Corn yield estimation using multi-spectral imagery at R3-R4 growth stage
A remote sensing approach that uses satellite and drone-based multi-spectral imagery captured at the R3-R4 corn growth stage to accurately estimate grain and silage yield across farmer fields. Enables affordable, within-field yield mapping without expensive yield monitoring equipment, supporting better farm management decisions and on-farm research.
Overview
This solution provides an accessible, cost-effective method for estimating corn grain and silage yield at the farm, field, and within-field level using readily obtainable multi-spectral imagery. By capturing sensor data from satellites and unmanned aerial systems (UAS) at the R3-R4 corn growth stage (18-28 days after silking) and applying yield and vegetation index ratios, growers can obtain accurate yield estimates across farms, fields, and growing seasons without the need for expensive yield monitoring equipment. This approach democratizes access to high-resolution yield data, enabling improved economic and environmental decision-making and advancing on-farm research capabilities.
Technical specifications
- Optimal sensing window: Multi-spectral imagery is captured at the R3-R4 growth stage (18-28 days after silking), identified as the best timing for accurate yield predictions.
- Sensor platforms: Satellite imagery and UAS-mounted multi-spectral cameras, including hybrid fixed-wing drones such as the Quantix, are used for data collection.
- Calibration approach: Yield and vegetation index ratios are used to calibrate yield estimates across different farms, fields, and growing seasons.
- Multi-stage data collection: Flights are planned at key growth stages including planting, V6, V10, and R3-R4 to evaluate accuracy of the ratio-based approach.
- Validation basis: Earlier work with active sensors (Greenseeker) and quadcopter-mounted multi-spectral imagery at the Aurora Research Farm and a local cash grain farm demonstrated the feasibility of this approach.
Technology readiness level
This technology is at an advanced validation stage. Prior research at Cornell University's Aurora Research Farm and a local cash grain farm demonstrated proof of concept using active sensors and quadcopter-mounted multi-spectral imagery. Current work (2019-2020) with approximately 30 corn growers has further refined the approach, identifying R3-R4 as the optimal timing for yield predictions. Future validation will involve flying ten fields per farm across five farms with accurate yield data and reliable collection capabilities, combining drone and satellite imagery to evaluate the accuracy of the ratio-based calibration approach across diverse growing conditions.
About Cornell University
Cornell University is a comprehensive private, land-grant research university with campuses in Ithaca and New York City, combining significant scale with cross-disciplinary breadth. Industry connects through open-access user facilities and prototyping labs, pilot-scale testbeds, and a research and technology park that provide pathways from discovery to demonstration. A statewide extension network and integration with a major hospital system enable real-world deployment, while a graduate campus embedded in New York City’s tech corridor provides direct access to startups, venture investors, and corporate R&D teams. Research is supported by competitive federal funding from agencies such as the National Science Foundation, National Institutes of Health, the Department of Energy, and the U.S. Department of Agriculture. A dedicated technology transfer office streamlines IP management, licensing, startup formation, and corporate partnerships across campuses.
delivered to your inbox.