Wireless iot monitoring and machine learning system for hydroponic tomato fertigation optimization
A wireless IoT sensor network combined with machine learning to optimize fertilizer delivery in hydroponic tomato production. The system monitors water nutrient levels and greenhouse conditions to predict plant nutrition needs, reducing costly inputs in controlled environment agriculture.
Overview
This solution addresses the growing demand for efficient hydroponic food production by combining wireless IoT monitoring with predictive machine learning to optimize fertilizer delivery in greenhouse tomato systems. Hydroponic and controlled environment agriculture (CEA) offer a path to meeting global food demand, but supplemental resources such as lighting, fertilizer, and irrigation are expensive. This technology provides decision support to manage these costly inputs more precisely, helping growers reduce waste while maintaining optimal plant nutrition.
The system is being developed to detect differences in soluble fertilizer concentrations in real time and predict when plants require nutrient inputs, enabling data-driven fertigation rather than fixed-schedule applications.
Technical specifications
Core technology components:
- Wireless IoT sensor network deployed across Bato Bucket hydroponic systems in climate-controlled greenhouses
- Water quality sensors monitoring nitrate (NO3-), potassium (K), electrical conductivity (EC), pH, temperature, and dissolved oxygen
- Greenhouse environmental sensors tracking vapor pressure deficit (VPD), light, and temperature
- Plant health monitoring via spectrometer for NDVI and SPAD meter for chlorophyll concentration
- Artificial neural network model trained to predict plant nutrition status (NDVI and SPAD) from water nutrient and climate data inputs
- Low-cost, open-source hardware architecture designed for accessibility and reproducibility
Team expertise and prior validated systems:
- Decade-long track record in plant irrigation and nutrition research
- Previously developed an irrigation control system based on real-time plant water demand (evapotranspiration)
- Built an automated greenhouse control system that maintains optimal VPD levels
- Created LOCOS, a low-cost (under $1,000) open-source monitoring device successfully deployed in multiple agricultural studies
Technology readiness level
The technology is currently in the research and validation phase. The proposed validation will equip two Bato Bucket hydroponic systems with the wireless sensor network and apply high and low fertilizer treatments to compare plant responses. Data collected from water characteristics, greenhouse environment, and plant health metrics will be used to train and validate the machine learning model. The team has demonstrated prior capability through existing IoT systems and crop production research, positioning the project for meaningful proof-of-concept results in a controlled greenhouse environment. Commercial deployment would follow successful model validation and refinement.
About Oregon State University
Oregon State University is a comprehensive public research university and Oregon’s land‑grant institution, with a main campus in Corvallis and a statewide footprint. Industry partners tap a statewide Extension network and county offices to pilot and scale solutions with communities and companies across Oregon. A coastal marine science campus in Newport anchors ocean research and provides access to open‑ocean wave‑energy test ranges and grid‑connected infrastructure under development nearby, enabling sea‑to‑shore prototyping. Field stations and university‑managed research forests support long‑term trials and product validation in real‑world environments. A dedicated technology transfer office and the OSU Advantage programs—including the Advantage Accelerator—streamline IP, licensing, startup formation, and industry agreements.
delivered to your inbox.