Skip to main content
. 2020 May 18;10:8195. doi: 10.1038/s41598-020-65011-2

Figure 1.

Figure 1

Prediction of the genetic merit for grain yield using hyper-spectral crop image data. (A) Data consists of hyper-spectral reflectance data (xi) and phenotypic measurements of the target trait (yi, e.g., grain yield). (B) A subset of the data (the training set) is used to derive the coefficients (β) of a selection index. (C) These coefficients are then applied to image data of individuals in the testing set to derive the index (Ii) for each individual. The predictive ability of the index is assessed by calculating the accuracy of indirect selection (Acc(I)) in the testing set.