Accessibility navigation

Producing grain yield maps by merging combine harvester and remote sensing data

Karampoiki, M., Heiß, A., Sharipov, G. M., Mahmood, S., Todman, L. C. ORCID:, Murdoch, A., Griepentrog, H. W. and Paraforos, D. S. (2021) Producing grain yield maps by merging combine harvester and remote sensing data. In: Precision Agriculture '21, July 2021, Budapest, pp. 645-651, (ISBN 9789086863631)

Full text not archived in this repository.

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.3920/978-90-8686-916-9_77


High-quality combine harvester yield data are very important to produce yield maps. However, errors that derive from the combine harvester may be corrected. A data source that could be used to improve the yield maps obtained from harvester data is satellite-based data (e.g. Sentinel 2 (S2) imageries) and unmanned aerial vehicles (UAV) based data that are commonly used to predict grain yield and also define fertilisation rates. In this study, yield data from a combine harvester, a multi-spectral camera mounted on a UAV and S2 images were collected to produce yield maps that offer more accurate representation. To calibrate and validate this method, biomass samples were acquired manually before harvesting while erroneous yield data were replaced by remote sensing data. A regression analysis between the ground-truth biomass samples and the filtered yield data had an R2 value equal to 0.84, while the R2 of the biomass with the yield data obtained by the proposed methodology was equal to 0.90.

Item Type:Conference or Workshop Item (Paper)
Divisions:Life Sciences > School of Agriculture, Policy and Development > Department of Crop Science
ID Code:103268
Uncontrolled Keywords:normalised difference vegetation index (NDVI), Sentinel imagery, unmanned aerial vehicle (UAV) data, yield data cleaning

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation