Precision fruticulture in Flanders – a four-year study on sensing techniques, data analysis and variable rate applications

In recent years, precision agriculture is rapidly advancing. Sensing techniques such as (remote) UAV imagery and (proximal) soil scanning yield immense amounts of data. However, how to process, visualize and interpret those data and translate them into variable rate applications, remains a challenge. In order to develop applications of precision fruticulture, a ‘Conference’ pear orchard was monitored intensively for four consecutive years using soil apparent electrical conductivity (ECa) scans and RGB and multispectral unmanned aerial vehicle (UAV) imagery. Simultaneously, ground truth data were gathered, including flower intensity, vegetative growth and fruit yield. A clear relationship was observed between soil and crop characteristics. Therefore, the soil ECa map, together with flower intensity mapping derived from UAV imagery, was used to steer variable rate manual pruning and variable rate chemical thinning. The best results were obtained for variable pruning, but depended on the weather conditions during the growing season.