Developing and deploying an unmanned aerial system–based phenotyping program for maturity to support soybean breeding

Abstract Soybean [ Glycine max (L.) Merr.] varieties are categorized into different relative maturity groups (MGs) that correspond to the approximate region that the variety is best adapted. Maturity is an important trait that growers consider when deciding which varieties to plant and for breeders as a covariate to compare genotypes. Accurate phenotyping of maturity is an important task during line development but is labor‐intensive. High‐throughput phenotyping (HTP) of soybean maturity using unmanned aerial systems can reduce the labor and error associated with manual maturity notes. An HTP program for maturity will provide higher quality maturity data that will improve breeders’ ability to evaluate the performance of breeding lines on a large scale. The objective of this study was to develop an intuitive, accessible, and precise HTP program to determine the maturity of soybean varieties in the field that can be deployed in soybean breeding programs. In this study, “Matti,” a QGIS plugin, was developed to track the average green leaf index (GLI) of soybean research plots during the senescence period. Piecewise and local polynomial regression models monitor the senescence curve and provide maturity estimates when the GLI values are near or below a user‐specified threshold. This algorithm resulted in moderate to high correlations ( r = 0.52–0.97) between the ground truth and estimated maturity of soybean lines in both early and late maturity MGs. Similar correlations ( r = 0.43–0.72) were found for early generation materials. Results indicate that Matti can be easily implemented by soybean breeding programs to provide timely estimates of relative maturity.