I-Corps: Translation Potential of a Rapid Stress Detection Platform for Greenhouse Crops

Award ID: 2628973

This I-Corps project is based on the development of a decision-support software technology for crops grown in greenhouses. Greenhouse crop production continues to rely heavily on manual inspections and visual identification of plant stress, causing health problems to be detected only after visible symptoms appear. However, this is often too late for effective intervention. As greenhouse operations expand to meet increasing demand for high-quality food production, growers need scalable, automated solutions that provide earlier and more reliable crop health information while reducing labor requirements. This technology is designed to address this need by continuously monitoring crop-environment interactions to detect early indicators of crop stress and support harvest timing decisions before visible symptoms emerge. This may improve crop quality and yield, reduce avoidable crop losses, optimize the use of labor, water, nutrients, and energy, and strengthen the advantages for crops grown in greenhouses. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of crop a health decision-support system for controlled-environment agriculture. It is based on a plant physiology-informed digital twin and is designed to continuously measure near-canopy and root environmental signals and compare them with the digital twin to identify abnormal crop behavior before visible symptoms develop. This technology integrates crop physiology with data-driven anomaly detection to provide continuous, non-invasive assessment of crop health and decision support for harvest timing, which is unlike existing methods that depend primarily on manual observation or threshold-based monitoring of environmental variables. Early prototype validation has shown that the system can identify crop stress approximately 40 hours before visible symptoms appear under controlled greenhouse conditions. This early-warning capability may help growers reduce avoidable losses, minimize waste, and make better-informed crop management decisions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Ruth Shuman