SBIR-STTR Award

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) project is the introduction of urban farming as a viable new industry for small businesses by driving down the barrier of entry to hydroponic farming. Conventional hydroponic farming necessitates complex systems in which a variety of variables must be monitored and controlled by a skilled operator in response to changes throughout the plant lifecycle and care must be taken to control these variables precisely. This need for demanding management by a technically-educated farmer has restricted the widespread adoption of urban hydroponic farming. This project will result in a fully-automated precision farming platform managing the full scope of urban farming operations. The platform uses trends in a hydroponic grown zone to forecast changes to system variables and crop growth and to automatically and intelligently adjust vital parameters to optimize resource usage and maximize output. Because the precision doser will not require extensive agricultural expertise, it will make hydroponic farming accessible to small-scale farmers, restaurateurs, and private consumers. Once it becomes possible for non-industrial operations to establish hydroponics, urban farms can place sources of fresh, organic produce right in the heart of food deserts without reliance on GMOs, herbicides, or pesticides. This SBIR Phase I project proposes to develop a hydroponics farming control platform which intelligently predicts crop growth, forecasts vital system variables including the pH and electrical conductivity, and tunes environmental parameters in accordance with the forecasts, precisely adjusting the growing zone to maximize crop output while minimizing wasted resources. More than one-tenth of households in the United States cope without adequate nutrition or rely on processed foods, leading to the dual crisis of food insecurity and obesity throughout urban environments. Because they do not have the same extensive land and water requirements as traditional farming, hydroponic operations can take root in urban environments where access to fresh, nutritious produce is restricted. This project will target two aspects of hydroponic agriculture essential to the development of a precision farming tool: crop output and system parameters. By analyzing trends in plant growth, the platform will inform decision-making around resource usage, allowing the grower to adjust system parameters that promote the most successful crops. The final platform will directly address the concern of food deserts in urban localities, by offering a means to grow fresh produce locally, reducing the production costs of standard farming operations, and optimizing crop output in hydroponic systems. 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.

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is to improve vertical farms. The global threat to food security and the need to deal with unpredictable climate conditions have opened the doors to advanced precision agriculture and vertical urban farming. Rapidly growing global populations, demand for higher agricultural yields with limited arable farmland drive demand for vertical farming and new technologies to expand access to this method of sustainable crop cultivation. The proposed system will reduce the burden on the environment by decreasing water, fertilizers and pesticides required to grow crops. These micro-farms will boost agricultural profitability by providing a reliable, sustainable food system with fresh, healthy, and eco-friendly produce. This reduces food waste and the environmental impact of the food supply chain while improving yields and nutritional density. This SBIR Phase II project advances a system with integrated environmental control, consumables management, alerting, and scheduling. Furthermore, the automated controls are continuously improved by using camera vision to estimate yield and machine learning to forecast yield and optimize the environmental variables. To make the system cost-effective, a novel multispectral camera will be developed to collect agricultural data. Using machine learning, the images collected will be correlated to the environmental variables, such as pH and nutrient concentration, so that those variables can be optimized to increase yields. In order to improve scheduling and logistics, the platform will track inputs such as seeds, nutrients, and pH solution, using sensors and QR codes to automate consumable replacement. Sensors and software checks will determine when component or human failure have occurred, before they lead to crop failure, leading to just-in-time component replacement and maintenance. 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.