UAV-based plant growth monitoring for breeding and crop management decisions
A drone-based high-throughput phenotyping method that monitors crop growth rate throughout the season to predict end-of-season yield and assess environmental stress. Validated on maize across multiple seasons and environments, with applications for breeding programs and production-scale yield prediction.
Overview
This solution uses unmanned aerial vehicle (UAV) imagery to monitor plant growth rate throughout the growing season as an indicator of crop health and performance. Growth rate captures how a plant's genome interacts with its environment, providing an early signal of end-of-season yield potential. The approach supports both breeding programs seeking to develop varieties that respond favorably to specific conditions and production managers who need timely, field-scale insights to guide interventions.
The method has been validated on maize using multi-season UAV flights and applied to assess lodging damage following wind storms. Across a panel of 500 diverse genotypes grown in five environments, genotype explained 10.5–40.0% of observed variation in growth rate, while genotype-by-environment interaction explained 22.2–83.6%, underscoring the importance of environmental response in crop performance.
Technical specifications
Core capabilities:
- High-throughput monitoring of maize growth rate throughout development using UAV imagery collected at regular intervals during the growing season
- Assessment of lodging damage severity following wind events across multiple seasons
- Predictive models linking growth rate and lodging severity to yield, with R values ranging from 0.55–0.72 depending on lodging severity
- Scalable approach designed for thousands of plots and production-scale fields
Key features:
- Weekly drone flights enable continuous tracking of crop development and early detection of stress
- Compatible with diverse genotype panels and multi-environment trials, making it suitable for breeding evaluation
- Designed to integrate with combine yield maps for production-scale validation
Technology readiness level
The method has been demonstrated and refined through multi-season field campaigns on maize, including lodging assessment and yield prediction across diverse genotypes and environments. Ongoing validation involves weekly drone flights over more than 7,500 plots through the Genomes2Fields Initiative, alongside flights on production fields at University of Minnesota Research and Outreach Centers to test yield prediction and targeted management interventions in real production settings.
About University of Minnesota
The University of Minnesota is a flagship, comprehensive public research university spanning multiple campuses, with a large research enterprise and clinical integration. Industry engages through co-located labs on the Twin Cities campuses, access to an academic health system for clinical translation, and pilot and field-testing facilities that speed scale-up. A statewide extension network and outreach centers provide real-world sites and data partnerships across Minnesota, while proximity to a dense medtech and Fortune 500 corridor enables frequent collaboration. Research is supported by competitive federal funding, including NIH, NSF, DOE, USDA, and DoD. A dedicated technology transfer office manages IP, licensing, sponsored research agreements, and startup incubation to speed commercialization.
delivered to your inbox.