Communications of the ACM
New Research Accurately Predicts Australian Wheat Harvests Months in Advance
Research by the U.S. National Science Foundation found that machine learning techniques could anticipate the size of Australian wheat yields as long as two months before the end of the growing season.
Credit: Bluemoose
A U.S. National Science Foundation-funded project found that machine learning techniques could anticipate Australian wheat yields two months before the end of the growing season.
The University of Illinois' Kaiyu Guan said, "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."
Guan noted the satellite data provided additional information which significantly refined wheat harvest prediction.
The researchers applied this information to forecast yield, with about 75% accuracy two months prior to crop maturation.
From National Science Foundation
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found