SBIR Phase I: A real-time precision nutrient analysis and management system for hydroponic farming operations

Envonics Llc, North Miami FL

Investigators

Abstract

The broader impact of this Small Business Innovation Research (SBIR) Phase I project is to promote the viability and sustainability of small-to-medium indoor, urban, and controlled environment agriculture (CEA) farms. As the global population grows to 10 billion by 2050, the agriculture industry will need to produce 70% more food using only 5% more land. Indoor farming can make a significant contribution to meet this demand sustainably. Indoor farmers are also seasonally and geographically independent, which means they can help meet demands for locally produced fresh foods and are protected from extreme weather events. These farms primarily use soilless growing methods, such as hydroponics, that currently suffer from critical needs for efficient and affordable methods to monitor and manage nutrients and water in order to be financially viable and environmentally sustainable. The proposed project provides an innovative solution for nutrient management in hydroponic farming, thereby lowering the costs, increasing the yield potential, and supporting the viability of such farms. By supporting the expansion of the national hydroponics industry, this project will increase the local production of and expand access to fresh produce. This SBIR Phase I project will develop a nutrient management system to provide CEA farmers with real-time information about the nutrients in the growth solution of their crops. The proposed solution will utilize ion-selective electrode (ISE) technology and a decision support system powered by machine learning (ML). This project will focus on the critically needed engineering and data analytics research and development to de-risk major technical challenges in the development of the nutrient management system, providing proof-of-feasibility. The key objectives of this project are to: 1) design a special chamber for the sensors to minimize the interference and increase accuracy, 2) validate the feasibility and accuracy of this new design in a greenhouse setting, 3) develop a predictive algorithm to automatically calibrate the sensors, and 4) measure and predict deficiencies in leafy greens production: collecting empirical evidence of nutrient deficiency to train ML models to identify, and ultimately, predict a deficiency prior to when it is observable. 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.