Year: 2025
Type: article
Abstract: The development of quick, easy, and low‐cost methods to quantify within‐field variation is essential to successful implementation of mid‐season management for precision agriculture at scale. Temporal plant height and growth rates collected with unoccupied aerial vehicles mounted with red, green, blue sensors have the potential to predict variation in end of season grain yield throughout the field. To test this, image‐based plant height data were collected weekly from planting to flowering in production maize fields to assess within‐field variation in growth curves and the relationship with grain yield. A different commercial hybrid was grown under standard production conditions in each year of the experiment to assess the generalizability of the model. Plant height and growth rate had variable correlation with grain yield depending on the time point and growth environment ( r = −0.61 to 0.76). A partial least squares model trained using temporal growth rate predicted within field grain yield variation with an average correlation of r = 0.46 across years. Insufficient water affected the prediction accuracy in one field due to the limited representation of drought environments in the training data used for model development. In the future, with more training data from a range of stress environments, such as drought, this method has potential for high accuracy grain yield prediction across a range of environmental conditions. This study demonstrates the potential of using unoccupied aerial vehicles to derive vegetative growth patterns and model within‐field variation, and has application in making mid‐season management decisions.
Source: The Plant Phenome Journal
DOI: 10.1002/ppj2.70025
Authors: Dorothy D. Sweet, Julian Cooper, Cory D. Hirsch, Cory D. Hirsch, Candice N. Hirsch, Candice N. Hirsch
Institution: University of Minnesota
Language: English
Subfield: Ecology
Field: Environmental Science
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: gold
Estimated APC paid: $3,100
OpenAlex ID: W4410907553