural supply chain based on “Internet +” if and only if the information platform’s claim to the agricultural producer is less than the agricultural producer’s claim to the delivery service provider. Also, a rise in consumers’ claims or the agricultural producer’s reputational loss due to inferior products will motivate the quality control of an agricultural procedure. Meanwhile, the market price of agricultural products will also increase with enhanced quality control procedures. The quality-control level of a delivery service provider is inversely proportional to the information platform or its own reputational loss. Thus, the key to promoting quality control along the supply chain is to strengthen the responsibility confirmation of an inferior product between the agricultural producer and the delivery service provider.
Reduction in production levels due to the scarcity of water for crops, decrease in herds due to inadequate food and water for livestock and increased risk of forest fires due to drought, are some of the consequences that come with the El Niño phenomenon for the agricultural sector of Guatemala, due to the reduction of water levels.Following similar problems of climate variability throughout the region, the International Center for Tropical Agriculture in Central America (CIAT) through the Decision and Policy Analysis (DAPA) Research Area, is carrying out studies on water balance and monitoring climatic data, in order to contribute to the development of an agroclimatic bulletin that will later be distributed to local producers and partners to contribute to the processes of climate adaptation in the region.The studies are also within the framework of the "A Common Journey" project of the CGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) and is financed by the International Fund for Agricultural Development (IFAD).