Ai-based greenhouse tomato monitoring and fertigation modulation system
An IoT and AI-driven fertigation management system for greenhouse tomatoes that uses low-cost nutrient sensors, cameras, and cloud analytics to detect stress early and optimize nutrient and water delivery based on variety, growth stage, and greenhouse conditions.
Overview
This solution addresses the challenge of precisely tuning fertigation in greenhouse tomato production to maximize nutrient and water efficiency. The system recognizes that optimal fertigation depends on tomato variety traits such as biomass, fruit size, yield potential, and days to maturity, as well as growth stage and real-time greenhouse conditions. By combining IoT sensors, spectral imaging, and AI-based modeling, the platform enables frequent monitoring and data-driven management decisions to reduce resource waste and improve yield outcomes.
Technical specifications
- IoT sensor network for continuous monitoring of fertigation nutrient levels, flow rate, temperature, humidity, and air flow
- Low-cost nutrient sensors integrated with the fertigation system for frequent data collection
- Camera-based plant imaging including spectral imaging for early stress detection (within 2 days of a fertigation malfunction)
- AI-based feature selection algorithms for identifying stress indicators and distinguishing nutrient deficiency from water stress (drought or over-watering)
- Arduino control board for orchestrating sensor data and image acquisition
- Cloud-based data storage, visualization, and monitoring dashboard for remote greenhouse management
- Fertigation decision model designed to adjust nutrient and water delivery based on variety, growth stage, and simulated malfunction scenarios
Technology readiness level
The underlying early-stage stress detection method has been patented and validated through three rounds of nutrient deficiency and water stress studies on greenhouse industrial hemp, involving two varieties and three repetitions with 96 plants per round. These studies confirmed the advantages of early detection and timely mitigation while revealing limitations in adjusting fertigation for best management practices. Future validation will deploy the full IoT sensor system and camera track in a University of Minnesota greenhouse, with tomato growing trials designed to test variety-specific responses and simulated fertigation malfunctions including abrupt changes in flow rate and nutrient content.
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.