Source: UNIVERSITY OF FLORIDA submitted to NRP
AI-ENHANCED RAPID RESPONSE TOOL FOR EXTREME WEATHER EVENTS UTILIZING AERIAL AND GROUND REMOTE SENSING
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
COMPLETE
Funding Source
AFRI COMPETITIVE GRANT
Reporting Frequency
Annual
Accession No.
1029713
Grant No.
2023-68016-38995
Cumulative Award Amt.
$299,500.00
Proposal No.
2022-11481
Multistate No.
(N/A)
Project Start Date
Feb 1, 2023
Project End Date
Jan 31, 2024
Grant Year
2023
Program Code
[A1712]- Rapid Response to Extreme Weather Events Across Food and Agricultural Systems
Recipient Organization
UNIVERSITY OF FLORIDA
G022 MCCARTY HALL
GAINESVILLE,FL 32611
Performing Department
(N/A)
Non Technical Summary
Hurricane Ian, a category 4 storm, with winds between 111 and 155 miles per hour, hit the State of Florida (among other States) with a catastrophic impact. Hurricane Ian poses a major risk to Florida's specialty crop industry. More than 20 inches (508 mm) of rain fell in places where the storm center passed, with 12 inches (304 mm) common outside that zone. Several rivers in farm regions set new flood state records. Based on a preliminary estimate from UF, agriculture losses in Florida from Ian's impact could reach $1.56 billion. About 5 million acres of farmland were affected by the storm. However, the real impact and long-term effect of the storm are very difficult to be determined with the current surveying techniques.Our team has developed a cloud- and artificial intelligence (AI) based technology, Agroview, to process, analyze, and visualize data collected from aerial (e.g., unmanned aerial vehicles-UAVs and aeroplanes) and ground-based sensing systems. This novel technology can serve as a digital twin of an agricultural field. We have also developed a ground-based (AI-enhanced) sensor, AgroSense, to detect and count fruit on trees. The main goal of this proposal is to utilize and further develop the two AI-enhance technologies, Agroview and AgroSense, to assess damages and risks in specialty crop production caused by extreme weather events.The specific objectives of this project are: (i) Train AI models to automatically detect and visualize damages on specialty crops caused by extreme weather events (case studies on citrus, tomato, and pepper). (ii) Evaluate this novel technology in commercial fields in collaboration with growers and a crop insurance company. Collect data from at least 20,000 acres. Conduct a feasibility study to evaluate if the developed tool is cost-effective. Develop an extension program to demonstrate the novel rapid response tool.The use of this novel technology in commercial fields is expected to help specialty crop growers to rapidly calculate losses and better communicate recovery needs to ensure business viability and minimize interruption to the U.S. produce supply chain due to unexpected weather and climatic events.
Animal Health Component
70%
Research Effort Categories
Basic
(N/A)
Applied
70%
Developmental
30%
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
8070999202050%
4020430202050%
Knowledge Area
807 - Disaster Preparedness, Mitigation, Response, and Recovery; 402 - Engineering Systems and Equipment;

Subject Of Investigation
0430 - Climate; 0999 - Citrus, general/other;

Field Of Science
2020 - Engineering;
Goals / Objectives
The main goal of this proposal is to utilize and train/calibrate two AI-enhance technologies, Agroview and AgroSense, to assess damages and risks in specialty crop production caused by extreme weather events (e.g., hurricanes).The specific objectives are:Train AI models and develop a module on Agroview to automatically detect and visualize damages on specialty crops caused by extreme weather events (aka, Hurricane Ian). Utilize both aerial (aka, UAVs) and ground (aka, AgroSense) sensing platforms for data collection. Conduct case studies on citrus, tomato, and pepper.Evaluate this novel technology in commercial fields in collaboration with growers and a crop insurance company. Collect data from at least 20,000 acres of citrus, tomato, and pepper fields covering South and Central Florida; areas with high and different types (e.g., high winds, heavy precipitation, flooding, or combination) of impacts. Develop an extension program to demonstrate the impact of extreme weather events and the novel rapid response tool.
Project Methods
The activities to achieved the project objectivies include:Objective 1: Train AI models and develop a module on Agroview to automatically detect and visualize damages on specialty crops caused by extreme weather events (aka Hurricane Ian). Utilize both aerial (aka, UAVs) and ground (aka, AgroSense) sensing platforms for data collection. Case studies on citrus, tomato, and pepper.Activity 1: Train AI models to analyze UAV imagery and detect: (i) uprooted (fallen) trees; (ii) damaged and broken tree limbs; (iii) damaged tomato/pepper plants; (iv) flooding areas; and potentially (v) defoliation (canopy density and health).Activity 2: Train AI models to analyze AgroSense imagery and detect fallen fruit (aka, fruit drops) and detect disease spread (e.g., citrus canker).Objective 2: Evaluate this novel technology in commercial fields in collaboration with growers and a crop insurance company. Collect data from at least 20,000 acres of citrus, tomato, and pepper fields. Develop an extension program to demonstrate the impact of extreme weather events and the novel rapid response tool.Activity 3: Utilize this novel technology to assess damages on at least 20,000 acres of citrus, tomato, and pepper fields in collaboration with growers and a crop insurance company. Data will be collected immediately (10,000 to 15,000 acres within 3 months) and after 6-8 months (with 20% on same fields to assess changes on plant development) to assess the longer impact of the Extreme Weather Event.Activity 4: Develop an extension program to rapidly respond to extreme weather events. Conduct a feasibility study (cost-benefit analysis) of the proposed technology.

Progress 02/01/23 to 01/31/24

Outputs
Target Audience:Specialty crop growers and allied industry; students and faculty, extension agents. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?One PhD student, one intern, and two faculty attended and presented at the 2nd AI in Agriculture Conference: Innovation and Discovery to Equitably Meet Producer Needs and Perceptions in Orlando, FL, on April 17-19, 2023. Two post-doctoral research associates and one faculty attended and presented at the 3rd Annual AI in Agriculture and Natural Resources Conference in College Station, TX, on April 15-17, 2024. How have the results been disseminated to communities of interest?Dr. Ampatzidis (and team) presented findings of this project in several extension, educational, and outreach venues, including: AI and remote sensing for precision crop management. Center for Remote Sensing, IFAS/UF, April 26, 2024. AI and robotics in agriculture. AI In-service-training (IST), Wimauma, FL, April 9, 2024. AI applications for crop monitoring and predictive analytics. (co-presented with Dr. Congliang Zhou). AI In-service-training (IST), Wimauma, FL, April 9, 2024. Robotics and AI for vegetable production. Florida Citrus Show, Fort Pierce, FL, April 3, 2024. AI-enabled technologies for precision crop management. Hort3213 Fruit and Nut Production, Oklahoma State University, February 26, 2024. Robotics, automation, and AI for specialty crops. Florida AgTech and AI Expo, Punta Gorda, FL, December 14, 2023. Potential technologies to maximize drone use. South Florida Veg Growers Meeting: Whitefly Management, Immokalee, FL, November 29, 2023. AI-enabled technologies for precision management of specialty crops. USDA ARS-Northeast Area retreat, November 14, 2023. Drones and AI for Precision Crop Management. Florida Ag Expo, Gulf Coast Research and Education Center, Wimauma, FL, November 9, 2023. Artificial intelligence enhanced technology for precision citrus production. Cold Hardy Citrus Field Day, Quincy, FL, October 26, 2023. Artificial intelligence for precision orchard management. Citrus Expo, Tampa, FL, August 16-17, 2023. Artificial Intelligence and precision agriculture in vegetable production. Citrus Show, Vegetable Session, Fort Pierce, April 13, 2023. UAVs, Sensors, & Other Applied Research Technology. Research Center Administrators Society (RCAS) Meeting, Gulf Coast REC, February 6, 2023. What do you plan to do during the next reporting period to accomplish the goals? Nothing Reported

Impacts
What was accomplished under these goals? Data were collected in around 18,000 acres from aerial (unmanned aerial vehicles-UAVs, and airplanes) and ground (Agrosense) sensing platforms equipped with RGB, RGB-D, and multispectral cameras in citrus and vegetable production areas in Florida affected by Hurricane Ian. Data were collected before and after Hurricane Ian. The data were analyzed and visualized on Agroview (AI- and cloud-based technology). Agroview's artificial intelligence (AI) models were trained on aerial images (from UAVs and airplanes) and developed further to detect damages to specialty crops caused by extreme weather events (aka Hurricane Ian). More specifically, the AI models were trained to detect uprooted (fallen) trees, flooding areas, and defoliation (canopy density and health). Agrosense's (ground-based sensing platform) were trained to detect damaged and broken tree limbs, defoliation (canopy density and health), and damaged vegetable plants (e.g., tomato and pepper). An extension and outreach program was established to present this new technology to our stakeholders. It is expected that this novel technology could help specialty crop growers and crop insurance companies to rapidly calculate losses and better communicate recovery needs to ensure business viability and minimize interruption to the U.S. produce supply chain due to unexpected weather and climatic events.

Publications

  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Vijayakumar V., Ampatzidis Y., Costa L., 2023. Tree-level Citrus Yield Prediction Utilizing Ground and Aerial Machine Vision and Machine Learning. Smart Agricultural Technology, 100077, https://doi.org/10.1016/j.atech.2022.100077.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Hariharan J., Ampatzidis Y., Abdulridha J., Batuman O., 2023. An AI-based spectral data analysis process for recognizing unique plant biomarkers and disease features. Computers and Electronics in Agriculture, 204, 107574, https://doi.org/10.1016/j.compag.2022.107574.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Javidan S.M., Banakar A., Vakilian K.A., Ampatzidis Y., 2023. Tomato leaf diseases classification using image processing and weighted ensemble learning. Agronomy Journal, http://doi.org/10.1002/agj2.21293.
  • Type: Journal Articles Status: Under Review Year Published: 2024 Citation: Javidan S.M., Banakar A., Vakilian K.A., Ampatzidis Y., Rahnama K., 2024. Promising approach for crop health monitoring: Early detection and spectral signature identification of tomato fungal diseases by RGB and Hyperspectral image analysis and machine learning. European Journal of Agronomy (under review)
  • Type: Conference Papers and Presentations Status: Other Year Published: 2024 Citation: 1. Ampatzidis Y., 2024. Can AI and automation transform specialty crop production? 16th International Conference on Precision Agriculture (ICPA), International Symposium on robotics and Automation, Manhattan, Kansas, USA, July 21-24. 2. Zou C. and Ampatzidis Y., 2024. AI-enabled 3D vision system for rapid and accurate tree trunk detection and diameter estimation. 16th International Conference on Precision Agriculture (ICPA), Manhattan, Kansas, USA, July 21-24. 3. Ampatzidis Y. and Lacerda C., 2024. Agroview: enhance satellite imagery using super-resolution and generative AI for precision management in specialty crops. AgEng International Conference of EurAgEng, Agricultural Engineering Challenges in Existing and New Agrosystems, Athens, Greece, July 1-4, 2024. 4. Trentin C., Lacerda C.M.F., Shiratsuchi L., Ampatzidis Y., 2024. AI in orchard: improving sustainability through predictive yield in trees. 3rd Annual AI in Agriculture and Natural Resources Conference, College Station, TX, April 15-17, 2024.https://doi.org/10.1109/QICAR61538.2024.10496652 5. Ampatzidis Y., 2024. Agroview and Agrosense for AI-enhanced precision orchard management. SE Regional Fruit and Vegetable Conference, Savannah, GA, January 11-14, 2024 6. Ampatzidis Y., 2023. AI-Enhanced Technologies for Precision Management of Specialty Crops. Sustainable Precision Agriculture in the Era of IoT and Artificial Intelligence, Bard Ag-AI Workshop, Beer Sheva, Israel, July 18-20, 2023. 7. Ampatzidis Y., 2023. Solutions to critical issues facing field and specialty crop production. Integrative Precision Agriculture  Local Solutions Through Global Advances International Conference, Athens, Georgia, May 18-19, 2023. 8. Hariharan J., Ampatzidis Y., Abdulridha J., Batuman O., 2023. An AI-Based Spectral Data Analysis Process for Recognizing Unique Plant Biomarkers and Disease Features. AI in Agriculture Conference: Innovation and Discovery to Equitably meet Producer Needs and Perceptions, Orlando, FL, April 17-19, 2023. 9. 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. 10. Liu W. and Ampatzidis Y., 2023. Mapping citrus orchards utilizing aerial imagery with Agroview and Lidar. AI in Agriculture Conference: Innovation and Discovery to Equitably meet Producer Needs and Perceptions, Orlando, FL, April 17-19, 2023.