Progress 07/01/22 to 02/28/23
Outputs
Target Audience:tree crop growers and allied industry, extension personnel, and policymakers. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided?Three members of the team attended seminars offered by NVIDIA on the use of embedded programming for real-time AI applications. They also attended the ASABE (American Society of Agricultural and Biological Engineers) conference on July 17-20, 2022, in Huston, Texas, and presented the findings of this project. Dr. Ampatzidis attended three other conferences too (see dissemination session) and presented the findings of this project. How have the results been disseminated to communities of interest?To begin commercialization, AgIntel secured and exhibited Agroview's nutrient analysis modules at the 2022 Citrus & Specialty Crop Expo, in Fort Myers, FL, from August 17-18, 2022. We were able to demonstrate the initial working nutrient analysis models to over 1,000 growers and other stakeholders. From October 2022 through January 2023, we conducted over twenty investor presentations that featured our results in our future product capabilities. We have also completed the licensing option with the University of Florida to commercialize the Agrosense ground sensor. Furthermore, Dr. Ampatzidis presented the findings of this project in four extension, educational, and outreach venues including: UAVs, Sensors, & Other Applied Research Technology. Research Center Administrators Society (RCAS) Meeting, Gulf Coast REC, February 6, 2023. AI-enhanced smart machinery for precision scouting and spraying. National Alliance of Independent Crop Consultants (NAICC) 2023 Annual Meeting and AG PRO EXPO, Nashville, TN, January 23-27, 2023. AI-enhanced precision management in specialty crops. USDA National Agricultural Statistics Service, Research and Development Division (virtual seminar). September 29, 2022. Robotics and AI in specialty crop production. 4-H robotics team, Exploding Bacon (virtual seminar). September 26, 2022. What do you plan to do during the next reporting period to accomplish the goals?
Nothing Reported
Impacts
What was accomplished under these goals?
The first step in developing the Smart Nutrient was to produce applicable prescription maps from Agroview's fertility maps. Hence, a tool/feature was developed to convert a fertility map to a prescription map on Agroview. With this tool, a grower or farm manager can manually input the prescription rate for each management zone of the fertility map. The user can download the prescription map on a memory stick (as a geojson file) and upload it on Agrosense. As the prescription map may not cover the specific needs of each individual plant (e.g., a large tree needs more nutrients compared to a small/reset tree, even if they are in the same management zone), Agrosense's real-time data can be used to individually integrate the ground data (e.g., tree canopy volume and leaf density) with the provided prescription map to adjust the application rate for each individual tree, thus we have a fine-tuned application per tree. A data fusion algorithm was developed on Agrosense for this purpose (aka, determining in real-time the tree canopy volume and leaf density and also identifying the desired application rate based on the management zone from the prescription map). The user interfaces (UI) for Agroview and Agrosense were re-designed for allowing further customization according to different user preferences. In Phase I, we also upgraded the control unit of the Agrosense for smart spray/fertilizer applications (Obj. #2). We developed a custom printed circuit board (PCB) with all connections and electronics required for the controller of the smart sprayer/fertilizer, for reliability and easy maintenance. A new Jetson module (Jetson Xavier NX Industrial Fanless PC - Model: DSBOX-NX2) was selected and benchmark tested on 24 V to check if the power supply of most tractors can feed the system. The updated system now uses a standard 24 V for ease of maintenance and production. On the UI and control unit, we added more features requested by our grower and industry collaborators. For example, we included a manual speed option to UI when GPS speed data are not available or contain a lot of noise. A configuration for the lidar's zone activation areas in degrees was also developed, allowing the user to adjust for uncommon terrains such as crevices and canals between crop rows. A real-time backup feature to store "important" data was also developed, for large-scale production and faster maintenance, in case the smart controller stops working because of damaged parts. New parts were tested for lower heat generation to optimize the life cycle of all components. The smart sprayer was tested in orchards and no issues were recorded. The designs of the sensing and control system were improved significantly. A tool was developed to automatically produce a Nutrient Application Record Form after every fertilizer application, based on new BMP requirements. A software and UI were developed to collect data (e.g., date/time of application, RPA and "spraying map", location/field, etc.) from the smart controller to automatically complete and generate the Nutrient Application Record Form. A manual tool also allows the user to input other information that cannot be collected automatically (e.g., nutrient source, commodity grown, etc.). Finally, another tool was developed to automatically detect under- and over-sprayed areas on the developed spray heatmaps. This tool can be used by the manager to better evaluate the quality of every fertilizer application. These two tools were requested by our grower collaborators.
Publications
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Costa L., and Ampatzidis Y., 2022. Smart tree crop sprayer sensing system utilizing sensor fusion and artificial intelligence. ASABE Annual International Meeting, July 17-20, 2200585, doi:10.13031/aim.202200585.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Ampatzidis Y., 2022. AI-enhanced smart farming. The 6th IEEE UV2022, International Conference on Universal Village, Virtual and main venue in Boston, USA, October 22-25, 2022 (Keynote Speaker).
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Ampatzidis Y., 2022. AI-enhanced precision nutrient management in specialty crops. 2022 ASA â¿¿ CSSA â¿¿ SSSA International Annual Meeting, Symposium 125: Nutrient Management and Innovations in Sensor Technology, Baltimore, MD, USA, November 6-9, 2022 (Invited Speaker).
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Ampatzidis Y., 2023. AI-enhanced smart machinery for precision scouting and spraying. Annual Meeting and Ag Expo of the National Alliance of Independent Crop Consultants (NAICC), Nashville, TN, January 23-27, 2023.
- Type:
Conference Papers and Presentations
Status:
Accepted
Year Published:
2023
Citation:
Lacerda C., Costa L, Ampatzidis Y., 2023. The process of optimizing a cloud based software infrastructure: Agroview, a case of study. AI in Agriculture Conference: Innovation and Discovery to Equitably meet Producer Needs and Perceptions, Orlando, FL, April 17-19, 2023.
- Type:
Conference Papers and Presentations
Status:
Accepted
Year Published:
2023
Citation:
Costa L. and Ampatzidis Y., 2023. Building reliability: development of a prototype to production for a smart citrus tree sprayer using sensor fusion and artificial intelligence. AI in Agriculture Conference: Innovation and Discovery to Equitably meet Producer Needs and Perceptions, Orlando, FL, April 17-19, 2023.
|