Plot‐level satellite imagery can substitute for UAVs in assessing maize phenotypes across multistate field trials

Abstract

Societal Impact Statement Maize plays a key role in agricultural profitability and food security on six continents. Successful efforts to breed higher‐yielding maize varieties depend on replicated yield trials in many environments. Capturing in‐season data can help improve and accelerate the development of regionally adapted hybrids, but collecting these data can be impractical in many locations. We demonstrate that satellite remote sensing could play a similar role in crop performance assessment as unmanned aerial vehicles (UAVs) but with far lower labor costs and the greatest ease of collection at remote field sites. This dataset and benchmarks have the potential to enable predictive models that could guide farmers and crop breeders in decision‐making. Summary Accurate early yield estimates at fields and plots offer potential benefits to farmers in optimizing their agronomic practices and breeders in screening thousands of varieties contributing to improving agriculture and food production systems. Effective approaches to track plant growth and predict yield require large datasets of remote sensing and ground truth data collected across multiple environments. Low‐altitude drone flights are increasingly being used to collect data from field evaluations of new crop varieties, while satellite imagery is being explored to track yield and management practices at regional scales. Satellite platforms exhibit logistical and technical advantages in scalability and accessibility and could facilitate plot‐level predictions, especially with steadily improving spatial resolution. However, plot‐level, high‐resolution satellite images capturing differences in genotypes from multiple environments with ground truth measurements are not publicly available. Here, we generated, described, and evaluated over 20,000 plot‐level images of over 80 hybrid maize varieties grown across the US corn belt under various management practices collected from (near simultaneous) satellite and drone (synonym UAVs, UASs) flights integrated with ground truth yield measurement. Of the six baseline models examined, models employing data collected from satellite images often matched the performance of models employing drone images for both within and cross‐environment yield prediction.