Citrus rootstock evaluation utilizing UAV-based remote sensing and artificial intelligence

Abstract

The implementation of breeding methods requires the creation of a large and genetically diverse training population. Large-scale experiments are needed for the rapid acquisition of phenotypic data to explore the correlation between genomic and phenotypic information. Traditional sensing technologies for field surveys and field phenotyping rely on manual sampling and are time consuming and labor intensive. Since availability of personnel trained for phenotyping is a major problem, small UAVs (unmanned aerial vehicles) equipped with various sensors can simplify the surveying procedure, decrease data collection time, and reduce cost. In this study, we evaluated the phenotypic characteristics of sweet orange trees grafted on 25 rootstock cultivars with different influences on plant growth and productivity utilizing a UAV-based high throughput phenotyping system. Data collected by UAV were compared with data collected manually according to standard horticultural procedures. The UAV-based technique was able to detect and count citrus trees with high precision (99.9%) in an orchard of 4931 trees and estimate tree canopy size with a high correlation (R = 0.84) with the manual collected data. No correlation of UAV-based data and manually collected data was observed for yield. The reason for the observed deviation is the influence of different rootstock cultivars on yield efficiency. Despite the low vigor-inducing effect of some rootstocks, they are highly productive, whilst others are high in vigor but produce less fruit. Our study demonstrates the high accuracy of the UAV technique to assess tree size. When using these techniques, it is essential to recognize the limitations imposed by the biological system.