Publications

@article{churuvija_pose-versatile_2025,

title = {A pose-versatile imaging system for comprehensive 3D modeling of planar-canopy fruit trees for automated orchard operations},

author = {Martin Churuvija and Ranjan Sapkota and Dawood Ahmed and Manoj Karkee},

url = {https://www.sciencedirect.com/science/article/pii/S0168169925000055},

doi = {10.1016/j.compag.2025.109899},

issn = {0168-1699},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-01},

journal = {Computers and Electronics in Agriculture},

volume = {230},

pages = {109899},

abstract = {High-density tree fruit production systems employ SNAP (Simple, Narrow, Accessible and Productive) canopy architectures, such as the UFO (Upright Fruiting Offshoots) system, that require intensive management practices. The growing adoption of these production systems in the USA, along with the decline of farm labor in the country, has sparked interest in automating manual orchard operations. Machine vision plays a key role in the development of robotic solutions because the success of these robots largely depends on the ability of the imaging systems (ISs) to quickly and accurately generate three-dimensional (3D) models of the surroundings. Tree models, for example, are essential to determine cutting points and guide cutting tools to the correct positions when pruning selectively. However, the ISs proposed in recent studies do not produce sufficiently comprehensive models, are expensive, and/or are impractical for commercial applications. In this study, a novel, time-efficient, and pose-versatile imaging system (Mobile IS) was developed and tested to overcome these issues. The Mobile IS utilized off-the-shelf cameras to capture an initial 3D point cloud model of a scene and then dynamically refined the model in real time by integrating additional point clouds from close range and different poses using simple photogrammetric techniques. To evaluate the performance of the Mobile IS, a wide range of UFO-trained tree offshoot diameters (OSDs), and side-branch lengths (SBLs) and spacings (SBSs)\textemdashparameters on which the pruning rules for UFOs are based\textemdashwere measured on the models reconstructed by the Mobile IS and a fixed-pose imaging system (Fixed IS) and compared to ground truth. Mobile IS models exhibited higher accuracy compared to the Fixed IS models, as evidenced by the root mean square (RMS) errors of the Mobile IS measurements (RMSEOSD of 4.9 mm, RMSESBL of 8.0 mm, and RMSESBS of 3.6 mm) and the Fixed IS measurements (RMSEOSD of 5.9 mm, RMSESBL of 18.1 mm, and RMSESBS of 3.8 mm). The versatility of pose enabled the Mobile IS to overcome occlusions and areas with low-confidence depth values. The results suggest that the Mobile IS holds promise as an IS for various robotic applications, including automated pruning, thinning and harvesting, across different tree fruit crops and canopy architectures.},

keywords = {AI, Labor},

pubstate = {published},

tppubtype = {article}

}

@article{weingram_definition_2025,

title = {A definition and taxonomy of digital twins: case studies with machine learning and scientific applications},

author = {Adam Weingram and Carolyn Cui and Stephanie Lin and Samuel Munoz and Toby Jacob and Joshua Viers and Xiaoyi Lu},

url = {https://www.frontiersin.org/journals/high-performance-computing/articles/10.3389/fhpcp.2025.1536501/full},

doi = {10.3389/fhpcp.2025.1536501},

issn = {2813-7337},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-01},

journal = {Frontiers in High Performance Computing},

volume = {3},

note = {Publisher: Frontiers},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ahmed_estimating_2025,

title = {Estimating optimal crop-load for individual branches in apple tree canopies using YOLOv8},

author = {Dawood Ahmed and Ranjan Sapkota and Martin Churuvija and Manoj Karkee},

url = {https://www.sciencedirect.com/science/article/pii/S0168169924010883},

doi = {10.1016/j.compag.2024.109697},

issn = {0168-1699},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-01},

journal = {Computers and Electronics in Agriculture},

volume = {229},

pages = {109697},

abstract = {Shortage of labor in fruit crop production has become a significant challenge in recent years. Therefore, mechanized and automated machines have emerged as promising alternatives to labor-intensive orchard operations such as harvesting, pruning, and thinning. One of the key aspects of the automated machines in accomplishing these tasks is their ability to identify tree canopy parts such as trunk and branches and estimate their geometric and topological parameters such as branch diameter, branch length, branch angles, and spacing between branches. By utilizing geometric parameters such as branch diameter, length, and orientation, researchers then can develop automated pruning and thinning systems that make more effective decisions to achieve optimal fruit yield and quality by accurately estimating the desired crop-load. In this study, we propose a machine vision system for estimating one of the canopy parameters in apple orchards: branch diameter. This parameter was used to estimate the optimal number of fruit that individual branches could bear in a commercial orchard, which provides a basis for robotic pruning, flower thinning, and fruitlet thinning so that desired fruit yield and quality could be achieved. Utilizing color and depth information collected with an RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA), a YOLOv8-based instance segmentation technique was developed to identify trunks and branches of apple trees in the dormant season. We then applied a Principal Component Analysis (PCA) technique to estimate branch orientation, which was subsequently utilized to estimate branch diameter. The estimated branch diameter was used to calculate the Limb Cross Sectional Area (LCSA), which was then used to estimate optimal crop-load, as a larger LCSA indicates a higher potential fruit-bearing capacity of the branch. With this approach, Root Mean Squared Error (RMSE) for branch diameter estimation was calculated to be 2.06 mm (relative RMSE 10.82%) and the same for crop-load estimation (Number of fruits per branch) to be 3.93 (relative RMSE 22.25%). Our study demonstrated a promising workflow with a high level of performance in identifying and sizing branches of apple trees in a dynamic orchard environment and integrating farm management practices into automated decision-making for optimizing crop-load in apple orchards.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{abatzoglou_shorter_2025,

title = {Shorter growing seasons may moderate climate change effects on crop water demands},

author = {John T Abatzoglou and Lauren E Parker and Joshua H Viers and Josue Medell\'{i}n-Azuara and Alvar Escriva-Bou and Justin L Huntington and Emily L Williams and Kitri Rajagopalan},

url = {https://dx.doi.org/10.1088/1748-9326/adb1f5},

doi = {10.1088/1748-9326/adb1f5},

issn = {1748-9326},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-01},

journal = {Environmental Research Letters},

volume = {20},

number = {3},

pages = {034017},

abstract = {Rising evaporative demand (ETo) with a warming climate contributes to diminished water availability in water-stressed agricultural regions globally. While increased ETo typically necessitates increased irrigation, we explore how crop phenological response can moderate this challenge. Focusing on five key agricultural crops in California’s San Joaquin Valley (SJV), we employ coupled water balance and phenology models to project crop water demands as a function of increased ETo and changing phenology. All crops exhibited accelerated growth from a shortened growing season with warming. The shortened crop maturation period partially to fully offset increased crop water demands due to rising ETo, with the largest phenological influence for annual crops such as tomato and corn. By contrast, models that do not account for phenological changes showed increased irrigation demands of approximately 3.5%\textendash4.5% per °C of global warming primarily due to increased ETo. Integration with dynamic phenological models for the five key crops across the extent of agricultural land in the SJV showed a 1.6% decrease in irrigation needs under a 2 °C warming scenario. While phenological change alongside plant physiological responses to increased atmospheric CO2 may help buffer the impact of climate change on crop irrigation demand, decreased crop yields with a shorter growing season and continued reliance of groundwater reserves for agricultural water use and reduced spring snowpack will threaten coupled agricultural and water security in the region.},

note = {Publisher: IOP Publishing},

keywords = {AI, Water},

pubstate = {published},

tppubtype = {article}

}

@article{sapkota_multi-modal_2025,

title = {Multi-Modal LLMs in Agriculture: A Comprehensive Review},

author = {Ranjan Sapkota and Rizwan Qureshi and Muhammad Usman Hadi and Syed Zohaib Hassan and Ferhat Sadak and Maged Shoman and Muhammad Sajjad and Fayaz Ali Dharejo and Achyut Paudel and Jiajia Li and Zhichao Meng and John Shutske and Manoj Karkee},

url = {https://ieeexplore.ieee.org/document/11173627},

doi = {10.1109/TASE.2025.3612154},

issn = {1558-3783},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {IEEE Transactions on Automation Science and Engineering},

volume = {22},

pages = {22510\textendash22540},

abstract = {Given the rapid emergence and applications of Multi-Modal Large Language Models (MM-LLMs) across various scientific fields, insights regarding their applicability in agriculture are still only partially explored. This paper conducts an in-depth review of MM-LLMs in agriculture, focusing on understanding how MM-LLMs can be developed and implemented to optimize agricultural processes, increase efficiency, and reduce costs. Recent studies have explored the capabilities of MM-LLMs in agricultural information processing and decision-making. Despite these advancements, significant gaps persist, particularly in addressing domain-specific challenges such as variable data quality and availability, integration with existing agricultural systems, and the creation of robust training datasets that accurately represent complex agricultural environments. Moreover, a comprehensive understanding of the capabilities, challenges, and limitations of MM-LLMs in agricultural information processing and application is still missing. Exploring these areas is crucial to providing the community with a broader perspective and a clearer understanding of MM-LLMs’ applications, establishing a benchmark for the current state and emerging trends in this field. To bridge this gap, this survey reviews the progress of MM-LLMs and their utilization in agriculture, with an additional focus on 11 key research questions (RQs), where 4 RQs are general and 7 RQs are agriculture focused. By addressing these RQs, this review outlines the current opportunities and challenges, limitations, and future roadmap for MM-LLMs in agriculture. The findings indicate that multi-modal MM-LLMs not only simplify complex agricultural challenges but also significantly enhance decision-making and improve the efficiency of agricultural image processing. These advancements position MM-LLMs as an essential tool for the future of farming. For continued research and understanding, an organized and regularly updated list of papers on MM-LLMs is available at https://github.com/JiajiaLi04/Multi-Modal-LLMs-in-Agriculture Note to Practitioners\textemdashMotivated by the need to optimize agricultural practices, this paper investigates the use of Large Language Models (MM-LLMs) to improve efficiency and decision-making in agriculture. We delve into critical RQs to reveal the capabilities and challenges of MM-LLMs, and their potential applications in the agricultural sector. Looking ahead, our findings suggest a promising future for the integration of MM-LLMs in agriculture, potentially revolutionizing how we manage and operate farms.},

keywords = {Agriculture, Analytical models, ChatGPT, Computational modeling, Computer vision, Data models, Deep learning, Farming, generative artificial intelligence, Hidden Markov models, Large language models (LLMs), Machine Learning, Precision agriculture, Reviews, Training, Transformers, Translation, Vision-language models},

pubstate = {published},

tppubtype = {article}

}

@article{ahmed_integrated_2025,

title = {An Integrated Visual Servoing Framework for Precise Robotic Pruning Operations in Modern Commercial Orchard},

author = {Dawood Ahmed and Basit Muhammad Imran and Martin Churuvija and Manoj Karkee},

url = {https://www.sciencedirect.com/science/article/pii/S2405896325024565},

doi = {https://doi.org/10.1016/j.ifacol.2025.11.758},

issn = {2405-8963},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {IFAC-PapersOnLine},

volume = {59},

number = {23},

pages = {28\textendash33},

abstract = {This study presents a vision-guided robotic control system for automated fruit tree pruning applications. Traditional pruning practices are labor-intensive and limit agricultural efficiency and scalability, highlighting the need for advanced automation. A key challenge is the precise, robust positioning of the cutting tool in complex orchard environments, where dense branches and occlusions make target access difficult. To address this, an Intel RealSense D435 camera is mounted on the flange of a UR5e robotic arm and CoTracker3, a transformer-based point tracker, is utilized for visual servoing control that centers tracked points in the camera view. The system integrates proportional control with iterative inverse kinematics to achieve precise end-effector positioning. The system was validated in Gazebo simulation, achieving a 77.77% success rate within 5mm positional tolerance and 100% success rate within 10mm tolerance, with a mean end-effector error of 4.28 ± 1.36 mm. The vision controller demonstrated robust performance across diverse target positions within the pixel workspace. The results validate the effectiveness of integrating vision-based tracking with kinematic control for precision agricultural tasks. Future work will focus on real-world implementation and the integration of force sensing for actual cutting operations.},

keywords = {agricultural automation, agricultural robotics, perception, precision pruning, robotic manipulator, sensing, visual servoing},

pubstate = {published},

tppubtype = {article}

}

@article{belakaria_non-myopic_2025,

title = {Non-Myopic Multi-Objective Bayesian Optimization},

author = {Syrine Belakaria and Alaleh Ahmadian and Barbara E. Engelhardt and Stefano Ermon and Jana Doppa},

url = {https://openreview.net/forum?id=2e1aZZd88C},

issn = {2835-8856},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Transactions on Machine Learning Research},

abstract = {We consider the problem of finite-horizon sequential experimental design to solve multi-objective optimization (MOO) of expensive black-box objective functions. This problem arises in many real-world applications, including materials design, where we have a small resource budget to make and evaluate candidate materials in the lab. We solve this problem using the framework of Bayesian optimization (BO) and propose the first set of non-myopic methods for MOO problems. Prior work on non-myopic BO for single-objective problems relies on the Bellman optimality principle to handle the lookahead reasoning process. However, this principle does not hold for most MOO problems because the reward function needs to satisfy some conditions: scalar variable, monotonicity, and additivity. We address this challenge by using hypervolume improvement (HVI) as our scalarization approach, which allows us to use a lower-bound on the Bellman equation to approximate the finite-horizon using a batch expected hypervolume improvement (EHVI) acquisition function (AF) for MOO. Our formulation naturally allows us to use other improvement-based scalarizations and compare their efficacy to HVI. We derive three non-myopic AFs for MOBO: 1) the Nested AF, which is based on the exact computation of the lower bound, 2) the Joint AF, which is a lower bound on the nested AF, and 3) the BINOM AF, which is a fast and approximate variant based on batch multi-objective acquisition functions. Our experiments on multiple diverse real-world MO problems demonstrate that our non-myopic AFs substantially improve performance over the existing myopic AFs for MOBO.},

keywords = {AI},

pubstate = {published},

tppubtype = {article}

}

@article{sapkota_improved_2025,

title = {Improved YOLOv12 with LLM-Generated Synthetic Data for Enhanced Apple Detection and Benchmarking Against YOLOv11 and YOLOv10⁎⁎Sponsor and financial support acknowledgment goes here. Paper titles should be written in uppercase and lowercase letters, not all uppercase.},

author = {Ranjan Sapkota and Manoj Karkee},

url = {https://www.sciencedirect.com/science/article/pii/S2405896325024929},

doi = {https://doi.org/10.1016/j.ifacol.2025.11.793},

issn = {2405-8963},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {IFAC-PapersOnLine},

volume = {59},

number = {23},

pages = {239\textendash244},

abstract = {Accurate fruit detection in orchards remains a major bottleneck in agricultural automation due to the high cost and labor demands of data collection and annotation. This study evaluated the performance of the YOLOv12 object detection model, and compared against the performances YOLOv11 and YOLOv10 for apple detection in commercial orchards based on the model training completed entirely on synthetic images generated by Large Language Models (LLMs). The YOLOv12n configuration achieved the highest precision at 0.916, the highest recall at 0.969, and the highest mean Average Precision (mAP@50) at 0.978. In comparison, the YOLOv11 series was led by YOLO11x, which achieved the highest precision at 0.857, recall at 0.85, and mAP@50 at 0.91. For the YOLOv10 series, YOLOv10b and YOLOv10l both achieved the highest precision at 0.85, with YOLOv10n achieving the highest recall at 0.8 and mAP@50 at 0.89. These findings demonstrated that YOLOv12, when trained on realistic LLM-generated datasets surpassed its predecessors in key performance metrics. The technique also offered a cost-effective solution by reducing the need for extensive manual data collection in the agricultural field. In addition, this study compared the computational efficiency of all versions of YOLOv12, v11 and v10, where YOLOv11n reported the lowest inference time at 4.7 ms, compared to YOLOv12n’s 5.6 ms and YOLOv10n’s 5.9 ms. Although YOLOv12 is new and more accurate than YOLOv11, and YOLOv10, YOLO11n still stays the fastest YOLO model among YOLOv10, YOLOv11 and YOLOv12 series of models.},

keywords = {agricultural automation, Apple detection, LLM, Synthetic Image Generation, YOLOv10, YOLOv11, YOLOv12, YOLOv12 object detection, You Only Look Once},

pubstate = {published},

tppubtype = {article}

}