Data Mining in Precision Agriculture: Management of Spatial Information

Precision Agriculture is the application of state-of-the-art GPS technology in connection with site-specific, sensor-based treatment of the crop. It can also be described as a data-driven approach to agriculture, which is strongly connected with a number of data mining problems. One of those is also an inherently important task in agriculture: yield prediction. The question is: can a field's yield be predicted in-season using available geo-coded data sets?. In the past, a number of approaches have been proposed towards this problem. Often, a broad variety of regression models for non-spatial data have been used, like regression trees, neural networks and support vector machines. But in a cross-validation learning approach, issues with the assumption of the data records' statistical independence keep emerging. Hence, the geographical location of data records should clearly be considered while establishing a regression model and assessing its predictive performance. This paper gives a short overview of the available data, points out in detail the main issue with the classical learning approaches and presents a novel spatial cross-validation technique to overcome the problems with the classical approach towards the aforementioned yield prediction task.