Smart agricultural technology最新文献

{"title":"Research on Operational Trajectory Control Methods and Per-formance Testing of Multi-Degree-of-Freedom Robotic Arms for Fruit Tree Pruning","authors":"Long Song ,&nbsp;He Zhu ,&nbsp;Yan Zhou ,&nbsp;Lei He","doi":"10.1016/j.atech.2026.102016","DOIUrl":"10.1016/j.atech.2026.102016","url":null,"abstract":"<div><div>Addressing the challenges of high labor intensity, high missed-cut rates, and low cutting success rates in fruit tree branch pruning, this study focuses on apple tree branches and proposes a multi-degree-of-freedom fruit tree pruning robotic arm along with a method for controlling its operational trajectory. Based on an investigation of dwarf self-rooted apple orchard planting patterns, an overall trajectory control strategy was formulated. Joint torque expressions were derived using Lagrange dynamics, and joint driving forces were determined via quintic interpolation. Environmental data were captured and reconstructed using a Kinect V2 depth camera. Trajectory planning and collision analysis were performed in simulation, leading to an improved Rapidly-exploring Random Tree (RRT) algorithm that reduces planning time. A prototype was built and tested for pruning trajectory planning and control. Results show that with a collision distance of 150 mm, the improved RRT algorithm achieved a 90% obstacle avoidance success rate and an average path execution time of 18.8 s. This study offers new insights for pruning device development and pro-vides academic reference for multi-degree-of-freedom robotic arm trajectory control.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"14 ","pages":"Article 102016"},"PeriodicalIF":5.7,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147546754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robotic Pruning System Integrating 3D Structural Information and Vision-Based End-Effector Positioning Correction","authors":"Tomoaki Hizatate ,&nbsp;Masaki Nishio ,&nbsp;Noboru Noguchi","doi":"10.1016/j.atech.2026.101966","DOIUrl":"10.1016/j.atech.2026.101966","url":null,"abstract":"<div><div>This study presents an autonomous robotic pruning system for grapevines that integrates vine-structure estimation, motion planning, and a vision-based end-effector position-correction mechanism. Field trials on 16 vines (10 single-pass; 6 two-stage) achieved pruning success rates of up to 82% and completed pruning of a single vine in 92 s under our test conditions. Enabling the position-correction module increased the per-task success rate from 68% to 82%; this difference was statistically significant in our single-pass analysis (Mann–Whitney U = 90.5, p = 0.040). The correction step itself succeeded in 90% of attempts and added 0.98 s (8.8%) to the cycle time. Bud-count control met or modestly exceeded the target in &gt;85% of successful cuts. Comparing operational strategies at the set level, the two-stage approach showed a higher task success rate and fewer collisions than single-pass pruning (Mann–Whitney tests), while other failure modes were broadly similar. These findings indicate promising but preliminary performance. The evaluation is limited in scale (n = 16 vines), conducted in a single season, and focuses on one platform and vineyard context; consequently, generalizability remains to be established. Future work will address retry mechanisms, depth-sensing stability, and throughput improvements via pruning-order optimization and dual-arm operation.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"14 ","pages":"Article 101966"},"PeriodicalIF":5.7,"publicationDate":"2026-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147546752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Short-term forecasting and predictive control of rooftop greenhouse microclimate using multi-horizon machine learning models","authors":"Joaquim Cebolla-Alemany ,&nbsp;Yunyao Cheng ,&nbsp;Laia Pintó-Espín ,&nbsp;Michele Albano ,&nbsp;Marcel Macarulla ,&nbsp;Santiago Gassó-Domingo","doi":"10.1016/j.atech.2025.101733","DOIUrl":"10.1016/j.atech.2025.101733","url":null,"abstract":"<div><div>This study presents a data-driven forecasting and control framework tailored to rooftop smart greenhouses integrated into buildings for urban agriculture—a context rarely addressed in existing literature. By combining internal environmental data, external meteorological inputs, and actuator operation states, the framework enables short-term temperature forecasting with high temporal resolution (5, 10, and 15-minute horizons). Advanced feature engineering techniques—including lag variables, rolling statistics, and derived indicators—were applied to capture complex greenhouse dynamics. Seven regression-based machine learning models (namely, Decision Tree, Random Forest, Gradient Boosting, XGBoost, LightGBM, Support Vector Regression, and Multi-layer Perceptron) were trained and systematically compared using cross-validation and SHAP-based interpretability. The best-performing model for each horizon was selected and integrated into a threshold-based and a fuzzy logic-based predictive control system. Results from real-world rooftop greenhouse data show robust forecasting performance (R² &gt; 0.98, MAE between 0.280 and 0.311, and RMSE between 0.638 and 0.728 for the best performing model across all horizons) and demonstrate that the fuzzy controller achieved over 60% energy savings compared to traditional threshold-based strategies, while maintaining climate stability. This work highlights the feasibility of deploying data-driven MPC strategies in building-integrated greenhouse environments and their compatibility with digital twin ecosystems. It also identifies key challenges for generalization, including dataset size, system configuration, and geographical variability.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101733"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hyperspectral inversion of leaf nitrogen content in wheat by integrating CWT-SPA feature optimization and XGBoost-SSA model","authors":"Chen Gu ,&nbsp;Huaiyang Liu ,&nbsp;Yunhao You ,&nbsp;Qianghao Zeng ,&nbsp;Zhenxiang Zhou ,&nbsp;Ming Song ,&nbsp;Yun Shi ,&nbsp;Tong Tian","doi":"10.1016/j.atech.2025.101765","DOIUrl":"10.1016/j.atech.2025.101765","url":null,"abstract":"<div><div>Leaf nitrogen content (LNC) is an essential physiological indicator for assessing the growth status of wheat. However, the accuracy and generalization of remote sensing-based monitoring models are often constrained by spatial and temporal variability. To overcome these limitations, this study proposes a cascaded optimization framework that integrates signal enhancement, feature selection, and intelligent optimization algorithms. First, the raw spectral data were preprocessed using Savitzky-Golay (SG) smoothing and a first-order derivative transformation, followed by a multi-scale continuous wavelet transform (CWT). Then, relevant spectral bands were identified through Pearson correlation analysis, and further dimensionality reduction was performed using the successive projections algorithm (SPA). Finally, two regression models were developed: an Extreme Gradient Boosting (XGBoost) model optimized with the Sparrow Search Algorithm (SSA) and an Extreme Learning Machine (ELM) optimized with the Artificial Hummingbird Algorithm (AHA). The XGBoost-SSA model demonstrated superior predictive performance on the test set, achieving a coefficient of determination (R²) of approximately 0.79, a root mean square error (RMSE) of approximately 0.14 mg/g, and a mean absolute percentage error (MAPE) of approximately 9.31%. On an independent external validation set, the XGBoost-SSA model also showed strong generalization capability, maintaining an R² of approximately 0.73, an RMSE of approximately 0.14 mg/g, and a MAPE of approximately 9.63%. These findings underscore the value of medium-scale CWT-SPA in spectral feature extraction and highlight the advantages of swarm intelligence algorithms in enhancing regression model performance. Overall, the proposed approach provides a reliable solution for high-precision nitrogen monitoring using hyperspectral remote sensing and supports data-driven applications in smart agriculture.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101765"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating wheat disease severity from high-resolution UAV multispectral imagery using deep learning","authors":"Maitiniyazi Maimaitijiang ,&nbsp;Dalitso Yabwalo ,&nbsp;Ubaid-ur-Rehman Janjua ,&nbsp;Mohammad Maruf Billah ,&nbsp;Bruce Millett ,&nbsp;Sunish K. Sehgal ,&nbsp;Shaukat Ali","doi":"10.1016/j.atech.2025.101729","DOIUrl":"10.1016/j.atech.2025.101729","url":null,"abstract":"<div><div>Bacterial Leaf Streak (BLS) and Fusarium Head Blight (FHB) are among the most damaging diseases of wheat (Triticum aestivum), with severe consequences for grain yield, quality, and ultimately food safety and security. Rapid and precise assessment of disease severity in the fields is crucial for effective field management, potential yield loss evaluation, and high-throughput phenotyping. This research examined the utility of UAV-based multispectral imagery in combination with both traditional machine learning and modern deep learning approaches to estimate wheat disease severity under field conditions. Data collection was carried out at two wheat experimental fields in South Dakota, USA, where Unmanned Aerial Vehicle (UAV) multispectral imagery was acquired in parallel with plot-level measurements of BLS and FHB severity. Spectral and textural metrics extracted from the UAV imagery served as inputs for machine/deep learning-based regression analyses. Regression models evaluated in this work comprised traditional machine learning methods Partial Least Squares Regression (PLSR), Random Forest Regression (RFR), and three deep learning architectures: Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and multi-head self-attention (MHSA)-enhanced CNN (Att-CNN). In addition, a deep transfer learning framework was tested by transferring an Att-CNN model trained on BLS to FHB severity estimation. The results showed that deep learning methods, particularly CNN-based architectures, consistently outperformed conventional machine learning approaches. Incorporation of a MHSA mechanism into the CNN architecture further enhanced performance, especially for BLS severity estimation. Att-CNN achieved the best results for both diseases, with R² = 0.83 and RRMSE = 30.55 % for BLS, and R² = 0.70 and RRMSE = 37.05 % for FHB. While estimation of FHB severity remained more challenging, transfer learning from BLS substantially improved prediction accuracy, raising R² from 0.70 to 0.79 and reducing RRMSE from 37.05 % to 31.31 %. The study highlights the considerable potential of UAV multispectral imagery, though with notable limitations, for monitoring crop diseases. This work also demonstrates the added value of attention-based deep learning and transfer learning techniques in addressing complex applications in agricultural remote sensing.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101729"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving growth period prediction of greenhouse cut chrysanthemum: Incorporating precise photo-thermal effect and multi-model ensemble approaches","authors":"Huahao Liu,&nbsp;Yin Wu,&nbsp;Jinshan Lu,&nbsp;Tingyu Gou,&nbsp;Shuang Zhao,&nbsp;Fadi Chen,&nbsp;Sumei Chen,&nbsp;Weimin Fang,&nbsp;Zhiyong Guan","doi":"10.1016/j.atech.2025.101685","DOIUrl":"10.1016/j.atech.2025.101685","url":null,"abstract":"<div><div>Accurate prediction of the cut chrysanthemum growth cycle is essential for precise market scheduling and quality control. While existing models primarily target the flowering date, key developmental stages remain poorly quantified. Through controlled experiments with varying planting dates and light levels, this study systematically analyzed the stage-specific influence of photosynthetic photon flux (PPF). We found that reduced PPF significantly delays both vegetative growth and harvest timing but does not affect floral bud differentiation. To address these stage-dependent responses, we developed a multi-model ensemble (MME) framework that integrates the most accurate models for each critical phase: the accumulated photo-thermal product for initiating short-day treatment, the triangular-function-based relative thermal effect for bud emergence, and the chrysanthemum clock model for the optimal harvest date. Validation results demonstrate that this integrated approach achieves significantly higher predictive accuracy than any single model. This research not only provides a reliable tool for the year-round precision production management of cut chrysanthemum but also offers a physiologically-based MME methodology reference for modeling the growth of horticultural crops.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101685"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Green instructions: Intelligent lighting via real-time chlorophyll fluorescence feedback: Enhancing yield and energy efficiency in controlled environment agriculture","authors":"Jim Stevens,&nbsp;Phillip Davey,&nbsp;Piotr Kasznicki,&nbsp;Tanja A Hofmann,&nbsp;Tracy Lawson","doi":"10.1016/j.atech.2025.101593","DOIUrl":"10.1016/j.atech.2025.101593","url":null,"abstract":"<div><div>Controlled Environment Agriculture (CEA) delivers increased crop production per unit land, contributing to resilient food systems amidst challenges of climate change, population growth and urbanization. However, high energy costs and the associated carbon footprint for using LED lighting imposes substantial barriers to the widespread adoption of CEA. While light is indispensable for growth, critically its utilization by crops throughout the photoperiod remains sub-optimal, reducing photosynthetic efficiency and wasting energy. Here we have developed and demonstrated a novel real-time plant bio-feedback system that enables crops to directly ‘communicate’ optimal lighting requirements. Continuous non-invasive monitoring of photochemistry elicited decreased demand for light by basil at the end of the photoperiod, which, delivered by our system, improved yield per unit power. Specifically, our innovative approach increased yield by 13.5 % and reduced energy consumption per unit fresh mass by 6.2 %, delivering a 17 % decrease in CO₂ required to generate fresh mass yield. Application of this technique at scale can significantly improve resource management of CEA, supporting the productivity, profitability and sustainability of this food industry.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101593"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital twins as decision-support tools for automation in agriculture: A case study on robotic vaccination","authors":"Emilio Hurtado,&nbsp;Chandra Suryadevara,&nbsp;Jayden Walker,&nbsp;Gerard Tayag,&nbsp;Hardeep Ryait","doi":"10.1016/j.atech.2025.101675","DOIUrl":"10.1016/j.atech.2025.101675","url":null,"abstract":"<div><div>Agriculture faces increasing pressure to improve efficiency, ensure animal welfare, and reduce dependence on manual labour, yet traditional operations often lag in adopting Industry 4.0 and 5.0 solutions. Digital technologies, particularly digital twins, offer a transformative approach by enabling virtual representation, real-time simulation, predictive analytics, and performance validation prior to physical deployment, thereby providing a cost-effective proof of concept. This paper introduces a framework that not only showcases a robotic vaccination system for feedlots but also establishes a proof-of-concept pathway to demonstrate the potential value and practicality of such technologies for agriculture. One of the latest state-of-the-art development environments, NVIDIA Isaac Sim, provides a robust platform for building these digital twins, allowing robotic systems to be tested and optimized in realistic, dynamic environments. Using this environment, we outline a robotic vaccination system that combines a robotic arm-based injection mechanism with reinforcement learning agents and a Detectron2 deep learning model these systems allow for precise neck muscle segmentation and accurate vaccine site targeting. The system was evaluated on two robotic platforms: Isaac Sim’s built-in Franka Emika Panda arm and a customized manipulator, which may offer realistic and cost-effective solutions for feedlots. Simulation results demonstrate achievable positional accuracy, robust control, and reliable task execution across both platforms. This digital twin-based framework reduces reliance on early-stage physical prototyping, enhances safety, measures operational efficiency, and serves as a decision-support tool, highlighting the critical role of digital simulation in enabling practical, scalable automation in modern agriculture.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101675"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145645986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Disturbance observer based adaptive sliding mode control for driving motor speed regulation in Maize Electric Fertilizer Applicator","authors":"Zhiqiang Li,&nbsp;Kun Luo,&nbsp;Liang Tao,&nbsp;Yan Zhou","doi":"10.1016/j.atech.2025.101721","DOIUrl":"10.1016/j.atech.2025.101721","url":null,"abstract":"<div><div>Electric fertilizer applicators significantly improve the uniformity, stability, and efficiency of summer maize fertilization. However, the complex soil environment in farmlands introduces uncertainties such as parameter variations, load disturbances, frictional resistance, and positioning errors, which degrade the control accuracy and robustness of the driving motor. To address these challenges, this study proposes a disturbance observer (DO)-based adaptive sliding mode control (ASMC) method. First, a control model for the soil-straw coupling system of the electric fertilizer applicator (EFA) was established, accounting for parameter variations and external load disturbances, thereby simplifying controller design. Second, a convergence rate mechanism was introduced to accelerate convergence time, ensuring the system reaches the sliding surface within a finite time, with the convergence rate being adjustable through parameter design. Additionally, a disturbance observer was designed to estimate both mismatched and matched disturbances, enabling feedforward compensation to improve tracking accuracy and reduce system chattering. Experimental results demonstrate that the proposed method achieves high control accuracy and robustness, ensuring rapid and stable state regulation for the EFA. This work provides new ideas for the design of smart agricultural machinery controllers and effectively promotes the control upgrade of agricultural electromechanical systems.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101721"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A two-stage method for wheat stripe rust grading based on YOLOv11-leaf and convnextv2-rust","authors":"Dejia Zhang ,&nbsp;Nurdila Xiayidan ,&nbsp;Xudong Yang ,&nbsp;Caihong Chen ,&nbsp;Yanting He ,&nbsp;Xinli Zhou","doi":"10.1016/j.atech.2025.101646","DOIUrl":"10.1016/j.atech.2025.101646","url":null,"abstract":"<div><div>Wheat stripe rust is a major fungal disease severely impacting global wheat production. However, in complex field environments, the disease’s early lesions are small and its severity grading is highly subjective, leading to low accuracy and deployment challenges in automated recognition. To address this challenge, this study aims to develop an efficient and precise automated recognition framework for wheat stripe rust. We propose a two-stage recognition framework integrating lightweight detection with fine-grained classification. First, based on a constructed field image dataset covering the international standard 0–9 disease severity scale, we designed a lightweight object detection model, YOLOv11-leaf, to precisely localize and extract leaf regions from complex backgrounds. Subsequently, for the fine-grained task of disease severity grading, we modified the ConvNeXtV2 network to propose the ConvNeXtV2-rust classification model, enabling automatic determination of disease severity levels on extracted leaves. Experimental results demonstrate that YOLOv11-leaf achieves 96.71 % accuracy in detection tasks, representing a 7.06 % improvement over YOLOv11n. For classification tasks, ConvNeXtV2-rust achieves 75.94 % accuracy, surpassing the original ConvNeXtV2 by 1.75 %. This study provides a high-precision, easily deployable practical solution for crop disease-resistant breeding screening and intelligent field forecasting systems. It advances the precise prevention and control of crop pests and diseases while accelerating the development of precision agriculture.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"13 ","pages":"Article 101646"},"PeriodicalIF":5.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}