I-Corps: Image processing platform to identify photosynthetic pigment density to measure nitrogen content and manage fertilizer (Smart Sustainable Fertilizer Manager)

The broader impact/commercial potential of this I-Corps project is the development of a technology to determine the fertilizer needs of potted plants. Large-scale nursery production, a sizable component of the agriculture industry, involves the use of containers to grow plants. An acre of land in nursery production houses up to 300,000 containers, many of which receive excessive fertilizer application.

Nitrogen (N) is a macronutrient that affects plant chlorophyll content, which may be used to define the growth status and leaf N content in plants. The proposed technology may enable nursery producers to determine the fertilizer needs of potted plants and help avoid overfertilization and nutrient runoff. In addition, the proposed technology may promote plant health and environmental sustainability as well as enable big data to be collected from fertilizer practices in large and small settings.

This I-Corps project is based on the development of a smart, sustainable fertilizer manager platform that uses image processing and machine learning to measure leaf nitrogen content. The proposed technology allows the use of any camera sensor to image and process leaf color to identify the photosynthetic pigment density in a non-destructive way and compare this measurement with the existing cloud data for analysis.

Current fertilizer management is typically based on published fertilizer recommendations, which vary among plant species. The proposed design uses a single image taken by a smartphone to give a recommendation on fertilizer needs for potted plants (flowers and ornamentals). The image is scanned and analyzed, and the user receives a message indicating whether a plant is deficient in nutrients.

Core machine learning is being used to train a model based on the “green value” provided by completed and ongoing research projects. The technology's Application Programming Interface (API) will be embedded in the application.

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.