Brief Summary of Minutes of Annual Meeting

Brief Summary of Minutes of Annual Meeting

Meeting Summary:

2023-06-20

8:30 AM – Meeting called to order (Yu Jiang)

8:30 AM to 8:45 AM – Attendee introduction

8:45 AM to 9:15 AM – Welcome address by Dr. Olga I. Padilla-Zakour, interim director of Cornell AgriTech

9:15 to noon – Business meeting

• Summary of 2022 meeting/reports approved.
• New secretary nominated and approved: Yuzhen Lu
• W4009 renewal update
  • Proposal development led by Dr. Stavros Vougioukas and submitted the initial proposal on 2023-01-23. Proposal duration is from 2023-10-01 to 2028-09-30.
  • Positive comments received on 2023-04-17, and major suggestions were to improve participation across the US.
  • Revised proposal submitted on 2023-05-24, with 27 participants from 13 states.
  • Waiting for the final approval from USDA NIFA.
• Meeting location and time in 2024
  • Potential locations: Michigan, Florida, Texas, Hawaii (preferred due to its tropical fruit industry), and Alaska.
  • The coming W4009 chair (Hao Gan) will work with a team to finalize the schedule.
• Announcements
  • NIFA report by Dr. Steven Thomson
    • Expand AI program, small- to medium-scale with focus on connection to MSI
    • New USDA/NSF FRR program to replace the previous NRI
    • NIFA/NSF CPS program
    • AFRI A1521/A1541 have been very competitive.
  • Special Issue from Computer and Electronics in Agriculture (IF 8.3)
    • A special topic on specialty crop engineering. Application deadline: 2023-12-31, minimum 15 papers per special issue.
    • Add acknowledgement to the W3009 and other programs supporting specialty crop engineering.
  • FIRA conference: https://fira-usa.com/
  • Cornell CIDA Hackathon: https://digitalaghackathon.com/
• Collaboration opportunity
  • A conference on specialty crop engineering

12:00 PM to 1 PM – Lunch

1:00 PM to 5:00 PM – Institute report presentations

5:05 PM – Adjourned the meeting.

Arizona

• A new, energy-saving steam applicator effectively kills weed seeds before planting. Trials in spinach yielded excellent broadleaf weed control (>80%) and drastically cut manual weeding time (>80%), performing better than untreated controls. The tool's work rates and fuel costs were reasonable, even at a slow 0.15 mph speed, achieving 0.10 ac/hr and $800/ac.
• A novel, low-cost electronic monitoring system of high temporal resolution in-situ soil respiration was developed, and an invention disclosure was filed on the device.

California

• A prototype was built to measure the yield of individual almond trees during mechanical harvesting with off-ground harvesters. The system does not require the harvester to stop; instead, it measures the volume of the almonds inline, as they are transported on the conveyor belts of a commercial harvested (TOL company). Thus, the system is compatible with commercial harvesting machines and procedures that implement high-speed harvesting at commercial scale.
• Developed a fully automated almond yield mapping prototype system. The system comprised a 2D Lidar and an encoder to measure the almond pile profile and the speed of the belt respectively; an RTK-GPS to record harvester location; a vibration sensor to record the tree shaking time instants; an inertial sensor to record harvester motion. Software was developed to pre-process the data and combine the filtered and cleaned data from all the sensors to generate yield maps of the harvested almonds.
• Initiated the research and outreach program related to safety for robotics and emerging technologies in agriculture.
• Presented and co-organized the “Labor & Ergonomics for Emerging Technologies” session in the “Addressing Grand Challenges in the Produce Industry” workshop.
• Hosted a hybrid (virtual and in-person) applied extension workshop titled: “Addressing Grand Challenges in the Produce Industry”.
• Co-PI and Co-organizer of a workshop funded by USDA, AFRI ($50,000), titled “SAfety For Emerging Robotics and Autonomous aGriculture (SAFER AG)” that was held November 9-10, 2022, in Urbana, IL.
• Co-host a workshop titled “Emerging Technology in Agriculture: Keeping Health and Safety at the Forefront” on May 11, 2023, at UC Davis in California, to discuss the safety and health concerns for farmworkers related to robotics and new technologies in agriculture.
• Support ongoing development of a unique sensor system for in-field 3D plant phenotype measurements by introducing computer algorithms for automated, high-throughput phenotyping of Solanaceae crops like tomato and pepper. These machine learning and image processing algorithms successfully measure critical traits including the time to first open flower and first green fruit, requiring automatic detection in farm settings.
• Practical learning modules were created to train engineering graduate students in designing autonomous robots and sensors using machine learning to automate laborious tasks in specialty crop production. The modules cover edge computing, IoT, network dashboards, servo motor control for navigation, optical and acoustic sensors for object detection, machine vision for crop detection and fruit localization, path optimization, automated harvest, transport, and machine learning.
• A remote sensing model prototype was created to estimate grapevine leaf and canopy nitrogen levels using hyperspectral data, utilizing diverse data analytics methods like linear regression, machine learning, and physics-based modeling. A new hybrid method was developed, combining mechanistic trait retrieval outputs with advanced machine learning to improve model prediction accuracy and consistency.
• Machine learning techniques were used to i) map global irrigated area at high temporal and spatial resolution using satellite imagery, ii) evaluate irrigation water demand at county level and iii) to evaluate feature importance and to forecast reference evapotranspiration.
• Finalize editorial revisions for booklets, and extension type publication in topics related to fresh fruit and vegetable quality factors, their evaluation, and sensing of environmental conditions during the transport of refrigerated produce (Telematics).
• Initiated the development of non-invasive visual assessment tools, including cell-phone applications, to infer quality attributes of dry coffee beans. This is beneficial to both the consumer and producers of coffee in California as a specialty crop.

Florida

• Kadyampakeni: We also had two presentations for in-service training for extension agents and crop advisors. Two Ph.D. students completed their doctoral programs.
• Ampatzidis: Several disease detection and monitoring systems were developed for vegetable crops utilizing UAV-based hyperspectral imaging and machine learning. These technologies were able to classify several severity stages of the diseases.
• Ampatzidis: An AI-enabled yield prediction system was developed for citrus using aerial and ground sensing systems.
• Ampatzidis: An AI-enhanced technique was developed to determine citrus leaf nutrient concentration utilizing UAV multispectral imaging.
• Ampatzidis: A smart tree crop sprayer was developed using sensor fusion and artificial intelligence.
• Choi: This year, we successfully developed a computer vision-based and comprehensive strawberry crop load prediction system for yield forecasting. This system incorporated machine learning algorithms, sensor technology, and data analysis to predict harvest amounts throughout the growing season.
• Choi: We have made significant progress in a project aimed at modernizing the manual mite release methods in strawberry farming. We have successfully built the first prototype of this mechanism, enhancing the precision of mite deployment in pest control. We have identified areas that require improvement to increase the overall system efficiency.
• Lee: A smartphone app and a portable imaging device were developed to detect two-spotted spider mites using artificial intelligence. An autonomous vehicle navigation method was developed to improve the accuracy and robustness of existing fusion algorithms by taking information from a camera, IMU, and GPS receiver and fusing them through nonlinear batch optimization.

Kentucky

• We used data collected from Aquaculture projects to determine the appropriate sizing for solar systems to ensure continuous, remote power for various daily system electrical loads. Various configuration options were also considered.

Michigan

• Multi-class weed detection datasets were created and made publicly available to the research community to accelerate developing robust machine vision-based weed recognition systems. Accompanied with the open datasets were large suites of weed detection benchmarking models that are publicly accessible.
• Open-source graphical software was developed for weed imagery and real-time weed detection.
• Blueberry fruit detection models were built to assist in harvest decision making.

Mississippi

• The team evaluated a newly designed real-time moisture sensor system for cotton gin. Results showed that the system was sufficiently robust for real-time application with sufficient repeatability. Additional experiments are planned for the 2023 season to determine alternate configurations and to improve sensitivity.
• The team developed a computer vision system to detect blackberries accurately and efficiently in the orchards, which will be utilized for soft robotic harvesting tasks in real-time. A dual-camera system is under development for better detection and localization purposes due to the small size of the target fruit. The graduate student working on this project won the Best Student Paper Award at SPIE conference in Orlando, FL.
• The team developed an automated image processing pipeline to map the bloom of almond trees to early forecast the yield of almond trees using UAV-based approach. The proposed approach was compared against the previously developed method by other researchers, enhanced bloom index (EBI), and satellite-based method. Results showed our approach is promising to estimate the almond yield during bloom stage.
• The team developed a computer vision system to detect wine grape bunches accurately, which will be utilized for crop load estimation for the growers in the vineyards. The proposed model was the combination of YOLOv5 and Swin-transformer to perform more efficiently.

New York

• Developed and deployed PhytoPatholoBot (PPB) in multiple grape production regions and breeding programs in the US to demonstrate autonomous disease scouting for genetics studies, breeding programs, and precision disease management.
• Developed and deployed an attachable implement of UV treatment to trellised crops such as grapes, apples, and strawberries, which has attracted attention worldwide.
• The team has utilized outcomes from the W3009 and collaborated with other state researchers to successfully secure additional funding support (NASA Acres and USDA SCRI VitisGen 3) for specialty crop engineering.

Pennsylvania

• A robotic apple blossom thinning system was develop with integration of an unmanned ground vehicle, a 3D machine vision system, a solenoid valve controlled- nozzle control system, and a RTK-GPS based localization system. A series of field test was conducted in the spring of 2023, and the results showed that the robotic blossom thinning system achieved targeted blossom thinning with more than 50% of chemical reduction and similar thinning performance by comparing to conventional air-blast sprayer.
• An integrated robotic green fruit thinning system was developed and tested in apple orchards. The system includes a 3D machine vision system (detection and localization), a UR5 robotic manipulator, a stem cutting end-effector, and a collision-free path planning algorithm. Field test showed that the robotic system successfully removed 87.5% of targeted fruits in the clusters.
• Continued to develop deep learning-based models for early apple bud detection and localization, and achieved over 90% accuracy for bud detection in orchard environment. Two types of end-effectors were developed and tested in the field for excessive bud removal. The test showed that the two end-effectors can remove flower buds at an early stage, while the scissor-type performed better in terms of efficiency.
• A computational fluid dynamic model was developed to determine the effects of wind speed and wind direction on static and mobile heating of the orchard. Utilizing the concept of “percentage of protected canopy (PPC)”, the simulation model was used to assess which heater scenarios would provide the maximum PPC. A mobile heater was mounted on the UGV, and field tests showed the advantage of using wind adapted heater angle control can improve heating efficiency significantly.
• Fully integrated, autonomous multi-agent frost protection system communications were in development. This provides the real-time capture of thermal images, transfer to a base station, execution of the path planning algorithm, and signal to the UGV to move to the destination for heating using the optimal path, without collisions and within acceptable navigation error. The calculated deviation of the UGV from the proposed path was 3.44 cm RMS error latitudinally and 8.28 cm longitudinally. The mean computational time for creating the paths was 7.85 seconds.
• Continued the field tests with the developed precision irrigation and precision spraying systems in the apple orchards and vegetable fields for various purposes. Especially, both precision irrigation and spraying technologies have been attracting attention from tree fruit and vegetable growers. We have worked with more than 10 growers for irrigation sensor setup, and there are about 5 growers in the area have been or are about to adopt the precision spraying system.

Tennessee

• A mobile robot platform was built for Tennessee pot-in-pot nursery production. The chassis and motor control system was completed for 15-gallon pots. Currently, the robot can be remote controlled using a joystick. It includes two driving motors, two mechanical grippers to grab the 15-gallon pot, and two linear actuator to lift the pot.
• A robotic farm built in previous years has been used to grow tomato plants and for developing flower mapping algorithms. Top-view image data was collected automatically by the robot. Yolo models were applied to detect flowers and Pix4D was used to create a 3D map of the entire plant bed. This is a preliminary study with an end goal of creating a drone-based autonomous pollination system.

Texas

• A deep learning model was developed to detect bacterial wilt disease in greenhouse tomato crops. Over-amplification of the contrast due to uneven illumination is a major concern for color image-based disease detection systems. We used image enhancement algorithms to adjust the light and contrast in the images. A new deep-learning approach was used to train the features on the plant leaves in the images to develop the disease prediction algorithm. The system achieved more than 90% classification accuracy, advocating its implementation for site-specific crop management systems, including robotic spraying and disease watchdog.
• An end-to-end deep learning algorithm is developed for non-destructive measurements of hydroponic lettuce phenotypic traits. Different deep-learning approaches were tested to develop a lightweight model for deployment on edge devices. The results indicate that biomass, leaf area, dry weight, and plant height can be measured non-destructively with high accuracy (up to 95%). The developed algorithm can be deployed on edge devices for real-time crop growth monitoring.
• A review of AI and automation applications in CEA and the nursery industry was conducted, and the results were published in a scientific journal. The survey highlighted the status of technology development for CEA and the nursery industry. Also, it summarized the pros and cons of different AI models and automation techniques implemented for various tasks in CEA production.

Washington

• Integrated an automated green shoot thinning system with a commercial thinning machine for precision green shoot thinning in vineyards.
• Further improved a 12-armed robotic apple harvester and continued field evaluation of the harvester in commercial orchards.
• Further developed a machine-vision and robotic system for pruning apple and cherry trees. Vision system was advanced to accurately detect secondary branches in trees and recreate 3D structure of trees for effective pruning decisions.
• Integrated end-effector and vision system with a soft-robotic manipulator for apple picking and flower thinning.
• Evaluated cell-phone-based models for lag-phase detection and crop-estimation in vineyards.
• Developed a canopy density estimation method, a decision support system, and a precision application system for individual plant level nitrogen application in apple orchards.
• Developed and evaluated various methods for improved water, nitrogen, and phosphorus status assessment in wine grapes using ground-based hyperspectral imaging.
• Developed and evaluated a robotic system for pollination and green fruit thinning. Pollination. Robotic pollination system focused on identifying king flower and applying pollens precisely onto king flowers for targeted pollination. Robotic green fruit thinning has been investigated with various end-effectors including scissor cutter, claw-like mechanism, and vacuum suctioning.
• Optimized, automated fixed spray system (i.e., solid set chemical delivery system) configurations were tested to validate the biological efficacy in apple orchard orchards. System configurations were revised for their applicability in crop protection and heat stress mitigation in grapevines.
• Optimized intelligent sprayer spray rates to efficiently apply chemicals in modern apple orchards. The optimized systems are being tested for precision chemical blossom thinning in smart orchard blocks in the 2023 field season.
• The IoT-enabled Crop Physiology Sensing System (CPSS 3.0) was automated to mitigate heat stress in apple orchards, evaluating the effectiveness of different cooling and netting techniques. It also adapted for heat stress mitigation in VSP trained grapevines.
• Continual public-private partnership to establish smart orchard framework in commercial settings and develop data driven decision support for on-farm production management. WSU researched crop water use mapping solution has been translated to use for understanding crop water use (evapotranspiration) in smart apple orchard. The neutrality of the model was tested using manned aircraft collected arial imagery data.
• Developed and validated grapevine canopy vigor variation mapping solutions using aerial imagery data for in season decision support on canopy, irrigation management, precision crop protection, etc.

Arizona

Peer-reviewed Publications

• Raja, R., Slaughter, D.C., Fennimore, S.A. & Siemens, M.C. 2023. Real-time control of high-resolution micro-jet sprayer integrated with machine vision for precision weed control. Biosystems Eng. 228: 31-48.
• Guerra, N., Fennimore, S.A., Siemens, M.C., & Goodhue, R.E. 2022. Band steaming for weed and disease control in leafy greens and carrots. Sci. 57(11): 1453-1459.

Patents

• Heun J.T., Andrade-Sanchez P., & Sanyal D. 2023. Low-Cost Electronic Monitoring System of High Temporal Resolution In-Situ Soil Respiration. TLA Invention Disclosure UA23-221. Tucson, Ariz: Tech Launch Arizona, University of Arizona.
• Bahr, N. A., Siemens, M.C., Godinez, Jr., & Fennimore, S.A. 2022. Method and apparatus for applying steam for soil disinfestation. TLA Invention Disclosure UA22-190. Tucson, Ariz: Tech Launch Arizona, University of Arizona.

Book Chapters

• Fennimore, S.A. & Siemens, M.C. 2023. Mechanized weed management in vegetable crops. In Encyclopedia of Smart Agricultural Technologies, ed. Q. Zhang. Cham, Switzerland: Springer, Cham. https://doi.org/10.1007/978-3-030-89123-7_244-2.

California

Peer-reviewed Publications

• Tang M, Sadowski DL, Peng C, Vougioukas SG, Klever B, Khasla SDS, Brown PH and Jin Y. (2023). Tree-level almond yield estimation from high resolution aerial imagery with convolutional neural network. Front. Plant Sci. 14:1070699. https://doi.org/10.3389/fpls.2023.1070699
• Peng, C., Fei, Z., Vougioukas, SG. (2023). GNSS-Free End-of-Row Detection and Headland Manoeuvring for Orchard Navigation Using a Depth Camera. Machines 11(1), 84. https://doi.org/10.3390/machines11010084.
• Ghafoor, A., F. A. Khan, F. Khorsandi, M. A. Khan, H. M. Nauman, and M. U. Farid. Development and Evaluation of a Prototype Self-Propelled Crop Sprayer for Agricultural Sustainability in Small Farms. Sustainability, (2022), 14: 9204.
• Khan, F. A., A. Ghafoor, M. A. Khan, M. U. Chattha, and F. Khorsandi. Parameter Optimization of Newly Developed Self-Propelled Variable Height Crop Sprayer Using Response Surface Methodology (RSM) Approach. Agriculture, (2022), 12(3):408.
• Chou, H. Y., F. Khorsandi, S. G.Vougioukas, F. A.Fathallah . Developing and evaluating an autonomous agricultural all-terrain vehicle for field. experimental rollover simulations. Computers and Electronics in Agriculture, (2022), 194: 106735.
• Khorsandi, F., G. D. M. Araujo, and F. Fathallah. A systematic review of youth and all-terrain vehicles safety in agriculture. Journal of Agromedicine, (2022), 1-23.
• Araujo, G. D. M., F. Khorsandi, and F.A. Fathallah. Forces Required to Operate Controls on Agricultural All-Terrain Vehicles: Implications for Youth. Journal of Ergonomics, (2022), 1-15.
• Dos Santos FFL, de Queiroz DM, Valente DSM, Khorsandi F, de Moura Araújo G. Analysis of Different Electric Current Frequencies in Soil Apparent Conductivity. Journal of Biosystems Engineering, (2023), 1-14.
• Gibbs, J., C. Sheridan, F. Khorsandi*, A. Yoder. Emphasizing Safe Engineering Design Features of Quad Bikes in Agricultural Safety Programs. JASH, (2023), 29(2): 121-127.
• Araujo, G. D. M., F. Khorsandi, F. A. Fathallah. Reach Evaluation to Operate Controls on Agricultural All-Terrain Vehicles: Implications for Young Operators. Journal of Safety Research, (2023), 84: 353-363.
• Sirapoom Peanusaha, Alireza Pourreza, Yuto Kamya, Matthew Fidelibus. Grape Nitrogen retrieval by hyperspectral sensing–Part I: leaf level. Under review in the Journal of Remote Sensing of Environment.
• Yuto Kamya, Alireza Pourreza, Sirapoom Peanusaha, Hamid Jafarbiglu, Matthew Fidelibus. Grape Nitrogen retrieval by hyperspectral sensing–Part II: canopy level. In-preparation.
• Ahmadi A., Daccache A., Snyder R., Suvočarev K. (2022). Meteorological driving forces of reference evapotranspiration and their trends in California, Science of The Total Environment, 157823.
• Emami, M.; Ahmadi, A.; Daccache, A.; Nazif, S.; Mousavi, S.-F.; Karami, H. County-Level Irrigation Water Demand Estimation Using Machine Learning: Case Study of California. Water 2022, 14, 1937.

Florida

Peer-reviewed Publications

• Ghoveisi, H., M. Kadyampakeni, J. Qureshi, and L. Diepenbrock. 2023. Water use efficiency in young citrus trees on metalized UV reflective mulch compared to bare ground. Water 2023, 15, 2098. https://doi.org/10.3390/w15112098
• Kwakye, S. and M. Kadyampakeni. 2023. Impact of deficit irrigation on growth and water relations of HLB-affected citrus trees under greenhouse conditions. Water 15, 2085. https://doi.org/10.3390/w15112085
• Brewer, M. 2023. Citrus row-middle management using cover crops for suppressing weeds and improving soil. Ph.D. Dissertation, University of Florida, Gainesville, FL.
• Teshome F.T., Bayabil H.K., Hoogenboom G., Schaffer B., Singh A., Ampatzidis Y., 2023. Unmanned Aerial Vehicle (UAV) Imaging and Machine Learning Applications for Plant Phenotyping. Computers and Electronics in Agriculture, 212, 108064, https://doi.org/10.1016/j.compag.2023.108064.
• Zhou C., Lee W.S., Liburd O.E., Aygun I., Zhou X., Pourreza A., Schueller J.K., Ampatzidis Y., 2023. Detecting Two-spotted Spider Mites and Predatory Mites in Strawberry Using Deep Learning. Smart Agricultural Technology, 100229, https://doi.org/10.1016/j.atech.2023.100229.
• 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.
• 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.
• Momeny M., Neshat A.A., Jahanbakhshi A., Bakhtoor M.., Ampatzidis Y., Radeva P., 2023. Grading and fraud detection of Saffron via learning-to-augment incorporated inception-v4 CNN. Food Control, 109554, https://doi.org/10.1016/j.foodcont.2022.109554.
• Panta S., Zhou B., Zhu L., Maness N., Rohla C., Costa L., Ampatzidis Y., Fontainer C., Kaur A., Zhang, L., 2023. Selecting non-linear mixed effect model for growth and development of pecan nut. Scientia Horticulturae, 309, 111614, https://doi.org/10.1016/j.scienta.2022.111614.
• Poudyal C., Sandhu H., Ampatzidis Y., Odero D.C., Arbelo O.C., Cherry R.H., Costa L., 2023. Prediction of morho-physiological traits in sugarcane using aerial imagery and machine learning. Smart Agricultural Technology, 100104, https://doi.org/10.1016/j.atech.2022.100104.
• 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.
• Javidan S.M., Banakar A., Vakilian K.A., Ampatzidis Y., 2023. Diagnosis of grape leaf diseases using automatic K-means clustering and machine learning. Smart Agricultural Technology, 100081, https://doi.org/10.1016/j.atech.2022.100081.
• Momeny M., Jahanbakhshi A., Neshat A.A., Hadipour-Rokni R., Zhang Y-D., Ampatzidis Y., 2022. Detection of citrus black spot disease and ripeness level in orange fruit using robust and generalized deep CNN based on learning-to-augment strategy. Ecological Informatics, 101829, https://doi.org/10.1016/j.ecoinf.2022.101829.
• Zhou X., Ampatzidis Y., Lee W.S., Zhou C., Agehara S., Schueller J.K., 2022. Deep learning-based postharvest strawberry bruise detection under UV and incandescent light. Computers and Electronics in Agriculture, 22, 107389, https://doi.org/10.1016/j.compag.2022.107389.
• Longchamps L., Tisseyre B., Taylor J., Sagoo L, Momin Md.A., Fountas S., Manfrini L., Ampatzidis Y., Schueller K.J., Khosla R., 2022. Yield sensing technologies for perennial and annual horticultural crops: a review. Precision Agriculture, https://doi.org/10.1007/s11119-022-09906-2.
• Poudyal C., Costa L., Sandhu H., Ampatzidis Y., Odero D.C., Arbelo O.C., Cherry R.H., 2022. Sugarcane yield prediction and genotype selection using UAV-based hyperspectral imaging and machine learning. Agronomy Journal, doi.org/10.1002/agj2.21133.
• Abdulridha J., Ampatzidis Y., Qureshi J., Roberts P., 2022. Identification and classification of downy mildew development stages in watermelon utilizing aerial and ground remote sensing and machine learning. Frontiers in Plant Science, 13, 791018, https://doi.org/10.3389/fpls.2022.791018.
• Costa L., McBreen J., Ampatzidis Y., Guo J., Reisi Gahrooei M., Babar A., 2022. Using UAV-based hyperspectral imaging and functional regression to assist in predicting grain yield and related traits in wheat under heat-related stress environments for the purpose of stable yielding genotypes. Precision Agriculture, 23(2), 622-642, https://doi.org/10.1007/s11119-021-09852-5.
• Costa L., Kunwar S., Ampatzidis Y., Albrecht U., 2022. Determining leaf nutrient concentrations in citrus trees using UAV imagery and machine learning. Precision Agriculture, 23(3), 854-875, https://doi.org/10.1007/s11119-021-09864-1.
• Mirbod, O., Choi, D., Heinemann, P. H., Marini, R. P., & He, L. (2023). On-tree apple fruit size estimation using stereo vision with deep learning-based occlusion handling. Biosystems Engineering, 226, 27-42. (open access)
• Yuan, W., Choi, D., Bolkas, D., Heinemann, P. H., & He, L. (2022). Sensitivity examination of YOLOv4 regarding test image distortion and training dataset attribute for apple flower bud classification. International Journal of Remote Sensing, 43(8), 3106-3130.
• Yuan, W., Choi, D., & Bolkas, D. (2022). GNSS-IMU-assisted colored ICP for UAV-LiDAR point cloud registration of peach trees. Computers and Electronics in Agriculture, 197, 106966.
• Zhang, H., He, L., Di Gioia, F., Choi, D., Elia, A., & Heinemann, P. (2022). LoRaWAN based Internet of Things (IoT) System for Precision Irrigation in Plasticulture Fresh-market Tomato. Smart Agricultural Technology, 100053.
• Zhou, X., Y. Ampatzidis, W. S. Lee, C. Zhou, S. Agehara, and J. K. Schueller. 2022. Deep learning-based postharvest strawberry bruise detection under UV and incandescent light. Computers and Electronics in Agriculture 202 (2022) 107389. https://doi.org/10.1016/j.compag.2022.107389.
• Patel, A.M., W. S. Lee, and N. A. Peres. 2022. Imaging and deep learning based approach to leaf wetness detection in strawberry. Sensors 2022, 22, 8558. https://doi.org/10.3390/s22218558.

Thesis/Dissertation

• Uthman, Q.O. 2023. Management of huanglongbing-affected “Valencia” sweet oranges in sandy soils of central Florida: sorption kinetics and equilibria, uptake, and leaching of nutrients and imidacloprid in a Florida sandy soil. D. Dissertation, University of Florida, Gainesville, FL.

Michigan

Peer-reviewed Publications

• Dang, F., Chen, D., Lu, Y., Li, Z., 2023. YOLOWeeds: a novel benchmark of YOLO object detectors for multi-class weed detection in cotton production systems. Computers and Electronics in Agriculture 205, 107655.
• Rahman, A., Lu, Y., Wang, H., 2023. Performance evaluation of deep learning object detectors for weed detection for cotton. Smart Agricultural Technology 3, 100126.

Mississippi

Peer-reviewed Publications

• Lucas Gay, Filip To, Joe Thomas, Sean Donohoe, “Inline Real-Time Moisture Sensing System for Gin Cotton”, Proceedings of National Cotton Council Belt-wide Cotton Conferences, New Orleans, January 10-12, 2023.
• Zhang, X., Thayananthan, T., Usman, M., Liu, W., & Chen, Y. (2023, June). Multi-ripeness level blackberry detection using YOLOv7 for soft robotic harvesting. In Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping VIII (Vol. 12539, pp. 85-96). SPIE. https://doi.org/10.1117/12.2663367
• Chakraborty, M., Pourreza, A., Zhang, X., Jafarbiglu, H., Shackel, K. A., & DeJong, T. (2023). Early almond yield forecasting by bloom mapping using aerial imagery and deep learning. Computers and Electronics in Agriculture. (Accepted)
• Peng, H., Zhong, J., Liu, H., Li, J., Yao, M., & Zhang, X. (2023). ResDense-focal-DeepLabV3+ enabled litchi branch semantic segmentation for robotic harvesting. Computers and Electronics in Agriculture, 206, 107691. https://doi.org/10.1016/j.compag.2023.107691
• Lu, S., Liu, X., He, Z., Zhang, X., Liu, W., & Karkee, M. (2022). Swin-transformer-YOLOv5 for real-time wine grape bunch detection. Remote Sensing, 14(22), 5853. https://doi.org/10.3390/rs14225853

Book Chapters:

• Zhang, X. (2023). Robotics and Automation Technologies: Plant-machine interface. In Encyclopedia of Smart Agriculture Technologies (Zhang, Q. ed.), Springer. https://doi.org/10.1007/978-3-030-89123-7_124-1
• He, L., Zhang, X., & Zahid, A. (2023). Chapter 2 – Mechanical management of modern planar fruit tree canopies. In Advanced Automation for Tree Fruit Orchards and Vineyards (Vougioukas, S. G., & Zhang, Q. ed.), Springer Book Series: Agriculture Automation and Control. https://doi.org/10.1007/978-3-031-26941-7_2

New York

Peer-reviewed Publications

• Liu, E., Gold, K., Cadle-Davidson, L., Combs, D., & Jiang, Y. (2022, October). Near Real-Time Vineyard Downy Mildew Detection and Severity Estimation. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 9187-9194). IEEE.
• Kanaley, K., Paul, A., Combs, D., Liu, E., Jiang, Y., & Gold, K. (2022, December). Mapping Winegrape Disease Epidemics with SkySat and PlanetScope Imagery. In AGU Fall Meeting Abstracts (Vol. 2022, pp. IN43A-05).

Pennsylvania

Peer-reviewed Publications

• Hussain, M., He, L., Heinemann, P., & Schupp, J. (2022). Green fruit removal dynamics for robotic green fruit thinning end-effector development. Journal of ASABE 65(4), 779-788.
• Mahmud, M. S., Zahid, A., He, L., Zhu, H., Heinemann, P., Choi, D., & Krawczyk, G. (2022). Development of an automatic airflow control system for precision sprayers based on tree canopy density. Journal of ASABE 65(6), 1225-1240.
• Mu, X., He, L., Heinemann, P., Schupp, J., & Karkee, M. (2023). Mask R-CNN based king flowers identification for precise apple pollination. Smart Agricultural Technology 4, 100151.
• Mahmud, M. S., He, L., Heinemann, P., Choi, D., & Zhu, H. (2023). Unmanned aerial vehicle based tree canopy characteristics measurement for precision spray applications. Smart Agricultural Technology 4(100153).
• Hussain, M., He, L., Schupp, J., Lyons, D., & Heinemann, P. (2023). Green fruit segmentation and orientation estimation for robotic green fruit thinning of apples. Computers and Electronics in Agriculture 207, 107734.
• Yuan, W., Hua, W., Heinemann, P.H. & He, L. (2023). UAV photogrammetry-based apple orchard blossom density estimation and mapping. Horticulturae, 9(2), 266.
• Mahmud, M.S., He, L., Zahid, A., Heinemann, P., Choi, D., Krawczyk, G. & Zhu, H., 2023. Detection and infected area segmentation of apple fire blight using image processing and deep transfer learning for site-specific management. Computers and Electronics in Agriculture, 209, 107862.

Book Chapter:

• He, L., Zhang, X., & Zahid, A. (2023). Mechanical Management of Modern Planar Fruit Tree Canopies. In Book: Advanced Automation for Tree Fruit Orchards and Vineyards. Cham: Springer International Publishing.
• He, L. (2022). Variable rate Technologies for Precision Agriculture. In Zhang, Q. (eds) Encyclopedia of Smart Agriculture Technologies. Springer, Cham. ISBN/ISSN: 978-3-030-89123-7
• Gohil, H & He, L. (2023). Precision Irrigation for Orchards. In: Zhang, Q. (eds) Encyclopedia of Smart Agriculture Technologies. Springer, Cham. ISBN/ISSN: 978-3-030-89123-7_193-1

Thesis and Dissertation:

• Kittiphum Pawikhum (2022). Design of end-effectors for thinning apples in the green fruit stage. MS Thesis. The Pennsylvania State University.
• Rashmi Sahu (2023). Development of vision system and end-effector for automatic bud thinning of apple tree: early crop load management. MS Thesis. The Pennsylvania State University.

Tennessee

Peer-reviewed Publications

• Rice, C. R., McDonald, S. T., Shi, Y., Gan, H., Lee, W. S., Chen, Y., & Wang, Z. (2022). Perception, Path Planning, and Flight Control for a Drone-Enabled Autonomous Pollination System. Robotics, 11(6), 144.
• Rice, C.R., Gan, H., Wang, Z. (2023). Real-Time Path Planning and Collision-Free Flight

Control for Drone-Assisted Autonomous Pollination Systems. Information Processing in Agriculture. (under review).

Texas

Peer-reviewed Publications

• Ojo, M. O., and Zahid, A. 2023. Improving deep learning classifiers performance via preprocessing and class imbalance approaches in a plant disease detection pipeline. Agronomy, 13, 887.
• Mahmud, M.S., Zahid, A., and Das, A.K. 2023. Sensing and Automation Technologies for Ornamental Nursery Crop Production: Current Status and Future Prospects. Sensors, 23, 1818. https://doi.org/10.3390/s23041818
• Ojo, M. O., and Zahid, A. 2022. Deep learning in controlled environment agriculture: A review of recent advancements, challenges, and prospects, Sensors, 22(20), 7965

Book Chapters

• Zahid, A., and Mahmud, M.S. 2023. LiDAR Sensing and its Applications in Agriculture. Q. Zhang (ed.), Encyclopedia of Smart Agriculture Technologies, Springer Nature Switzerland

Washington

Peer-reviewed Publications

• Molaei, B., A. K. Chandel, R. Troy Peters, L. R. Khot, A. Khan, F. Maureira, and C. Stockle. 2023. Investigating the application of artificial hot and cold reference surfaces for improved ETc estimation using the UAS-METRIC energy balance model. Agricultural Water Management, 284, 108346. https://doi.org/10.1016/j.agwat.2023.108346.
• Chandel^l, A.K., M.M. Moyer, M. Keller, L.R. Khot, and G-A. Hoheisel. 2022. Soil and climate geographic information system data-derived risk mapping for grape phylloxera in Washington state. Frontiers in Plant Science, 13, 827393-827393 https://doi.org/10.3389/fpls.2022.827393
• Chandel, A.K., A.P. Rathnayake, and L.R. Khot. 2022. Mapping apple canopy attributes using aerial multispectral imagery for precision crop inputs management. Acta Horticulturae. 1346, 537-546, https://10.17660/ActaHortic.2022.1346.68
• Chandel, A. K., Amogi, B., Khot, L., Stockle, C. O., and R. T. Peters. 2022. Digitizing Crop Water Use with Data-Driven Approaches. Resource Magazine, 29(4), 14--16.
• Kalyanaraman*, A., M. Burnett, A. Fern, L. Khot, and J. Viers. 2022. Special report: The AgAID AI institute for transforming workforce and decision support in agriculture. Computers and Electronics in Agriculture, 197, 106944
• McCoy, M. L., G.-A. Hoheisel, L. R. Khot, and M. M. Moyer*. 2022. Adjusting air-assistance and nozzle style for optimized airblast sprayer use in eastern Washington vineyards. Catalyst: Discovery into Practice, 6(1): 9-19 https://doi:10.5344/catalyst.2021.21001 (Featured on cover page)
• Molaei, B., A. Chandel^l, R.T. Peters*, L.R. Khot, and J.Q. Vargas^l.   Investigating lodging in Spearmint with overhead sprinklers compared to drag hoses using the texture feature from low altitude RGB imagery. Information Processing in Agriculture, 9(2): 335-341 https://doi.org/10.1016/j.inpa.2021.02.003   
• Molaei, B., R.T. Peters*, L.R. Khot, and C. Stockle. 2022. Assessing suitability of auto-selection of hot and cold anchor pixels of the UAS-metric model for developing crop water use maps. Remote Sensing, 14(18), 4454; https://doi.org/10.3390/rs14184454
• Ranjan^l, R., R. Sinha^l, L.R. Khot*, and M. Whiting. 2022. Thermal-RGB imagery and in-field weather sensing derived sweet cherry wetness prediction model. Scientia Horticulturae, 294, 110782 https://doi.org/10.1016/j.scienta.2021.110782
• Rathnayake^l, A. P., A. Chandel^l, M. Schrader^l, G.-A. Hoheisel and L. R. Khot*. 2022. Air-assisted velocity profiles and perceptive canopy interactions of commercial airblast sprayers used in Pacific Northwest perennial specialty crop production. CIGR e-journal, 24 (1) 7039.
• Rathnayake^l, R. K Sahni^l, L. R. Khot*, G.-A. Hoheisel and H. Zhu. 2022. Intelligent sprayer spray rates optimization to efficiently apply chemicals in modern apple orchards. Journal of the ASABE, 65 (6): 1-10. https://doi.org/10.13031/ja.14654
• Sahni^l, R. K, R. Ranjan^l, L. R. Khot*, G.-A. Hoheisel and M. Grieshop. 2022. Reservoir units optimization in pneumatic spray delivery-based fixed spray system for large-scale commercial adaptation. Sustainability, 14, 10843. https://doi.org/10.3390/su141710843
• Schrader^l, M.J., A.P. Rathnayake^l, and L. R. Khot. 2022. Horticultural oil thermotherapy delivery system for perennial specialty crops: a-proof-of-concept and preliminary results. Applied Engineering in Agriculture, 38(2), 461-468.
• Schrader^l, M.J., P. Smytheman, E.H. Beers, and L.R. Khot*. 2022. An open-source low-cost imaging system plug-in for pheromone traps aiding remote insect pest population monitoring in fruit crops. Machines, 10(1), 52. https://doi.org/10.3390/machines10010052
• Sinha^l, R., J. Quiros Vargas^l, S. Sankaran and L. R. Khot*. 2022. High resolution aerial photogrammetry based 3D mapping of fruit crop canopies for precision inputs management. Information Processing in Agriculture,9(1): 11-23 https://doi.org/10.1016/j.inpa.2021.01.006.
• Worasit, S., A. Marzougui, A. A. Bates, B. Schroeder, L. R. Khot and S. Sankaran*. 2022. Identification of volatile biomarkers for high-throughput sensing of soft rot and Pythium leak diseases in stored potatoes. Food Chemistry, 370, 130910 https://doi.org/10.1016/j.foodchem.2021.130910
• Kang, C., Diverres, G., Karkee, M., Zhang, Q., & Keller, M. (2023). Decision-support system for precision regulated deficit irrigation management for wine grapes. Computers and Electronics in Agriculture, 208, 107777.
• Borrenpohl, D., & Karkee, M. (2023). Automated pruning decisions in dormant sweet cherry canopies using instance segmentation. Computers and Electronics in Agriculture, 207, 107716.
• Bayano-Tejero, S., Karkee, M., Rodríguez-Lizana, A., & Sola-Guirado, R. R. (2023). Estimation of harvested fruit weight using volume measurements with distance sensors: A case study with olives in a big box. Computers and Electronics in Agriculture, 205, 107620.
• Mu, X., He, L., Heinemann, P., Schupp, J., & Karkee, M. (2023). Mask R-CNN based apple flower detection and king flower identification for precision pollination. Smart Agricultural Technology, 4, 100151.
• Bayano-Tejero, S., Karkee, M., Rodríguez-Lizana, A., & Sola-Guirado, R. R. (2023). Estimation of harvested fruit weight using volume measurements with distance sensors: A case study with olives in a big box. Computers and Electronics in Agriculture, 205, 107620
• Lu, S., Liu, X., He, Z., Zhang, X., Liu, W., & Karkee, M. (2022). Swin-Transformer-YOLOv5 for Real-Time Wine Grape Bunch Detection. Remote Sensing, 14(22), 5853.
• Guo, J., Duan, J., Yang, Z., & Karkee, M. (2022). De-Handing Technologies for Banana Postharvest Operations—Updates and Challenges. Agriculture, 12(11), 1821.

Thesis/Dissertations

• Borrenpohl, D. (2023). Automated Pruning Decisions in Dormant Sweet Cherry Canopies using Instance Segmentation. MS Thesis, Washington State University.
• Bhattarai, U. (2023). Robotic Blossom Thinning System for Tree Fruit Crops. PhD Dissertation, Washington State University.
• Kang, C. (2023). Decision-Support System for Water Stress Assessment and Deficit Irrigation Management in Wine Grapes. PhD Dissertation, Washington State University.

Books and Book Chapters

• Sahni, R.K., and R. Khot* 2023. Fixed spray systems for perennial specialty crops. In: Zhang, Q. (eds) Encyclopedia of Smart Agriculture Technologies. Springer, Cham. https://doi.org/10.1007/978-3-030-89123-7_195-1
• Karkee, M., Majeed, Y., & Zhang, Q. (2023). Advanced Technologies for Crop-Load Management. In Advanced Automation for Tree Fruit Orchards and Vineyards(pp. 119-149) (Editors Stavros Vougioukas and Qin Zhang). Cham: Springer International Publishing.
• Karkee, M., &Silwal, A. (2023). Robotic Fruit Harvesting. In: Zhang, Q. (eds) Encyclopedia of Smart Agriculture Technologies. Springer, Cham. https://doi.org/10.1007/978-3-030-89123-7_139-1