Satellite-based modelling of protein content in winter wheat and malting barley
In: Precision agriculture '19Search for other papers by T. Börjesson in
Current site
Google Scholar
PubMed
Search for other papers by S. Wolters in
Current site
Google Scholar
PubMed
Search for other papers by M. Söderström in
Current site
Google Scholar
PubMed
Purchase instant access (PDF download and unlimited online access):
In this project, the aim was to develop satellite image-based models for prediction of protein concentration in malting barley and winter wheat at harvest. Using data from two out of three sampled regions in 2017, it was possible to predict the protein content in validation points in fields not included in the calibration with a mean absolute error (MAE) of less than 1% protein in all but one winter wheat field using a combination of early and late season satellite data. For 15% of the validation points, the predictions deviated more than 1% from the observations. In malting barley, it was sufficient to use only predictors from the late stage to achieve a similar prediction accuracy. For 2018, models similar to the ones from 2017 were obtained in only one of the regions. In the validations, MAE for fields not included in the calibration set were always below 1% in wheat and in 3 out of 4 fields in barley.