The Ohio State University Corporate Engagement Office

Back to All Technologies

Next-generation method for flow estimation and geospatial mapping of agricultural particulates

Agricultural Engineering
College of Food, Agricultural, and Environmental Sciences (CFAES)
Colley III, Richard
Fulton, John
Licensing Manager
Dahlman, Jason "Jay"


The Need

Next-generation agricultural sensor technology enables precise, data-based decision-making to be implemented at the farm level. Field operations data such as granular fertilizer application rates are useful to the producer, because optimization of nutrient supplementation increases use efficiency and decreases material costs. However, while there have been data-driven advances in other areas of field operation, methods for precise measurement of particulate application is a neglected area of agricultural innovation. For example, available technologies for calculating particulate application rates rely on indirect estimates, i.e. ‘as-applied’ rates. This results in error due to variation in the physical properties of the applied particulate, environmental conditions, and machinery operation. Furthermore, existing technologies that are meant to enhance applicator precision are only capable of detecting blockages in flow and providing unsophisticated estimations of inter-row variation. There is no available system that allows for direct quantification of application rates and calculation of optimal application.

The Technology

Researchers at Ohio State University led by Drs. Richard Colley and John Fulton have developed a system to estimate the mass flow rate of a particulate flow using machine vision technology. This machine vision technology involves imaging the particulate flow and processing the captured image data in real-time to extract information about the particulates flowing through an applicator. By using a machine vision system to directly observe the particulates as they are applied, the error introduced by indirect estimation is minimized, and users gain access to valuable information. Furthermore, this information can be combined with GPS-based location data to enable high-resolution geospatial mapping of particulate application. In turn, this system could be used as a method to estimate granular fertilizer application with unprecedented precision, where one may estimate the rates of granular fertilizer application for each row in a given landscape. Therefore, this method is capable of providing real-time feedback to the user on a row-by-row basis for the improvement of crop production efficiency.

Commercial Applications

  • Actionable agricultural data analytics
  • Geospatial mapping of sub-surface applications
  • Flow rate calculation for granulates (fertilizer, pesticide, seed, etc.)


  • Machine vision system substantially improves over indirect measurement systems
  • System provides precise data for more-reliable information
  • High-resolution geospatial data