Weed density prediction with secondary input of DEM information
In: Precision Agriculture ‘05Search for other papers by M. Jurado-Expósito in
Current site
Google Scholar
PubMed
Search for other papers by F. López-Granados in
Current site
Google Scholar
PubMed
Search for other papers by J. M. Peña-Barragán in
Current site
Google Scholar
PubMed
Search for other papers by L. García-Torres in
Current site
Google Scholar
PubMed
Purchase instant access (PDF download and unlimited online access):
This research addresses the issue of incorporating a digital elevation model (DEM) as secondary spatial information into the mapping of dominant weed species present in two sunflower crops in Andalusia (Spain). Two prediction methods were used and compared for mapping weed density for precision agriculture approaches: ordinary point kriging (OK), and kriging with an external drift (KED). The primary variable was obtained from an intensive weed density sampling and the secondary spatial information (i.e., elevation) was obtained from the DEM. Mean squared error (MSE) was used to evaluate the performance of the map prediction quality. The best prediction method to map most of the weed species was KED with the smallest MSE indicating the highest precision. Maps obtained from these kriged estimates showed that the incorporation of DEM as secondary exhaustive information, could improve the accuracy of predicted weed densities within fields for site-specific weed management.