Within-field wheat yield prediction from IKONOS data: a new matrix approach

Abstract

This study demonstrates a unique matrix approach to determine within-field variability in wheat yields using fine spatial resolution 4 m IKONOS data. The matrix approach involves solving a system of simultaneous equations based on IKONOS data and post-harvest yields available at entire field scale. This approach was compared with a regression-based modelling approach involving field-sensor measured yields and the corresponding IKONOS measured indices and wavebands. The IKONOS data explained 74–78% variability in wheat yield. This is a significant result since the finer spatial resolution leads to capturing greater spatial variability and detail in landscape relative to coarser spatial resolution data. A pixel-by-pixel mapping of wheat yield variability highlights the fine spatial detail provided by IKONOS data for precision farming applications.