Source: UNIVERSITY OF FLORIDA submitted to NRP
PRECISION PEST AND DISEASE MANAGEMENT IN SPECIALTY CROPS
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
COMPLETE
Funding Source
HATCH
Reporting Frequency
Annual
Accession No.
1015586
Grant No.
(N/A)
Cumulative Award Amt.
(N/A)
Proposal No.
(N/A)
Multistate No.
(N/A)
Project Start Date
Feb 20, 2018
Project End Date
Feb 11, 2023
Grant Year
(N/A)
Program Code
[(N/A)]- (N/A)
Recipient Organization
UNIVERSITY OF FLORIDA
G022 MCCARTY HALL
GAINESVILLE,FL 32611
Performing Department
Southwest Florida Research and Education Center, Immokalee
Non Technical Summary
In this project, we propose to develop an automated vision-based system to detect diseases and pests in the field, utilizing a variety of sensors (e.g. multispectral and hyperspectral cameras) and artificial intelligence (AI). The proposed system would substantially improve the ability to detect pests and diseases compared with the current technologies. It will automatically detect plant diseases and discriminate them from other disorders or pathogens, despite the strong similarities. It will cost-effectively detect and geo-locate weeds and pests and generate a prescription map (compatible with precision equipment) for variable rate application of agrochemicals. It can be used as a scouting tool, and it can be integrated with smart sprayers to apply agrochemicals (in real-time) only where needed. This optimal use of agrochemicals will decrease chemicals usage and expenses, minimize the negative environmental impact and produce safer fruit and vegetables.
Animal Health Component
60%
Research Effort Categories
Basic
10%
Applied
60%
Developmental
30%
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
4027210202060%
2160999202040%
Knowledge Area
216 - Integrated Pest Management Systems; 402 - Engineering Systems and Equipment;

Subject Of Investigation
0999 - Citrus, general/other; 7210 - Remote sensing equipment and technology;

Field Of Science
2020 - Engineering;
Goals / Objectives
Objective 1: Develop a smart pest and disease detection system (SPDD).Objective 2: Develop an automated and smart precision sprayer.Objective 3: Conduct comprehensive economic analyses and evaluate consumer acceptance of the proposed system.
Project Methods
Objective 1: Smart pest and disease detection system (SPDD).Develop and train deep-learning convolutional neural networks (DL-CNNs) with a novel abstraction-level data fusion algorithm to distinguish, identify, and geo-locate pest and diseases using data from multiple cameras (e.g. RGB, multispectral, hyperspectral, thermal). We will train the DL-CNNs to recognize weeds, diseases, insects and crop size/growth using thousands of digital images and other data from other sensors.Utilize artificial intelligence (AI) to develop an intelligent, automated and on-board vision-based detection system (including a hand-held device). An embedded high-speed microprocessor equipped with graphics processing units (GPUs) and several sensors will be used.Initial the AI will be trained to detect: (i) ACP in citrus; ii) whiteflies in tomato; (iii) mites in strawberry; (iv) CBS in citrus; (v) Grapevine Yellows and Grapevine Pierce's disease in grapes; (vi) fusarium, late blight and target spot in tomato; vii) common broadleaf weeds of strawberry.Objective 2: Automated and smart precision sprayer.Integrate the SPDD system with a variable rate, target-based, precision equipment to apply agrochemicals, in real-time, only where needed. The smart sprayer would be a mobile vehicle, an aerial system (e.g. Unmanned Aerial Vehicle-UAV) or a stationary pest trap.Evaluate the proposed integrated system on commercial fields and develop an outreach to extend technology to growers and other clientele. The performance of the proposed system will be evaluated on experimental and commercial fields.Objective 3: Conduct comprehensive economic analyses and evaluate consumer acceptance of the proposed system.The proposed technology will be compared to conventional methods and cost-benefit economic assessments will be conducted. We will survey specialty crop growers as to their likelihood of adopting the proposed system.

Progress 10/01/18 to 09/30/19

Outputs
Target Audience:The Florida agricultural industry, specifically growers and production managers, extension agents, other researches, and Florida's citizens. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?Three Ph.D. students and a post doctoral research associate were trained to develop remote sensing technologies and smart spraying systems utilizing machine vision and artificial intelligences. They published their project finding in high level peer-reviewed journals. How have the results been disseminated to communities of interest?We have presented our finding in several conferences (see publication list), field days and workshops. Some examples are: Abdulridha J., Ampatzidis Y., Qureshi J., 2020. Remote sensing technique to identify and detect three tomato diseases: bacterial spot, target spot, and tomato yellow leaf curl virus in the field. 2020 ASABE Annual International Meeting, Omaha, Nebraska, July 12-15, 2020. Abdulridha J., Ampatzidis Y., Kanissery R., 2020. Combining steam application with herbicides: an integrated weed management strategy in citrus for reducing the chemical footprint. 2020 ASABE Annual International Meeting, Omaha, Nebraska, July 12-15, 2020. Hariharan J., Ampatzidis Y., Abdulridha J., 2020. The Basis for development of a foundational biomarker reflectance signature database system for plant cell identification, disease detection, and classification purposes. 10th Annual Computing and Communication Workshop and Conference, IEEE CCWC, Las Vegas, NE, USA, January 6-8, 2020. Abdulridha J., Ampatzidis Y., Roberts P. and Kakarla S., 2020. Detecting and monitoring the progress of powdery mildew disease in squash using hyperspectral imaging and artificial neural networks. Proceeding at the International Symposium on Artificial Intelligence and Mathematics (ISAIM). Fort Lauderdale, FL. January 6-8, 2020. Partel V., Kim J., Costa L., Pardalos P. and Ampatzidis Y., 2020. Smart Sprayer for Precision Weed Control Using Artificial Intelligence: Comparison of Deep Learning Frameworks. Proceeding at the International Symposium on Artificial Intelligence and Mathematics (ISAIM). Fort Lauderdale, FL. January 6-8, 2020. Partel V., Nunes L., and Ampatzidis Y., 2019. Automated system for monitoring Asian citrus psyllid in orchards. 2019 Annual Conference and Trade Show, Florida American Society of Agricultural and Biological Engineers (FASABE). Delray Beach, Florida, June 26-29, 2019. Ampatzidis Y., and Partel V., 2019. Smart Sprayer for Precision Weed Management Utilizing Machine Vision and Artificial Intelligence. 132th Florida State Horticultural Society Annual Meeting, Orlando, June 9-11, 2019. Ampatzidis Y., 2020. Precision and smart spraying technology for vegetables. Vegetable Growers Meeting, SWFREC, Immokalee, August 20, 2020. Ampatzidis Y., 2020. Emerging technologies for vegetables. Vegetable and Specialty Crop Virtual Meeting, August 13, 2020. Ampatzidis Y., 2020. Precision and variable rate spraying and fertilizer applications. Virtual Ag BMP summit (Webinar), June 16, 2020. Ampatzidis Y., 2020. Emerging technologies for precision management in vegetables. SWFREC Vegetable Webinar, May 28, 2020. Partel V., and Ampatzidis Y., 2020. Machine vision and deep learning techniques for precision weed management. Precision Agriculture Webinar Series, Alabama Extension, May 21, 2020. Ampatzidis Y., 2020. Precision Farming Techniques for Citrus Production. 2020 Florida Citrus Show, Fort Pierce, January 23, 2020. Ampatzidis Y., 2020. Emerging Technologies for Specialty Crops. SWFREC Foundation Board Meeting. Southwest Florida Research and Education Center (SWFREC), Immokalee, January 21, 2020. Ampatzidis Y., 2019. Artificial Intelligence Applications in Agriculture. HOS Seminar, Horticultural Science Department, Gainesville, Fl, October 7, 2019. What do you plan to do during the next reporting period to accomplish the goals?We plan to continue developing remote sensing techniques for disease and pest detection, and smart farming technologies for precision pest management.

Impacts
What was accomplished under these goals? Several remote sensing techniques were developed to detect bacterial spot, target spot, and tomato yellow leaf curl virus in tomato fields, and powdery mildew disease in squash utilizing artificial intelligence and UAV-based hyperspectral imaging. Several papers were published in high quality refereed journals. An upgraded smart technology for precision pest management utilizing machine vision and artificial intelligence was developed (version 2). Initial designs and results helped us develop and submit a proposal to National Robotic Initiative (NRI), Nasional Research Foundation (NSF), entitled: "NRI: INT: COLLAB: High Throughput Multi-Robot Weed Management for Specialty Crop". This proposal was selected for funding (duration: 04/01/2020 - 03/31/2024). The proposed smart technology can distinguish target weeds from non-target objects (e.g. vegetable crops), with accuracy of more than 90%, and precisely spray on the desired target/location. It integrates a state of the art (AI-based) weed detection system with a novel fast and precision spraying system, and can significantly reduce the quantity of agrochemicals applied, especially compared with traditional broadcast sprayers. A paper describing this novel technology was published in the Computers and Electronics in Agriculture journal.

Publications

  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Hariharan J., Ampatzidis Y., Abdulridha J., 2020. The Basis for development of a foundational biomarker reflectance signature database system for plant cell identification, disease detection, and classification purposes. 10th Annual Computing and Communication Workshop and Conference, IEEE CCWC, Las Vegas, NE, USA, January 6-8, 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Partel V., Kim J., Costa L., Pardalos P. and Ampatzidis Y., 2020. Smart Sprayer for Precision Weed Control Using Artificial Intelligence: Comparison of Deep Learning Frameworks. Proceeding at the International Symposium on Artificial Intelligence and Mathematics (ISAIM). Fort Lauderdale, FL. January 68, 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2019 Citation: Partel V., Nunes L., and Ampatzidis Y., 2019. Automated system for monitoring Asian citrus psyllid in orchards. 2019 Annual Conference and Trade Show, Florida American Society of Agricultural and Biological Engineers (FASABE). Delray Beach, Florida, June 26-29, 2019.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2019 Citation: Ampatzidis Y., and Partel V., 2019. Smart Sprayer for Precision Weed Management Utilizing Machine Vision and Artificial Intelligence. 132th Florida State Horticultural Society Annual Meeting, Orlando, June 9-11, 2019.
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: Abdulridha J., Ampatzidis Y., Qureshi J., Roberts P., 2020. Laboratory and UAV-based identification and classification of tomato yellow leaf curl, bacterial spot, and target spot diseases in tomato utilizing hyperspectral imaging and machine learning. Remote Sensing, 12(17), 2732; doi:10.3390/rs12172732.
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: Abdulridha J., Ampatzidis Y., Roberts P., Kakarla S.C., 2020. Detecting powdery mildew disease in squash at different stages using UAV-based hyperspectral imaging and artificial intelligence. Biosystems Engineering, 135-148; doi.org/10.1016/j.biosystemseng.2020.07.001.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Abdulridha J., Ampatzidis Y., Roberts P. and Kakarla S., 2020. Detecting and monitoring the progress of powdery mildew disease in squash using hyperspectral imaging and artificial neural networks. Proceeding at the International Symposium on Artificial Intelligence and Mathematics (ISAIM). Fort Lauderdale, FL. January 68, 2020.
  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Abdulridha J., Ampatzidis Y., Kakarla S.C., Roberts P., 2019. Detection of target spot and bacterial spot diseases in tomato using UAV-based and benchtop-based hyperspectral imaging techniques. Precision Agriculture, (November) 1-24.
  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Abdulridha J., Kanissery R., McAvoy C., Ampatzidis Y., 2019. Evaluation of Steam Application for Weed Management in Citrus Groves. Applied Engineering in Agriculture, 35(5), 805-814, doi: 10.13031/aea.13494.
  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Hariharan J., Fuller J., Ampatzidis Y., Abdulridha J., Lerwill A., 2019. Finite Difference Analysis and Bivariate Correlation of Hyperspectral Data for Detecting Laurel Wilt Disease and Nutritional Deficiency in Avocado. Remote Sens. 2019, 11(15), 1748; https://doi.org/10.3390/rs11151748.
  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Abdulridha J., Batuman O., Ampatzidis Y., 2019. UAV-based Remote Sensing Technique to Detect Citrus Canker Disease Utilizing Hyperspectral Imaging and Machine Learning. Remote Sensing, 11(11), 1373.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Abdulridha J., Ampatzidis Y., Qureshi J., 2020. Remote sensing technique to identify and detect three tomato diseases: bacterial spot, target spot, and tomato yellow leaf curl virus in the field. 2020 ASABE Annual International Meeting, Omaha, Nebraska, July 12-15, 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Abdulridha J., Ampatzidis Y., Kanissery R., 2020. Combining steam application with herbicides: an integrated weed management strategy in citrus for reducing the chemical footprint. 2020 ASABE Annual International Meeting, Omaha, Nebraska, July 12-15, 2020.


Progress 02/20/18 to 09/30/18

Outputs
Target Audience:This reporting period the target audiences were the Florida agricultural industry, specifically growers and production managers, extension agents, other researches, and Florida's citizens. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?Three Ph.D. students and a post doctoral research associate were trained to develop remote sensing technologies and smart spraying systems utilizing machine vision and artificial intelligences. They published their project finding in high level peer-reviewed journals. How have the results been disseminated to communities of interest?We have presented our finding in several conferences (see publication list), field days and workshops. Some examples are: Ampatzidis Y., and Cruz A.C., 2018. Plant disease detection utilizing artificial intelligence and remote sensing. International Congress of Plant Pathology (ICPP) 2018: Plant Health in a Global Economy, July 29 - August 3, Boston, USA. Ampatzidis Y., 2018. UAV applications for specialty crops. XXX International Horticultural Congress, II International Symposium on Mechanization, Precision Horticulture, and Robotics, UAV workshop, 12-16 August, 2018, Istanbul Turkey. Ampatzidis Y. SmartAg and New Technologies for Specialty Crops, 2018. Vegetable field day, Hasting, FL, December 13, 2018 Ampatzidis Y. Smart Agriculture and Smart Machinery, 2018. Vegetable field day, Immokalee, FL, November 29, 2018. Ampatzidis Y. Precision Agriculture: Technology Applicable to Small Farms, 2018. Sustainable Ag and Food Systems Sharing, East Palatka, Florida, Nov 28. Ampatzidis Y. Precision Farming Technologies for Specialty Crops, 2018. Florida Ag Expo, Balm, Florida, November 7, 2018. Ampatzidis Y. Smart Agriculture and Artificial Intelligence, 2018. UF Biocomplexity group, Gainesville FL, October 16, 2018. Ampatzidis Y. New Technologies in Agriculture for Specialty Crops, 2018. Citrus Engineering Conference, Panel Session, Lake Alfred, FL, June 6, 2018. Ampatzidis Y. Remote Sensing for Citrus Disease Detection, 2018. Citrus Black Spot Workshop, Immokalee, Fl., May 7, 2018. Ampatzidis Y. Agricultural and Biological Engineering Technology Applied to Citrus Crops, 2018. Citrus Health Forum, NFREC, Quincy Fl., April 19, 2018. Ampatzidis Y. Smart Machines, UAV and Precision Farming Technologies, 2018 Citrus Innovation and Technology Show. Arcadia, Florida, April-5, 2018. Ampatzidis Y. Use of Precision Agricultural Technology for Water and Nutrient Best Management Practices, 2018. Best Management Practices, In-Service Training, Gainesville, Fl., February 22, 2018. Ampatzidis Y. Agricultural engineering technologies to improve citrus production, Citrus Show, Fort Pierce, Florida, Jan-24, 2018. Ampatzidis Y. Precision Agriculture for Specialty crops, 2018. Graduate Student Organization, Immokalee, Fl., February 27, 2018. What do you plan to do during the next reporting period to accomplish the goals?We plan to continue developing remote sensing techniques for disease and pest detection, and smart farming technologies for precision pest management.

Impacts
What was accomplished under these goals? A remote sensing technique was develop to detect laurel wilt disease in avocado in presence of other biotic and abiotic stresses. Two papers were published in the Computers and Electronics in Agriculture Journal. Additionally, a machine vision system was developed for the detection of grapevine yellows and grapevine Pierce's disease utilizing artificial intelligence. A journal paper was published to present findings of this work. A smart technology for precision pest management utilizing machine vision and artificial intelligence was developed too. Farmers use mainly herbicides for weed management and follow conventional crop protection strategies (utilizing a vast amount of chemicals) regardless of the negative impacts on the environment and human health. Almost all herbicide applications are made uniformly with conventional spraying equipment, despite the fact that distribution of weeds is typically patchy, resulting in increased input costs, increased risk of crop damage, pest resistance to chemicals, environmental pollution and contamination of products. This smart technology can distinguish target weeds from non-target objects (e.g. vegetable crops), with accuracy of more than 90%, and precisely spray on the desired target/location. It integrates a state of the art (AI-based) weed detection system with a novel fast and precision spraying system, and can significantly reduce the quantity of agrochemicals applied, especially compared with traditional broadcast sprayers.

Publications

  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Partel V., Kakarla S.C., and Ampatzidis Y., 2019. Development and Evaluation of a Low-Cost and Smart Technology for Precision Weed Management Utilizing Artificial Intelligence. Computers and Electronics in Agriculture, 157 (February 2019), 339-350.
  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Abdulridha J., Ehsani R., Abd-Elrahman A., Ampatzidis Y., 2019. A Remote Sensing technique for detecting laurel wilt disease in avocado in presence of other biotic and abiotic stresses. Computers and Electronics in Agriculture, 156 (January 2019), pp. 549-557.
  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Cruz A., Ampatzidis Y., Pierro R., Materazzi A., Panattoni A., De Bellis L., Luvisi A., 2019. Detection of Grapevine Yellows Symptoms in Vitis vinifera L. with Artificial Intelligence. Computers and Electronics in Agriculture, 157 (February 2019), pp. 63-76.
  • Type: Journal Articles Status: Published Year Published: 2018 Citation: Abdulridha J., Ampatzidis Y., Ehsani R., de Castro A., 2018. Evaluating the Performance of Spectral Features and Multivariate Analysis Tools to Detect Laurel Wilt Disease and Nutritional Deficiency in Avocado. Computers and Electronics in Agriculture, Vol. 155, Dec 2018, pp. 203-2011.
  • Type: Conference Papers and Presentations Status: Accepted Year Published: 2019 Citation: Ampatzidis Y., and Partel V., 2019. Precision Weed Management in Vegetables Utilizing Artificial Intelligence. XXXVII CIOSTA and CIGR International Conference, June 24-26, Rhodes, Greece.
  • Type: Conference Papers and Presentations Status: Accepted Year Published: 2019 Citation: Ampatzidis Y., and Partel V., 2019. Low-cost and automated remote sensing technology to assess fruit crops utilizing machine vision and artificial intelligence. European Federation for Information Technology in Agriculture, Food and the Environment (EFITA-HAICTA-WCCA Congress), June 27-29, Rhodes, Greece.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2018 Citation: Ampatzidis Y, 2018. Machine Learning and Artificial Intelligence for Pest and Plant Disease Detection. Florida ASABE Conference, June 13-16, Jensen Beach, Florida.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2018 Citation: Cruz A.C., El-Kereamy A., and Ampatzidis Y., 2018. Vision-based Grapevine Pierces disease detection system using artificial intelligence. ASABE Annual International Meeting, July 29  August 1, Detroit, Michigan, USA.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2018 Citation: Ampatzidis Y., and Cruz A.C., 2018. Plant disease detection utilizing artificial intelligence and remote sensing. International Congress of Plant Pathology (ICPP) 2018: Plant Health in a Global Economy, July 29  August 3, Boston, USA.