Temporal phenomic predictions from unoccupied aerial systems can outperform genomic predictions

Abstract

A major challenge of genetic improvement and selection is to accurately predict individuals with the highest fitness in a population without direct measurement. Over the last decade, genomic predictions (GP) based on genome-wide markers have become reliable and routine. Now phenotyping technologies, including unoccupied aerial systems (UAS also known as drones), can characterize individuals with a data depth comparable to genomics when used throughout growth. This study, for the first time, demonstrated that the prediction power of temporal UAS phenomic data can achieve or exceed that of genomic data. UAS data containing red-green-blue (RGB) bands over 15 growth time points and multispectral (RGB, red-edge and near infrared) bands over 12 time points were compared across 280 unique maize hybrids. Through cross-validation of untested genotypes in tested environments (CV2), temporal phenomic prediction (TPP), outperformed GP (0.80 vs 0.71); TPP and GP performed similarly in 3 other cross-validation scenarios. Genome-wide association mapping using area under temporal curves of vegetation indices (VIs) revealed 24.5% of a total of 241 discovered loci (59 loci) had associations with multiple VIs, explaining up to 51% of grain yield variation, less than GP and TPP predicted. This suggests TPP, like GP, integrates small effect loci well improving plant fitness predictions. More importantly, TPP appeared to work successfully on unrelated individuals unlike GP.

Keywords: genomic prediction; high-throughput phenotyping; phenomic prediction.

Fig. 1.

Prediction accuracy (on the y axis) of the phenomic prediction obtained by each model for 4 cross-validation schemes (on the x axis) belonging to each predicted variable (from left to right) in phenomic prediction. a) The prediction performance of TPP_RGB phenomic data derived from HTP platform including 25-meters elevation with RGB sensor. b) The prediction performance of TPP_Multi phenomic data derived from HTP platform including 120-m elevation with multispectral sensor. The boxes in each point cloud show mean values of prediction accuracies.

Fig. 2.

Each box plot shows the genomic prediction accuracy results belonging to each time points of each temporal trait in TPP_RGB, each contains 500-prediction accuracies. Y axis shows the prediction accuracy and x axis shows the flight date as days after planting time. Each box plot was colored based on the mean. Heatmap color scale was given in the figure legend changing between 0 and 0.6. Gray shading in each represents flowering time. Different time points of temporal traits were found to have different responses to genetic markers across growth stages of plant development.

Fig. 3.

The prediction accuracy results of yield belonging to the 3 models. GP represents the prediction accuracy of genomic prediction, TPP_Multi represents the prediction accuracy of phenomic prediction using the VIs derived from the multispectral images with low resolution, TPP_RGB represents the prediction accuracy of phenomic prediction using the VIs derived from the RGB images with high resolution. Four cross-validation schemes were used: predicting tested genotypes in tested environments (CV1), predicting untested genotypes in tested environments (CV2), tested genotypes in untested environments (CV3), and untested genotypes in untested environments (CV4). Phenomic prediction predicted the grain yield (GY) of maize hybrids better in CV2 than genomic prediction. Prediction accuracies were close to each other in CV3 and CV4.