Brief Summary of Minutes of Annual Meeting

Annual Meeting Minutes:

• Meeting Started 11:00 am on August 22, 2025 via Zoom.
• Faculty introduction
• Hao Gan presented a summary of the 2024 annual meeting, which was held in Hawaii.
• Committee Term Length Discussion: The committee discussed whether to adopt a 2-year or 1-year term for officers. Dr. Stavros advocated for a 2-year term, citing benefits for continuity, and Dr. Heinemann requested rationale for the change. Dr. Jiang supported the idea for smoother transitions with 2-year term, while Dr. Siemens opposed it. A vote was held: Objections to 2-year term: 8; Support for 2-year term: 5; Outcome: The committee will retain the 1-year term for officers.
• Workload management: Siemens emphasized distributing responsibilities among officers to reduce workload for the host of meetings.
• Proposal writing was clarified: typically done by the committee chair or PI. Dr. Stavros had written the current proposal.
• New secretary selection: Dr. Yu Jiang proposed Dr. Dong Chen name as secretary. Dr. Chen was accepted by the members of the W4009 multi-state project.
• New officers for 2025-26: Chair: Dr. Yuzhen Lu, Vice-Chair: Dr. Md Sultan Mahmud, Secretary: Dr. Dong Chen
• Next meeting host and location: Dr. Rex Sun expressed interest in hosting the 2026 meeting in Fargo, North Dakota, highlighting the presence of specialty crops such as grape, strawberry, and cranberry. He remained open to alternative locations but showed strong interest in hosting. Dr. Thomasson supported the idea of holding the meeting in Fargo. A motion to host the 2026 meeting in Fargo was moved by Dr. Daniel Lee and seconded by Dr. Yu Jiang. The W4009 multi-state project team agreed: The 2026 meeting will be held in Fargo, North Dakota.
• Meeting location and host for the future: Dr. Alex Thomasson expressed willingness to host a meeting in Mississippi in the future, possibly in 2027. Dr. Hao Gan also showed interest in hosting a future meeting in Tennessee and suggested discussing this meeting location section topic a regular agenda item for future meetings.
• Combining meetings discussion: Dr. Gan proposed the idea of combining the committee’s meeting with other multi-state projects (e.g., 1098) at the AI in Agriculture conference or other similar conference. Dr. Thomasson noted challenges in hosting joint meetings, emphasizing the need for leadership coordination between both projects due to overlapping interests. The group agreed that occasional joint meetings may be feasible, but separate meetings are still necessary. Cost concerns were raised regarding travel and hosting logistics. Dr. Heinemann suggested scheduling meetings before or after the ASABE conference to help reduce costs. Dr. Daniel Lee recommended small group meetings (separately for this group), which could allow visits to different states or universities.
• Discussion on research impact training: Dr. Alex Thomasson and Dr. Joe Dvorak discussed past impact training sessions, including one led by a USDA representative, Ms. Sara Delheimer (Delheimer@colostate.edu). The most notable session was an in-person workshop by Sara Delheimer in 2019 in Kentucky, prior to the pandemic. Details were limited due to the time being elapsed, but Dr. Dvorak shared Sara Delheimer’s contact information and mentioned she is likely still with the Multistate Group. The committee discussed the idea of officers reaching out to request a 30-minute workshop on research impact. Dr. Gan and Dr. Thomasson supported the idea of contacting USDA for future training opportunities. It was suggested that this topic be considered for future meeting agendas. The following links were shared by Dr. Dvorak

Multistate Research Fund Impacts | Impact Writing Workshops

Automation for Specialty Crops

Automation for Specialty Crops

https://www.mrfimpacts.org/single-post/automation-for-specialty-crops

• Annual Report: Dr. Gan will send details about the Annual Report via email to the committee. The report must be submitted within 60 days following the annual meeting.
• Business meeting adjourn: 12:15 pm

Arizona:

• The commercial scale steam applicator for thermally killing weed seed and soilborne pathogens prior to planting developed in this project was evaluated in carrot and spinach. Trial results showed that steam treatment provided very good weed control (75-92%, 4 trials) and significantly reduced hand weeding times and cost (45-65%, $140-400/acre) as compared to the untreated control. Work rates and machine costs were marginally acceptable, at 0.2 ac/hr and $1,139/ac respectively.
• An artificial intelligence pipeline was developed to recognize weeds in lettuce and spinach fields without requiring manual image segmentation, enabling automatic segmentation and classification. The model achieved an F1 score of over 85% at the bounding-box level for weed detection in lettuce fields, and over 75% at the pixel level, evaluated on approximately 10% of 939 annotated images. Preliminary results in spinach yielded an F1 score of 87.5% at the bounding-box level.
• An on-the-go multi-sensor platform integrated soil and plant sensors and was successfully deployed in a lettuce field 30 days after planting in Yuma AZ. The integrated device collected geo-referenced active spectral data over plant canopy in 670 nm (red), 730 nm (red edge), and 780 nm (NIR) wavelengths; as well as electrical conductivity, temperature, and Red and IR spectroscopy signals in the top 15 cm of the soil profile. Data acquisition incorporated RTK-level GNSS positioning data logged at 5 Hz. These data are being analyzed using machine learning techniques as part of a multiscale approach to smart nitrogen fertilization.

California:

• A prototype fruit-catching arm was built for shake-catch harvesting. The arm can penetrate a tree’s canopy and catch fruits that fall during shaking. A system model with multiple layers of such arms was developed and used in simulation for design and optimization.
• Thirty instrumented strawberry-picking carts were used by farm workers for six months, twice a week, to collect data that was used to calculate yield maps in one field in Salinas, CA.
• A fully automated almond yield mapping system developed at UCD was used to collect data in an almond orchard in Madera, CA, for two weeks.
• Develoiped a phenologically-aware, strawberry yield forecasting model that uses time-series of ground-based imagery to create yield forecasts several weeks in advance.
• Developed the first U.S. ATV safety test station that includes static, dynamic, and rollover simulators, providing a comprehensive platform for experimental testing and operator training. The ATV rollover simulator is also used for hands-on safety demonstrations and extension activities.
• Developed accurate multi-body finite element (FE) models to simulate rollover incidents and initiated several projects focused on safety in autonomous and robotic agricultural systems.
• Developing a phone application for predicting heat-related illnesses among farmworkers.
• Developed of a multi-trait predictive model and a multi-resolution remote sensing framework for assessing grapevine nutrient status. We successfully built a leaf-level model using hyperspectral reflectance (400–2500 nm) integrated with laboratory-measured traits, including major and micronutrients, chlorophyll, LMA, and EWT. The model achieved strong performance with an average R² of 0.73 and NRMSE of 0.07, confirming its ability to capture complex inter-trait relationships. Additionally, we simulated over 2,000 synthetic vineyard scenes using the HELIOS 3D ray-tracing framework on AWS to support canopy-level modeling and system scalability.

• Collaboratively initiated a project to introduce ergonomic risk into crop-transport robot scheduling algorithms to balance work efficiency and ergonomic risk. The project focuses on developing a dual-objective optimization approach to compute the schedules of crop-transport robots, which increases the work efficiency of harvest workers while restricting workers’ back fatigue from prolonged stooping. Performance and muscular fatigue data were collected from several farmworkers performing field strawberry harvesting in Salinas. Currently analyzing the data and preparing a paper for publication.
• Continued the study exploring an ultrasound-based system combined with an AI-enabled image pattern recognition system to detect farmworkers’ spine health status while performing labor-intensive tasks.  Collected data on phantom samples to test various simulated spinal discs under varying water content. Collaborated with an orthopedic surgeon to provide gold standard MRI images and general guidance on the clinical significance of the project.
• Continued to explore workers’ compensation records to investigate the role of emerging automated and robotic systems in injuries to farmworkers.  The AI-enabled approach to extract information from injury descriptions has been developed, and a paper has been prepared for submission, which demonstrates the novel approach.
• Evaluated the potential of deep learning (DL) models for ETo forecasting, particularly emphasizing the efficacy of a global learning scheme compared to traditional local learning. Global learning involves training forecasting models on pooled data from multiple time series, tested over new instances. We compared the performance of statistical models and advanced DL models, demonstrating significant accuracy enhancements in global learning schemes. We also explored automatic hyperparameter optimization for these models to achieve state-of-the-art forecasting accuracy, yielding RMSE values below 10 mm/month for one-year ahead forecasts on new, unseen stations.

• Inspired by the advancement of physics-informed neural networks (PINN), we Evaluated the integration of both empirical and semi-physical models into a DNN, particularly in the loss function for reference evapotranspiration estimation. The PINN improved ETo estimation performance, surpassing the fully-data driven model and the semi-physical models in all metrics. The optimal balance between physics and data-driven approaches was determined using the CMA-ES under various scenarios.
• Developed a Convolutional Neural Network (CNN) designed to compute crop canopy cover autonomously. We deployed a low cost IoT system with an RGB camera and we harnessed a dataset comprising 283,000 images, each with dimensions of 256 × 256 pixels, for network training. Optimizing the neural network was achieved through a Genetic Algorithm (GA), employing an objective function focused on minimizing parameter density while maintaining accuracy. The results indicate that our CNN, with fewer than 200,000 parameters, achieved an R² of 98 %, an MSE of 0.0024, and an MAE of 0.038.
• Two workshops were held to advance workforce development in agricultural technology. The first engaged 10 educators, and the second involved 20 growers, advisors, and industry professionals from Western states in hands-on sessions on AI, IoT, drones, and robotics. Participants received stipends to support their participation. These workshops served as a catalyst for transferring emerging technologies from research to on-farm applications.
• Coffee professionals know that the roast profile—the temperature over time—significantly affects coffee flavor and quality. Key factors include perceived sourness, measured as titratable acidity (TA), and color. Most research has focused on lab roasters with limited control, leaving the relationship between commercial roast profiles and TA and color unclear. Our study examined 5-kg commercial roasts with the same duration but different internal dynamics. We found titratable acidity (TA) peaks during the first crack and returns to initial levels by the second crack, with little variation in peak TA across profiles. Additionally, we identified a universal color curve that follows a predictable pattern. These insights help in controlling and achieving desired coffee qualities during roasting. 
• From a purely extension perspective, I also authored a book chapter relevant to the work carried out by this multistate group, specifically focusing on postharvest quality factors and their assessment.
•   A computer model of a shake-catch harvester, a harvest simulator, and a prototype fruit-catching arm.
• Approximately fifty precision yield maps were generated for strawberries and two tree-level yield maps for almond trees.
• Strawberry yield forecasts were made at 4 to 7 day intervals across multiple growing seasons at a commercial farm (about 40+ ground-based scans using RGB sensing system)
• 96 presentations related to ATV safety across various events, including workshops and training programs. This includes more than 68 California Occupational Safety and Health Administration (Cal/OSHA) training sessions for safety officers, managers, and inspectors, as well as numerous hands-on demonstrations and field activities.
• The integration of the multi-trait model into canopy-level simulations established a robust foundation for large-scale vineyard nutrient assessment. The simulated datasets showed high similarity to real-world multispectral imagery, enabling reliable model validation and training. Furthermore, a mobile application prototype—the Leaf Monitor App—was developed to provide real-time predictions from user-input spectral data, making nutrient assessment more accessible and efficient for researchers and growers. The web application of this tool can be found here: https://www.digitalaglab.com/LeafMonitorApp.
• Improved the accuracy of deep learning models for reference evapotranspiration forecasting in the Central Valley of California using global learning .
•  Described and developed a novel approach for reference evapotranspiration estimation using Physics informed neural network
• Developed a low-cost IoT platform for crop canopy cover estimation for better yield prediction and accurate irrigation management
• Survey results from the two workshops to advance workforce development in agricultural technology showed high participant satisfaction, with an average rating of 4.6 out of 5 and a 4.5 out of 5 likelihood of recommending the workshops. Participants reported significant knowledge gains in AI, IoT, drones, robotics, and precision irrigation, with educators planning to update curricula and industry participants intending to apply these technologies in their operations.
• Book chapter specifically focusing on postharvest quality factors and their assessment.  The extension publication significantly advances the understanding of postharvest quality assessment, control, and measurement, providing valuable insights that can improve quality control processes and extend the shelf life of produce. It also contributes to future research and practical applications in postharvest science, quality assessment, and sensing
• We compiled the most comprehensive, state-by-state list of regulated noxious weeds in the United States, including 1,000+ species from state lists and 112 species from the federal list, and systematically searched each by name on Amazon and eBay to document their online availability. This effort produced the first quantitative nationwide assessment of e-commerce pathways for invasive plant introduction. We also built and launched a publicly accessible online platform (https://regulatedplants.unu.edu/) that allows users to explore regulated species through interactive maps, keyword search, and integrated species data via GBIF.
• Our screening revealed that approximately 38% of state-listed noxious weeds are available on Amazon and eBay, despite their regulated status. For federally listed species, 7% were found on Amazon and 33% on eBay, indicating a major inconsistency in enforcement across platforms. Amazon showed partial compliance through shipping restrictions, while eBay had no similar mechanism in place. These findings were shared with researchers and California state officials and the online database is now being used as a reference tool for monitoring listings and informing potential enforcement action.

Florida:

• Dr. Lee’s team developed an end-to-end pipeline for strawberry production, integrating fruit detection, canopy analysis, yield forecasting, and hardware deployment. Their lightweight detection models achieved high accuracy across ripening stages, while a novel segmentation and depth estimation system enabled precise 3D canopy volume measurements from single-view images—surpassing traditional and manual methods in both scalability and detail.
• To enhance yield forecasting, the team introduced a multi-modal model that fused visual and weather data, significantly reducing prediction errors and improving alignment with actual yields across two cultivars and seasons. Field testing of four AgriBerry Vision (ABV) modules mounted on sprayers demonstrated real-time image capture and model inference capabilities, though further optimization is needed for seamless integration into large-scale operations.
• In another project, a high-accuracy leaf wetness detection system was developed for strawberries using a hybrid ConvLSTM model. This approach combined CNN-based spatial droplet detection with LSTM-driven temporal analysis, enabling robust classification of wet versus dry surfaces under varying conditions. With attention mechanisms and Focal Loss enhancing performance, the model reached 97% validation accuracy, empowering growers with timely moisture insights for precise fungicide application and improved crop health.
• Dr. Kadyampakeni presented 3 seminars at the Citrus Show, Citrus Institute, and Citrus and Specialty Crops Expo covering topics on automated irrigation and precision fertilizer application.
• Dr. Kadyampakeni was Guest Editor for two special issues in Irrigation Science on the topics of machine learning, artificial intelligence and irrigation automation and microirrigation.
• Dr. Li developed a customized deep learning model to rapidly quantify berry fruit internal bruising, given that evaluating fruit internal bruising manually is a tedious and time-consuming process. His group evaluated blueberries from 61 cultivars of soft to firm types over a three-year period. A web-app was developed and shared with the public.
• Dr. Li developed a robotic blueberry phenotyping system, called MARS-Phenobot, that collects data in the field and measures fruit-related phenotypic traits such as fruit number, maturity, and compactness. The work provides a promising solution for automated in-field blueberry fruit phenotyping, potentially replacing labor-intensive manual sampling. Furthermore, this approach could advance blueberry breeding programs, precision management, and mechanical/robotic harvesting.

Georgia:

• In the period between (10/01/2024 – 09/30/2025), one of the key milestones accomplished was an RGB-LiDAR integrated system for measuring trunk diameter and canopy volume in ornamental trees (e.g., oak), enabling maturity assessment and precision spraying. This work led to a publication in Smart Agricultural Technology. An AI-guided and large language model (LLM)-powered web application was also developed for real-time diagnosis of dogwood leaf spot severity, combining image analysis with large language models to provide severity scores and management advice. Users of this app can obtain real-time detection and area calculation results, along with AI analysis about the disease, by simply uploading a picture of the leaf of dogwood and describing the disease using a smartphone or computer. This study is under consideration for publication in Computers and Electronics in Agriculture. Ongoing efforts include a robotic system for real-time scouting and mapping of Japanese maple scale using machine vision and AI. In onion research, we developed an early version prototype delta robotic laser weeding system with a 60W blue diode laser to kill weeds in onion fields. The preliminary evaluation showed that 3 s and 2 s treatments killed 90% and 60% of weeds, while 1 s and 0.5 s exposures only killed 20% and 10%. The robotic system had a positioning accuracy of 0.85 millimeters, showing potential to reduce herbicide use and labor costs. Additionally, a remote sensing framework was initiated to monitor pecan bacterial leaf scorch, aiming to understand disease spread and inform precision management. Outputs include three manuscripts (three published, one under review), a functional AI app, robotic prototypes, and preliminary datasets. These tools offer measurable benefits such as improved disease detection, reduced chemical inputs, and enhanced decision-making. In the coming year, the team will focus on field validation, system optimization, stakeholder training, and expanded disease and pest monitoring using ground robots, UAVs and remote sensing.

Kentucky:

• With the sudden explosion of AI tools and systems, a key concern has been if they can accurately assess detailed agricultural information. This is a key consideration for creating agentic AI systems that solve real world agricultural problems. Vision systems are readily available that will process an image and accurately describe what is in it. However, an open question was whether an AI system could take those descriptions and retrieve additional information to make an informed assessment. As a general test of this ability, we investigated the ability of LLM embeddings and generative models to analyze, cluster and describe all the in-depth technical research presentations submitted to ASABE’s Annual International Meeting. If LLM-based tools can appropriately categorize and generate responses using this complex dataset, they should likewise be able to sort through and craft appropriate responses to general agricultural concerns. This experiment was successful and generated several websites where the outputs can be explored.
• ASABE AIM 2025 Presentation and Session Similarity Exploration Tool https://asabe-aim-2025-similarity-exploration-at-conference-app.streamlit.app/
• Automated Session Creation Visualization Tool - AIM 2025 (All Communities) https://sessioncreation-aim2025-all.streamlit.app/
• Presentation Similarity Exploration Tool https://asabeaimsimilarity2025.streamlit.app/

Massachusetts:

• We built a low-power impedance sensing circuit to replace commercial potentiostats, using multi-frequency sweeping (200 KΩ–1 MΩ) to distinguish signals from different nutrients inside the xylem of the plants.

• We evaluated multiple long-range communication protocols (LoRa, LoRa Backscatter, NB-IoT, LTE-M) to allow the sensors to transmit data to the base station (farmer houses) before relaying them to the cloud. We identified that LoRa for its robustness and support. Collision mitigation was explored through enhanced chirp modulation and concurrent interference cancellation. We are evaluating the performance of LoRa sensor nodes in the field. The line-of-sign conditions work perfectly but we are evaluating the performance of the communication protocols with a more practical settings with more blockages.
• To maintain zero-maintenance operation, we have investigated and tested multiple wind-based energy harvesting structures, selecting the most efficient configuration through field trials. The current prototype operated for couple of weeks continuously on a field without issues. We are still testing this functionality.
• The machine learning model to convert the captured signals into nutrient levels should be running on the devices to support in time water and fertilizer management. So, to enable this capability, we deployed an ARM Cortex-M4 MCU (MAX78000) with CNN acceleration to run intermittent computing and ML-based nutrient inference on-chip, enabling edge intelligence without external power or servers.
• Prototype nutrient sensors, low-power impedance circuits, LoRa-based communication modules, wind energy harvesters, ML-enabled MCU platform, and field data from real-world deployments.
• Demonstrated battery-free, in situ nutrient sensing with continuous operation.
• Reduced infrastructure and maintenance costs for remote farm monitoring.
• Enabled long-range wireless reporting and low-cost IoT scalability.
• Validated robust operation in real world environments.
• Plant sensor array development and validation.
• Low-power impedance sensing circuit completed.
• LoRa integration with interference mitigation.
• Energy harvesting deployment validated.
• Plans for Next Year: Expand sensing to additional ions, integrate hybrid solar-wind harvesting, scale to multi-node networks, and deploy pilot studies with growers to demonstrate agronomic impact.

Michigan:

• Short-term Outcomes: 1) developed computer algorithms for asparagus perception and conducted a preliminary test of two pneumatic actuator prototypes for selective harvesting asparagus, 2) developed a new multispectral vision-based automated sweetpotato grading and sorting system, 3) developed an improved version of a smart sprayer for precision vegetable weeding with both indoor and on-farm testing conducted and performed a on-farm demonstration to visitors, 4) assessed hyperspectral imaging for the detection of spotted wing drosophila infestation in blueberries, 5) developed a machine vision prototype for full canopy imaging of blueberries and a smartphone apple for blueberry detection to support precision management and established a comprehensive benchmark of real-time detectors for blueberry detection, and 6) build a preliminary version of a vision-based system for automated apple grading.
• Outputs: published 11 peer-reviewed journal articles, presented 6 conference papers, published a new multi-season open-access weed dataset, and released a smartphone application for blueberry detection. 
• Activities: Applied artificial intelligence and machine vision methods to fruit quality grading, asparagus perception for selective harvesting, precision vegetable weeding, and in-orchard fruit detection. AI and the Internet of Things were leveraged for irrigation and disease management of specialty crops.

Mississippi:

• At Mississippi State University, PI Dong Chen is leading research on artificial intelligence (AI) and automation for harvesting of delicate U.S. specialty crops, addressing a critical need in the industry, particularly for crops like blueberries and strawberries. His team has developed an open-source blueberry image dataset containing more than 600 annotated images, supporting the development of AI-based detection and yield estimation algorithms. Research outcomes have been disseminated through two conference presentations, including the 2025 AI in Agriculture Conference (Starkville, MS, March 31 through April 2) and the American Society for Horticultural Science (ASHS) Conference 2025 (New Orleans, LA, July 28 through August 1), and three journal manuscripts currently in preparation.
• In addition to research accomplishments, the team has played a major role in student training and workforce development. PI Chen serves as faculty advisor for two international student robotics competitions, the Farm Robotics Challenge and the ASABE Robotics Student Design Competition. Through these initiatives, over ten graduate and undergraduate students from Agricultural and Biological Engineering, Electrical and Computer Engineering, and related programs have gained hands-on experience in applying robotics and AI to solve real-world agricultural problems. Notably, the student teams have designed and prototyped a soft robotic system for strawberry harvesting, integrating AI-based perception modules for fruit detection and ripeness estimation. The system demonstrated a clear advantage over traditional rigid robotic systems, offering improved adaptability, gentler handling of delicate fruits, and enhanced operational safety during the Farm Robotics Challenge. These interdisciplinary efforts have enhanced student technical competencies and fostered partnerships with industry stakeholders focused on advancing agricultural automation and smart farming technologies.
• Also, PIs Dong Chen and Alex Thomasson are leading a project on high-accuracy high-precision phenotyping, involving collaborative robotics between a remote-sensing drone and a ground-based robot serving as a calibration reference for reflectance, crop height, and canopy temperature.  This project includes one graduate student and is being conducted collaboratively with colleagues at Kangwon National University in Korea.

New York:

• The second-gen Phytopatholobot (PPB) has been finalized and distributed to all major grape breeding programs across the US to support high throughput plant phenotyping for disease resistance studies and cultivation.
• A new data processing pipeline based on large multimodal model has been deployed to analyze image datasets from PPB v2 to quantify disease infection severity for grape downy and powdery mildews. This has been adopted by all major grape breeding programs in the US.
• A laboratory hyperspectral imaging system (400 to 1000 nm) with streamlined processing pipeline has been deployed at Cornell AgriTech to support a wide range of applications in plant science, entomology, postharvest quality assessment, and food science and processing.

Pennsylvania:

• Develop a robotic crop load management system for apples at flower bud stage. In this year, we have focused on developing a machine vision system to count flower bud numbers on a branch and also estimate the bud distribution and provide bud thinning decisions.
• Continued working on decision support system for robotic button mushroom harvesting, and a vacuum based mushroom picking end-effector was designed and tested at Penn State Mushroom Research Center. The decision support system provides the coordinates of each mushroom and also the picking sequence of mushrooms in a test tub.
• An integrated chemical thinning system was tested in both research and commercial apple orchards. The system included a machine vision system to count the number of green fruitlets on trees, and then a precision spraying system was used to apply chemical thinner based on the crop load at individual tree level. The results showed that the system saved 18% of chemical thinner while maintained similar thinning performance by comparing to the conventional spraying system.
• An unmanned ground robotic system was tested in a vineyard and a raspberry field. The tests showed that the system achieved autonomous spraying for pest management in these fields, while chemical usage and performance of pest control are still under analysis.
• A large amount of images was acquired for apple fruits with various surface defects, including insect damage, disease damage, and nutrient deficiency. A deep learning based algorithm was developed to identify these defects, which will be used for quantifying the quality of individual fruits for robotic selective harvesting.
• A deep learning based weed detection algorithm was developed to detect and quantify the weed density in apple orchards, especially the weeds under trees. A target spraying system is under development to precisely apply herbicides to these detected weeds.
• To effectively pick fruits from complex canopies, two types of picking mechanism with soft fingers/grippers were developed, and tested in both peaches and apples.
• A classification model was developed and tested to identify the invasive box tree moth, which attacks the ornamental boxwood. This invasive has been spreading in the northeast US and eastern Canada and was recently discovered in Pennsylvania. A phone-based app has been developed so that users can upload an image to determine if the insect is a box tree moth or some other similar-looking species, and a pheromone-lure prototype automated monitoring trap was designed and tested.
• A spectral vision system was developed to detect the asymptomatic diseases on button mushroom and the robot to treat the diseased mushroom is under developing.
• Develop a Robotic System for Automated Apple Tree Leaf Detection and Plant Phenotyping
•  
• A machine learning algorithm was developed to detect tomato defense proteins in hyperspectral images when corn earworm attacks tomato plants. The treatments included damage from naturally occurring (wild) earworms, a mutant earworm, and mechanically-induced, compared to a healthy plant control.
• Two types of automated pollinator monitoring insect traps were tested. “InsectEye” was field tested to determine its ability to classify different families of pollinators. BeeEye was tested in the lab to determine its ability to classify different bee species.

Tennessee:

• A robotic platform named Amiga was purchased as the base for a pot-in-pot nursery tree harvester.
• Multiple end-effector has been designed and tested to securely lift the plastic pots for tree pots.
• Computer vision algorithms is being developed for tree recognition and localization.

Texas:

• Harvesting is one of the most labor-intensive operations for greenhouse production. We designed a robotic end-effector prototype for harvesting lettuce with a pair of shear blades and a two-finger gripper mechanism operated using a single linear actuator. Cutting and holding mechanisms work together using the first-class lever technique, where applied and acting forces are connected at the pivot point. The end-effector prototype was integrated into a linear arm connected to a two-directional linear manipulator system operated using an embedded controller. Validation experiments were conducted, and the results indicated a 95.15% success rate in cutting and a 94.45% success rate in securely holding the lettuce during harvest. The developed robotic end-effector serves as a pivotal component in lettuce harvesting automation.
• Crop disease scouting is the first critical step for controlling plant diseases. We employed lightweight deep-learning models to detect tomato diseases using digital images (bacterial spot, early blight, healthy, late blight, leaf mold, septoria leaf spot, two-spotted spider mites, target spot, and yellow leaf curl virus). Models were deployed on low-cost and low-power consumption Edge devices to investigate their performance capabilities as standalone Edge-AI solutions. Our lightweight models achieved accuracies of up to 98.25% in detecting tomato diseases. Edge device (Raspberry Pi) with AI accelerator (Google Coral) achieved the best cost/Frame per second (FPS) performance of 0.14 compared to other Edge devices NVIDIA Jetson AGX Orin and NVIDIA Jetson Nano Orin with cost/FPS of 0.7 and 0.26, respectively. These results showed the potential of standalone Edge-AI solutions using low-cost and low-power-consuming software and hardware resources for early tomato disease detections.
• Energy consumption per unit area can be reduced by increasing the crop yield per unit area by optimizing planting density. We developed an AI model (Ensemble Seg) that combines Mask RCNN (instance segmentation) and DeepLabV3 (semantic segmentation) to adjust the spacing between NFT channels for optimal greenhouse space utilization. Images were collected daily throughout the growth cycle, capturing the full development period of the lettuce plants. Our model resulted in a segmentation accuracy of 0.95. To assess plant overlap, segmented masks of each plant and its neighboring plants were identified based on the distances between each plant’s center. Overlapping was then determined by pixels with identical coordinates in an image across the segmented masks. The developed model can be used for intelligent decision support to optimize space use in greenhouse hydroponic production.

Arizona:

• Kocher, M.F., Smith, J.A., Arnett, G., Werning, J.L., Siemens, M.C., & Hanna, M.H. (2025). ASABE S658 Planter test standard: 1. Row unit test. Appl. Eng. Agric. (In press)
• Parmar, S., Lou, W., McGinnis, E., Didan, K., Siemens, M.C. & Haiquan, L. (2025). Integrating box-based deep learning with zero-shot segmentation for improved weed and crop classification in lettuce fields. Agric., MDPI (Submitted) doi: 10.20944/preprints202506.0642.v1
• Kocher, M.F., Smith, J.A., Arnett, G., Werning, J.L., Siemens, M.C., & Hanna, M.H. (2025). ASABE S658 Planter test standard: 2. Monitor system test. Appl. Eng. Agric. (Accepted)

California:

• Anokye-Bempah, L., Styczynski, T., Ristenpart, W.D., & Donis-González, I.R. 2025. A universal color curve for roasted arabica coffee. Scientific Report 15 (24192). doi: https://doi.org/10.1038/s41598-025-06601-w.
• Anokye-Bempah, L., Styczynski, T., Teixeira Fernandes, N.A., Gervay-Hague, J., K., Ristenpart, W., & Donis-González, I.R. 2024. How Roast Profile Affects the Dynamics of Titratable Acidity during Coffee Roasting. Scientific Reports 14:8237. Doi: https://doi.org/10.1038/s41598-024-57256-y.
• Arman Ahmadi, Andre Daccache, Minxue He, Peyman Namadi, Alireza Ghaderi Bafti, Prabhjot Sandhu, Zhaojun Bai, Richard L. Snyder, Tariq Kadir (2025). Enhancing the accuracy and generalizability of reference evapotranspiration forecasting in California using deep global learning, Journal of Hydrology: Regional Studies, Volume 59,102339.
• Chouaib El Hachimi, Salwa Belaqziz, Saïd Khabba, Andre Daccache, Bouchra Ait Hssaine, Hasan Karjoun, Youness Ouassanouan, Badreddine Sebbar, Mohamed Hakim Kharrou, Salah Er-Raki, Abdelghani Chehbouni (2025). Physics-informed neural networks for enhanced reference evapotranspiration estimation in Morocco: Balancing semi-physical models and deep learning, Chemosphere, Volume 374, 2025,144238
• de Oca, A., Magney, T., Vougioukas, S.G., Racan, D., Torrez-Orozco, A., Fennimore, S. Martin, F., Earles, M.  (2024) Strawberry fruit yield forecasting using image-based time-series plant phenological stages sequences. Computers and Electronics in Agriculture. 237, Part B, 110516.
• Donis-González, I.R., Zakharov, F., Bruhn, C.M., Cantwell, M.I., Reid, M.S., Slaughter, D.C., & Kader, A. 2025. Book chapter: Postharvest Technology of Horticultural Crops, 4th Edition.  Kader, A., Thompson, J.F. & Salveit, M. (ed) – ANR publication 21658. Quality Factors and Their Evaluation, Vol. 4, Davis, CA. pp. 61.
• F. Puig, R. Gonzalez Perea, A. Daccache, M.A. Soriano, J.A. Rodríguez Díaz, Convolutional neural networks for accurate estimation of canopy cover, Smart Agricultural Technology, Volume 10, 2025, 100750, ISSN 2772-3755,

• Farajpoor, P., Pourreza, A., Narimani, M., El-kereamy, A., & Fidelibus, M. W. Leaf spectral reflectance prediction using multihead attention neural networks. Proceedings Volume 13475, Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping X; 134750V (2025) https://doi.org/10.1117/12.3061298

• Fu, K., Zhu, Y., Frehner, E., Rizzo, K., Vougioukas, S. G., Bailey, B. (2025). Analysis of the Potential Improvement of Mechanical Fresh-Market Fruit Harvesting Efficiency Utilizing a Dynamically Adjustable Multi-Level Fruit Catching and Retrieval System. Smart Agricultural Technology, 12, 101228.
• Karkee, M., Vougioukas, S. G., Devadoss, S., Bhusal, S. (2025) Mechanization Efforts in Fruit Tree Pruning and Thinning. Choices, 2nd Quarter 40(2), 10-15
•  Khan, F. A., Khorsandi, F., Ali, M., Ghafoor, A., Khan, R. A. R., Umair, M., Shahzaib, Rehman, A., & Hussain, Z. (2025). Spray drift reduction management in agriculture: A review. Journal Name, 20(1), 1–36.
•  Khorsandi, F., Farhadi, P., Denning, G., Grzebieta, R., Gibbs, J., Godler, Y., Heydinger, G., Hicks, D., Jennissen, C., Lundqvist, P., McIntosh, A., Rechnitzer, G., Simmons, K., & Yoder, A. (2025). Advancing all-terrain vehicle safety in agriculture: Insights and innovations from global experts. Journal Name, 31(3), 173–202.
• Khorsandi, F., Wong, J., & de Moura Araujo, G. (2025). Is it safe for children to ride youth-sized all-terrain vehicles? Journal Name, 94, 216–228.
• Lincoln, J., Gorucu, S., Khorsandi, F., Aby, G. R., Elliott, K. C., Shutske, J., & Issa, S. (2025). Occupational safety research needs in the field of robotics and automated equipment in agriculture. Journal Name, 31(3), 217–230.

• Peanusaha, S., Pourreza, A., Kamiya, Y., Fidelibus, M. W., & Chakraborty, M. (2024). Nitrogen retrieval in grapevine (Vitis vinifera L.) leaves by hyperspectral sensing. Remote Sensing of Environment, 302, 113966.
• Pourreza, A., Kamiya, Y., Peanusaha, S., Jafarbiglu, H., Moghimi, A., & Fidelibus, M. W. (2025). Nitrogen retrieval in grapevine canopy by hyperspectral imaging. Computers and Electronics in Agriculture, 229, 109717.

• Shutske, J., Issa, S. S., Johnson, T., Gorucu, S., Lincoln, J., Khorsandi, F., Pate, M., Smith, E., Versweyveld, J., Aaron, M. A., & Aby, G. R. (2025). SAFERAG – Risk assessment, standards, and regulation: Needs and recommendations. Journal Name, 31(1), 1–13.
• Vougioukas, S. G., Karkee, M., Devadoss, S., Gallardo, K., Charlton, D. (2025) Mechanization Efforts in Fruit Harvesting. Choices, 2nd Quarter 40(2), 3-9
• Wei, P., Peng, C., Lu, W., Zhu, Y., and Vougioukas, S.G. (2025) Efficient and Safe Trajectory Planning for Autonomous Agricultural Vehicle Headland Turning in Cluttered Orchard Environments. IEEE Robotics and Automation Letters 10(3) 2574-2581.
• Wong, C., & Moghimi, A. (2025). Stakeholder mapping of precision weeding commercialization ecosystem in California. Agricultural Systems, 222, 104152. https://doi.org/10.1016/J.AGSY.2024.104152
• Mesgaran, M. (2024, December). Web of Weeds: Tracking Online Sales of Noxious Weed in the US. In AGU Fall Meeting Abstracts (Vol. 2024, pp. IN24A-01)
• Mesgaran, M., P. Robeck, L. Blank. 2024. Digital Menace: Quantifying the Online Sale of Noxious Weeds in the US and EU. Weed Day Workshop, June 20204, Davis.

Florida:

Journal Publications

• Chen, Y., A. Shu, Z. Liu, Y. Chen, W.S. Lee, and Y. Zhang. 2025. SP-RTSD: A lightweight real-time strawberry detection on edge devices for onboard robotic harvesting. Journal of Field Robotics, 2025; 1-19. https://onlinelibrary.wiley.com/doi/10.1002/rob.22582.
• Tapia, R., W.S. Lee, V.M. Whitaker, and S. Lee. 2025. Multiple methods for predicting strawberry powdery mildew severity from field canopy reflectance data. PhytoFrontiers https://doi.org/10.1094/PHYTOFR-06-24-0063-SC.
• Kim, J.-H., Y.-H. Cho, K.-M. Kim, C.-Y. Lee, W. S. Lee, and J.-S. Nam. 2025. Sweet potato farming in the USA and South Korea: A comparative study of cultivation pattern and mechanization status. Journal of Biosystems Engineering (2025) 50:210–224. https://doi.org/10.1007/s42853-025-00260-5.
• Huang, Z., W. S. Lee, P. Yang, Y. Ampatzidis, S. Agehara, and N. A. Peres. 2025. Advanced canopy size estimation in strawberry production: a machine learning approach using YOLOv11 and SAM. Computers and Electronics in Agriculture 236 (2025), 110501. https://doi.org/10.1016/j.compag.2025.110501.
• Huang, Z., W. S. Lee, P. Zhang, H. Jeon, and H. Zhu. 2025. SASP: segment any strawberry plant, an end-to-end strawberry canopy volume estimation. Smart Agricultural Technology 11 (2025) 101017. https://doi.org/10.1016/j.atech.2025.101017.
• Pardo-Beainy, C., C. Parra, L. Solaque, and W. S. Lee. 2025. Deep learning and georeferenced RGB-D imaging for hydroponic strawberry yield mapping. Smart Agricultural Technology 12 (2025) 101293. https://doi.org/10.1016/j.atech.2025.101293.
• Liu, S., Ampatzidis, Y., Zhou, C., & Lee, W. S. 2025. AI-driven time series analysis for predicting strawberry weekly yields integrating fruit monitoring and weather data for optimized harvest planning. Computers and Electronics in Agriculture, 233, 110212.
• Uthman, Q.O., R. Muñoz-Carpena, A. Ritter, and D.M. Kadyampakeni. 2025. Differential water and imidacloprid transport under unsaturated Florida citrus field conditions. Vadose Zone J. https://doi.org/10.1002/vzj2.70043
• Fort, J., V. Sharma, M. Dukes, S. Agehara, D. Kadyampakeni, and C.A. Chase. 2025. Micro-irrigation systems for water conservation during establishment and freeze protection in Florida strawberry production. Sci. Hortic. https://doi.org/10.1016/j.scienta.2025.114368
• De Souza Junior, J.P., and D.M. Kadyampakeni. 2025. Differential nutrient dynamics in cowpea and sunn hemp under organic orange peel powder fertilization. Nutr. Cycl. Agroecosyst. https://doi.org/10.1007/s10705-025-10432-6
• Barbosa, I.J., J.P. Souza Junior, M. Garcia Costa, J.C. Barbosa Lúcio, D.M. Kadyampakeni, P.L. Gratão, L. Bianco de Carvalho, R. de Mello Prado, S. Bianco. 2025. Silicon-enhanced non-enzymatic antioxidant defense mechanisms in young orange trees under glyphosate-induced stress. BMC Plant Biology https://doi.org/10.1186/s12870-025-07054-z
• Kadyampakeni, D.M., E. Scudiero, and R. Shrestha. 2025. Advances in precision irrigation management in the twenty-first century. Irrigation Science 43, XXX-XXX. https://doi.org/10.1007/s00271-025-01038-5
• Costa, M.G., R. de Amorim Cordeiro, J.K. Rodrigues das Merces, L.S. de Medeiros, A.M. Cardoso, R. de Mello Prado, D.M. Kadyampakeni, M.T. Siqueira Lacerda, and J.P. de Souza JuniorP. 2025. Silicon can attenuate glyphosate-induced stress in young Handroanthus albus by improving photosynthetic efficiency and decreasing cellular electrolyte leakage. Scientific Reports 15:23077. https://doi.org/10.1038/s41598-025-07527-z
• Sambani, D., A.A. Atta and D.M. Kadyampakeni. 2025. Evaluation of various fertilizer products for improved performance of HLB-affected citrus trees. J. Plant Nutr. 48(16):2882-2897. https://doi.org/10.1080/01904167.2025.2502146
• Kadyampakeni, D.M., R.G. Anderson, and M.P. Schmidt. 2025. Advancing salinity and nutrient management for irrigation science. Irrig. Sci. 43:321–327, https://doi.org/10.1007/s00271-025-01023-y
• De Souza Junior, J.P., D.M. Kadyampakeni, M.A. Shahid, R. de Mello Prado, and J.L. Prieto FajardoG. 2025. Mitigating abiotic stress in citrus: the role of silicon for enhanced productivity and quality. Plant Stress 16:100837,
• https://doi.org/10.1016/j.stress.2025.100837
• Januarie, C.J. and D.M. Kadyampakeni. 2025. Nitrogen fertilization dynamics on one-year-old Dendrocalamus asper (Schult. & Schult.f.) Backer bamboo in Florida, Adv. Bamboo Sci. 11:100150. https://doi.org/10.1016/j.bamboo.2025.100150.
• Bautista, A.S., A. Agenjos, A. Martínez, A.I. Escudero, P. García-Arizo, R. Simeón, C. Meyer, and D.M. Kadyampakeni. 2025. Osmolyte regulation as an avocado crop management strategy for improving productivity under high temperature. Horticult. 11, 245. https://doi.org/10.3390/horticulturae11030245.
• Brewer, M., S.L. Strauss, R. Kanissery, and D.M. Kadyampakeni. 2025. The impacts of legume and non-legume cover crops on the performance of HLB-affected citrus trees. Journal of Plant Nutrition, 48(13):2235-2249. https://doi.org/10.1080/01904167.2025.2474031.
• Sambani, D., T. Vashish, D.B. Bright, and D.M. Kadyampakeni. 2025. The influence of soil pH on citrus root morphology and nutrient uptake efficiency. HortSci. 60(5):657–666. https://doi.org/10.21273/HORTSCI18486-25
• Brewer, M., S.L. Strauss, C. Chase, B. Sellers, D.M. Kadyampakeni, E. van Santen, and R. Kanissery. 2025. Effects of cover crops on weed suppression in the inter-row of citrus orchards. Weed Sci. 73(e15):1-11. https://doi.org/10.1017/wsc.2024.72
• Atta, A.A., K.T. Morgan, S. Hamido, and D.M. Kadyampakeni. 2025. Irrigation optimization enhances water management and tree performance in commercial citrus groves on sandy soil. Irri. Sci. 43:329–346, https://doi.org/10.1007/s00271-024-00938-2
• Liu, D., Li, Z., Wu, Z., and C. Li. 2024. Digital Twin/MARS-CycleGAN: Improved object detection for MARS phenotyping robot.  Journal of Field Robotics. https://doi.org/10.1002/rob.22473
• Jiang, L., L. Fu, and C. Li. 2024. Apple tree architectural trait phenotyping with organ-level instance segmentation from point cloud. Computers and Electronics in Agriculture. 229, 109708.
• Rodriguez-Sanchez, J., J. Snider, K. Johnsen, and C. Li. 2024. Spatiotemporal registration of terrestrial laser scanning data for time-series field phenotyping. Frontiers in Plant Science. 15: 1436120.
• Petti, D., S. Li, and C. Li. 2024. Graph neural networks for lightweight plant organ tracking. Computers and Electronics in Agriculture. 225: 109294.
• Tan, C., J. Sun, A. Paterson, H. Song, C. Li. 2024. Three-View Cotton Flower Counting through Multi-Object Tracking and RGB-D Imagery. Biosystems Engineering. 246: 233-247
• Chen, Y., Xiao, Z., Pan, Y., Zhao, L., Dai, H., Wu, Z., Li, C., Zhang, T., Li, C., Zhu, D. and Liu, T., 2024. Mask-Guided Vision Transformer for Few-Shot Learning. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/TNNLS.2024.3418527.
• Hou, J., X. Wang, B. Park. C. Li. 2024. A multiscale computation study on bruise susceptibility of blueberries from mechanical impact. Postharvest Biology and Technology. 208: 112660.
• Ye Chu, Josh Clevenger, Kendall Lee, Jing Zhang, Changying Li. Genetic breeding to improve freeze tolerance in blueberries, a review. Horticulturae. 11(6).
• Monica Borghi, C. Li, et al. 2025. Enhancing entomophilous pollination for sustainable crop production. Horticultural Research. 122(4), e70234.
• Tan, C., C. Li, P. Perkins-Veazie, H. Oh, R. Xu, M. Iorizzo. 2025. High throughput assessment of blueberry fruit internal bruising using deep learning models. Frontiers in Plant Science. 16, 1575038.
• Li, Z., R. Xu, C. Li, L. Fu. 2025. Visual Navigation and Crop Mapping of a Phenotyping Robot MARS-PhenoBot in Simulation. Smart Agricultural Technology. 11:100910.
• Li, Z., R. Xu, C. Li, P. Munoz, F. Takeda, and B. Leme. 2025. In-field blueberry fruit phenotyping with a MARS-PhenoBot and customized BerryNet. Computers and Electronics in Agriculture. 232, 110057.

Conference Papers/Presentations/Posters

• Huang, Z., and W. S. Lee. 2025. A state space model with tree topology for strawberry detection. AI in Agriculture Conference: The Role of AI in Autonomous Agricultural Systems and Socioeconomic Effects. Starkville, MS, March 31 to April 2, 2025.
• Liu S., Ampatzidis Y., Lee W.S., Zhou C., 2025. Optimizing strawberry harvest planning through machine vision and AI-enabled predictive analytics. AI in Agriculture Conference: The Role of AI in Autonomous Agricultural Systems and Socioeconomic Effects. Starkville, MS, March 31 to April 2, 2025.
• Huang, Z., W.S. Lee, and M. Le. 2025. AI-driven plant tracking and segmentation for precise canopy estimation in strawberry field. ASABE Paper No. 202500347. St. Joseph, MI.: ASABE.
• Kamsikiri, K., A. Atta and D.M. Kadyampakeni. 2025. Comparison of conventional drip and microspinkler irrigation in citrus production systems on Florida sandy soils. ASABE Annual Meeting Conference Proceedings, Toronto, Canada. pp 1-13. https://doi.org/10.13031/aim.202500888
• Kamsikiri K., A. Atta, and D.M. Kadyampakeni. 2025. Comparison of Conventional and Drip Irrigation Systems for Young HLB-Affected Citrus Trees. 136th Florida State Horticultural Society (FSHS) Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Bonda L.F. and D.M. Kadyampakeni. 2025. Impact of nitrogen rates on growth and biomass accumulation of young macadamia trees. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Thompson, T.R. and D.M. Kadyampakeni. 2025. Impacts of nutrient ratios of calcium and zinc on citrus growth and root development. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• de Souza Junior, J.P. and D.M. Kadyampakeni. 2025. Comparative analysis of stabilized and non-stabilized silicon sources on photosynthetic performance of young orange trees. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Ritenour, M.A., A.A. Atta, C. Hu, A. Beany, and D.M. Kadyampakeni. 2025. Tree nutrition effects on postharvest fruit quality and shelf life of ‘Hamlin’ sweet orange. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Iqbal, S., D. Kadyampakeni and M.A. Shahid. 2025. Developing site-specific recommendations on nitrogen application rates and timing for satsuma mandarin production in north Florida. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Atta A., K.T. Morgan, M.A. Ritenour, M.A. Shahid, A. Wright, K. Morgan, M. Zekri, C. Oswalt, D. Williams and D.M. Kadyampakeni. 2025. The impact of phosphorus rates on HLB-affected tree health and performance in sandy soils. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Basar N.U., M.A. Shahid and D.M. Kadyampakeni. 2025. Impact of variable nitrogen rates on the growth and yield of HLB-affected sweet orange trees. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Prieto Fajardo, J.L.G, M. Shahid, W. Hammond, L. Diepenbrock and D.M. Kadyampakeni. 2025. Exploring the potential of silicon nanoparticles to mitigate water stress in citrus. 136th FSHS Annual Meeting, June 8-10, 2025. Bonita Springs, FL. (volunteered)
• Basar, N.U., M.A. Shahid and D.M. Kadyampakeni. 2025. Evaluating the impact of biostimulants on young sweet orange trees grafted onto different rootstocks. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Peddapuli, M., A. AttaP and D.M. Kadyampakeni. 2025. Optimizing nitrogen and phosphorus management for HLB-affected sweet orange. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Agunbiade, L.GM. Nunes and D.M. Kadyampakeni. 2025. Assessing the effects of varying rates of irrigation and potassium fertilization on the growth of Dendrocalamus asper bamboo in Florida. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Sambani, D., T. Vashisth and D.M. Kadyampakeni. 2025. The influence of soil pH on citrus root morphology and nutrient uptake efficiency. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Prieto, J. and D.M. Kadyampakeni. 2025. Exploring the potential of silicon nanoparticles to mitigate water stress in citrus. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Saleem, Y., S. Agehara and D.M. Kadyampakeni. 2025. Effects of reclaimed water on blueberry seedling growth and root morphology. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Kamsikiri, K. and D.M. Kadyampakeni. 2025. Optimizing molybdenum fertilization for young HLB-affected citrus trees. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Thompson, T. and D.M. Kadyampakeni. 2025. Impacts of nutrient ratios of calcium and zinc on citrus growth and root development. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)
• Januarie, C.J., L. Sharma, J. Vendramini, and D.M. Kadyampakeni. 2025. Variable rate fertilization of phosphorus in young Dendrocalamus asper bamboo in Florida. 17th SWES Research Forum, Gainesville, FL. Feb. 10, 2025. (volunteered)

• Petti, D. and C. Li. Active Learning for Real-Time Flower Counting with a Ground Mobile Robot. ASABE Annual International Meeting. Paper Number: 202400607. July 28-31, 2024, Anaheim, California.
• Muller. J, D. Petti, C. Li, S. Gorucu, M. Pilz, and B. Weichelt. Investigating the use of large language models in agricultural injury surveillance. ASABE Annual International Meeting. Paper Number: 202400572. July 28-31, 2024, Anaheim, California

Georgia:

• Rayamajhi, A., Lu, G., Tollner, E. W., Williams-Woodward, J., & Mahmud, M. S. (2025). Assessing ornamental tree maturity and spray requirements using depth sensing and LiDAR technologies. Smart Agricultural Technology, 101120.
• Rayamajhi, A., Jahanifar, H., & Mahmud, M. S. (2024). Measuring ornamental tree canopy attributes for precision spraying using drone technology and self-supervised segmentation. Computers and Electronics in Agriculture, 225, 109359.
• Rayamajhi, A. (2024). Precision Sprayer Technologies for Enhanced Ornamental Crop Management (Master's thesis, University of Georgia).

Kentucky:

• Dvorak, J. (2025). AI Tools and Text Embedding for Session Organization at ASABE’s Annual International Meeting. Journal of the ASABE, (in press). https://doi.org/10.13031/ja.16328
• Dvorak, J. (2024). Utilizing Super Capacitors to Improve Battery Performance in Electric Mobile Machinery. Applied Engineering in Agriculture, 40(6), 669–677. https://doi.org/10.13031/aea.16062
• Dvorak, J., Smith, B.*. (2024). Powering In-Field Continuous Robotic Systems Using Solar Energy Systems. 67(3): 617-630. Journal of the ASABE. doi: 10.13031/ja.15579

Michigan:

Journal Publications

• Xu, J., Lu, Y., 2025. 3D vision-based perception and length estimation of green asparagus for selective harvesting. Journal of the ASABE 68 (2), 239-256.
• Lu, Y., Mohammadi, P., 2025. Automated asparagus harvesting technology: A review of research and developments since the 1950s in the United States and beyond. Computers and Electronics in Agriculture 237, 110744
• Deng, B., Lu, Y., Vander Weide, J., 2025. Development and preliminary evaluation of a YOLO-based fruit counting and maturity evaluation mobile application for blueberries. Applied Engineering in Agriculture 41(3), 391-399.
• Deng, B., Lu, Y., 2025. Weed image augmentation by ControlNet-added stable diffusion for multi-class weed detection. Computers and Electronics in Agriculture 232, 110123.
• Mu, X., Y. Lu, 2025. Non-destructive detection of spotted wing Drosophila infestation in blueberry fruit using hyperspectral imaging technology. Agricultural Communications 3(3), 100096.
• Xu, J., Lu, Y., Deng, B., 2024. Design, prototyping, and evaluation of a new machine vision-based automated sweetpotato grading and sorting system. Journal of the ASABE 67 (5), 1369-1380.
• Deng, B., Lu, Y., Li, Z., 2024. Detection, counting, and maturity assessment of blueberries in canopy images using YOLOv8 and YOLOv9. Smart Agricultural Technology 9, 100620.
• Wade, C., Check, J., Chilvers, M., Dong, Y., (2025). Monitoring leaf wetness dynamics in corn and soybean fields using an IoT (Internet of Things)-based monitoring system. Smart Agricultural Technology. 11, 100919.
• Spafford, J., Hausbeck, M., Werling, B., Tucker, S., Dong, Y., (2025). Development of an Internet of Things (IoT)-Based Disease Forecaster to Manage Purple Spot On Asparagus Fern. Smart Agricultural Technology. 11, 100941.
• Kumari, S., Ali, N., Dagati, M., Dong, Y. (2025). IoT-Enabled Soil Moisture and Conductivity Monitoring Under Controlled and Field Fertigation Systems. AgriEngineering. 7 (7). 207.
• Dong, Y., Tucker, S., Singh, G., Ali, N., Yazdanpanah, N., Vander Wide, J., Sears, M., (2025). Optimizing Soil Moisture Sensor Placement Through Spatial Variability Analysis in Orchards. Smart Agricultural Technology. 10. 101273

Conference Papers/Other Publications

• Mu, X., Lu, Y., Deng, , 2025. A comparative benchmark of real-time detectors for blueberry detection towards precision orchard management. arXiv preprint: 2509.20580.
• Xu, J., Lu, Y., 2025. Development and evaluation of a multispectral vision-based automated sweet potato sorting system. Sensing for Agriculture and Food Quality and Safety XVII, 1348402. 
• Deng, B., Lu, Y., Brainard, D., 2025. Semi-Supervised Weed Detection in Vegetable Fields: In-domain and Cross-domain Experiments. arXiv preprint:2502.17673. Paper presented at the 2025 AgriControl Conference.
• Deng, B., Lu, Y., 2025. Weed image augmentation by IP-adapter-based stable diffusion for multiclass weed detection. Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications III; 1345909.
• Deng, B., Lu, Y., Brainard, Improvements and Evaluation of a Smart Sprayer Prototype for Weed Control in Vegetable Crops. 2025 ASABE Annual International Meeting 2500323
• Singh, N., Lu, Y., 2025. Development and laboratory assessment of cutting and snapping mechanisms for green asparagus harvesting. 2025 ASABE Annual International Meeting 2500323.

Mississippi:

• Li, Jiajia, Xinda Qi, Seyed Hamidreza Nabaei, Meiqi Liu, Dong Chen, Xin Zhang, Xunyuan Yin, and Zhaojian Li. "A survey on 3D reconstruction techniques in plant phenotyping: from classical methods to neural radiance fields (NeRF), 3D Gaussian splatting (3DGS), and beyond." arXiv preprint arXiv:2505.00737 (2025).
• Chen, Dong, and Yanbo Huang. "Integrating Reinforcement Learning and Large Language Models for Crop Production Process Management Optimization and Control through A New Knowledge-Based Deep Learning Paradigm." Computers and Electronics in Agriculture (2025).
• A Comparative Study of Deep Reinforcement Learning for Crop Production Management Joseph Balderas, Chen, Dong, Yanbo Huang, Li Wang, Ren-Cang Li, Smart Agriculture Technology, 2025
• Seyed Hamidreza Nabaei, Ryan Lenfant, Viswajith Govinda Rajan, Dong Chen, Michael P Timko, Bradford Campbell, Arsalan Heydarian, “Detecting Plant VOC Traces Using Indoor Air Quality Sensors”, Indoor Air (2025)

New York:

• Kanaley, K., Murdock, M.J., Qiu, T. et al. Maui: modular analytics of UAS imagery for specialty crop research. Plant Methods 21, 65 (2025). https://doi.org/10.1186/s13007-025-01376-7
• Liu, E., Gold, K. M., Cadle‐Davidson, L., Kanaley, K., Combs, D., & Jiang, Y. (2025). PhytoPatholoBot: Autonomous Ground Robot for Near‐Real‐Time Disease Scouting in the Vineyard. Journal of Field Robotics.
• Kanaley, K., Combs, D. B., Paul, A., Jiang, Y., Bates, T., & Gold, K. M. (2024). Assessing the capacity of high-resolution commercial satellite imagery for grapevine downy mildew detection and surveillance in New York state. Phytopathology®, 114(12), 2536-2545.
• Kanaley, K., Murdock, M., Liu, E., Romero, F., Paul, A., Chadwick, D., ... & Gold, K. (2024, December). Leveraging Thermal, Multi-and Hyperspectral UAS Data to Monitor Disease Impacts on Grapevine Physiology. In AGU Fall Meeting Abstracts (Vol. 2024, pp. GC32A-01).
• Yu, J., Jakubowski, R., Bates, T., Jiang, Y., & Chen, C. (2024). Integrating Hyperspectral Imaging and Machine Learning for Non-Destructive Damage Detection of Grapes. In 2024 ASABE Annual International Meeting (p. 1). American Society of Agricultural and Biological Engineers.

Pennsylvania:

Journal Articles:

• Pawikhum, K., Yang, Y., He, L., & Heinemann, P. (2025). Development of a machine vision system for apple bud thinning in precision crop load management. Computers and Electronics in Agriculture 236, 110479.
• Hua, W., Heinemann, P., & He, L. (2025). Frost management in agriculture with advanced sensing, modeling, and artificial intelligent technologies: A review. Computers and Electronics in Agriculture 231, 110027.
• Li, J., Lammers, K., Yin, X., Yin, X., He, L., Sheng, J., Lu, R., & Li, Z. (2025). MetaFruit meets foundation models: Leveraging a comprehensive multi-fruit daaset for advancing agricultural foundation models. Computers and Electronics in Agriculture 231, 109908.
• Kang, C., Mu, X., Seffrin, A.N., Di Gioia, F., & He, L. (2025). A recursive segmentation model for bok choy growth monitoring with Internet of Things (IoT) technology in controlled environment agriculture. Computers and Electronics in Agriculture 230, 109866.
• Hua, W., He, L., Heinemann, P., & Zhu, M. (2025). Precision heating strategy based dynamic heater path planning for frost protection in apple orchards. Biosystems Engineering 250: 117-132.
• Yang, Y., Mali, P., Arthur, L., Molaei, F., Atsyo, S., Geng, J., He, L., & Ghatrehsamani, S., (2025). Advanced technologies for precision tree fruit disease management: A review. Computers and Electronics in Agriculture 229, 109704.
• Pawikhum, K., He, L., Heinemann, P., & Bock, R.G. (2025). Design of End-Effectors for Thinning Apple in the Green Fruit Stage. Journal of the ASABE 68(2), 465-476.
• Majeed, Y., Fu, L., & He, L. (2024). Artificial intelligence-of-things (AIoT) in precision agriculture. Frontiers in Plant Science 15, 1369791.
• Kang, C., He, L., & Zhu, H. (2024). Assessment of spray patterns and efficiency of an unmanned sprayer used in planar growing systems. Precision Agriculture 25(5), 2271-2291.
• Hussain, M., He, L., Schupp, J., Lyons, D., & Heinemann, P. (2024). Green fruit‐stem pairing and clustering for machine vision system in robotic thinning of apples. Journal of Field Robotics 2024: 1-28.
• Hua, W., Heinemann, P., & He, L. (2024). Heat transfer modeling with fixed and mobile heaters for frost protection in apple orchards. Computers and Electronics in Agriculture 227, 109525.
• Mu, X., He, L., Heinemann, P., Schupp, J., Karkee, M., & Zhu, M. (2024). UGV‐based precision spraying system for chemical apple blossom thinning on trellis trained canopies. Journal of Field Robotics 2024: 1-12.

Extension Articles:

• Kang, C., He, L., and Peter, K. (2024). A low-cost microclimate monitoring system for orchard disease management. Pennsylvania Fruit News. 
• Arthur, L., Brunharo, C., Hussain, M., and He, L. (2024). Precision weed management in tree fruit orchards. Pennsylvania Fruit News.
• Mahnan, S., He, L., and Pecchia, J. (2025). Overview of button mushroom harvesting technologies. Penn State Extension.

Thesis and Dissertation:

• Basnet, Akash. (2024). Design of machine vision system and an end-effector for robotic apple harvesting in orchards. MS Thesis. The Pennsylvania State University.
• Yang, Yanqiu. (2025). Innovative integrated pest management: Data-driven approaches and noninvasive technologies for enhanced monitoring and decision-making in specialty crops. PhD Dissertation. The Pennsylvania State University.
• Geng, Jiarui. (2025). Multi-system framework for insect monitoring: From laboratory imaging to field applications. MS Thesis. The Pennsylvania State University.

Texas:

• Kuruppuarachchi, Chamika, Fnu Kulsoom, Hussam Ibrahim, Hamid Khan, Azlan Zahid, and Mazhar Sher. 2024. “Advancements in Plant Wearable Sensors.” Computers and Electronics in Agriculture 229: 109778.
• Majeed, Yaqoob, Mike O. Ojo, and Azlan Zahid. 2024. “Standalone Edge AI-Based Solution for Tomato Diseases Detection.” Smart Agricultural Technology 9: 100547.
• Ikram, Muhammad, Sikander Ameer, Fnu Kulsoom, Mazhar Sher, Ashfaq Ahmad, Azlan Zahid, and Young Chang. 2024. “Flexible Temperature and Humidity Sensors of Plants for Precision Agriculture: Current Challenges and Future Roadmap.” Computers and Electronics in Agriculture 226:109449.
• Bashir, Al, Yaqoob Majeed, and Azlan Zahid. 2024. “Development of an End-Effector for Robotic Harvesting of Hydroponic Lettuce.” In 2024 ASABE Annual International Meeting, Paper Number: 2400401 doi:10.13031/aim.202400401
• Ojo, Mike O., Azlan Zahid, and Joseph G. Masabni. 2024. “Estimating Hydroponic Lettuce Phenotypic Parameters for Efficient Resource Allocation.” Computers and Electronics in Agriculture 218: 108642.