Computers and Electronics in Agriculture最新文献

{"title":"Finite element modeling of the biomechanical properties of Populus tomentosa branches and analysis of pruning mechanisms","authors":"Yichen Ban ,&nbsp;Yang Liu ,&nbsp;Shihong Ba ,&nbsp;Kun Lyu ,&nbsp;Jian Wen ,&nbsp;Xiaopeng Bai ,&nbsp;Wenbin Li","doi":"10.1016/j.compag.2025.110502","DOIUrl":"10.1016/j.compag.2025.110502","url":null,"abstract":"<div><div>The finite element method can effectively simulate the pruning process to investigate the pruning mechanism. To ensure the reliability of the simulation results, it is essential to measure and calibrate the model parameters. In this study, a finite element model was established to simulate the pruning process executed by pruning robots. The biomechanical properties of <em>Populus tomentosa</em> branches were determined using mechanical tests. The finite element model parameters were calibrated using the Plackett-Burman and Box-Behnken methods, and the reliability of these calibrated parameters was subsequently validated through field testing in a forest environment. Finally, the calibrated finite element model was used to investigate the impact-cutting pruning mechanism of <em>Populus tomentosa</em> branches to further solve the problems of poor pruning quality and serious blade wear caused by unreasonable working parameters of the blade in the pruning process. The results indicate that the calibrated finite element model of the biomechanical properties of <em>Populus tomentosa</em> branches accurately simulates the pruning process. Moreover, the simulation results show that reducing the cutting speed and increasing the blade wedge angle led to a decrease in the peak stress and thus blade wear while increasing the cutting speed and reducing the blade wedge angle led to an improvement in the pruning quality. At cutting speeds of more than 6 m∙s⁻¹ and with a blade wedge angle of less than 35°, branches with a diameter of 25 mm were cut with a cutting share of nearly 100 %. This study provides a robust model for the simulation and optimization of impact-cutting pruning by robots, which is of considerable significance for the development of high-quality products in the enhancement of forestry pruning practices.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110502"},"PeriodicalIF":7.7,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simulation analysis of mechanical response and failure mechanisms of maize stubble-soil composite based on discrete element method and fiber bundle model","authors":"Chunxiang Zhuo ,&nbsp;Haiqing Tian ,&nbsp;Ziqing Xiao ,&nbsp;Qiaofei Mu ,&nbsp;Leifeng Tang ,&nbsp;Kai Zhao","doi":"10.1016/j.compag.2025.110452","DOIUrl":"10.1016/j.compag.2025.110452","url":null,"abstract":"<div><div>The interaction between agricultural machinery, root systems, and soil is crucial for root-soil mechanics and farmland conservation. However, existing studies have rarely explored the fine-scale simulation of crop root failure processes. Analyzing complex root fracture processes and failure mechanisms using discrete element method (DEM) still has certain limitations. This study develops a discrete element model of the crop stubble-soil composite (SSC) based on soil characteristics in arid and cold regions and maize root distribution. Additionally, the fiber bundle model (FBM) is applied to explain the root system’s progressive failure mode and stress distribution. The results show that the SSC model accurately represents the root-soil mechanical response and failure characteristics under external loading. The failure probability of root segments and cumulative failure probability follow Gaussian probability density function and cumulative distribution function, respectively, consistent with the statistical characteristics of fiber failure described by the FBM. Root particle bond rupture shows staged failure behavior, with the basal anchorage zone being most prone to concentrated fracture failure. The root functional zone exhibits a progressive failure process, while the bottom elongation zone demonstrates better stress dispersion and slippage failure. Under external loading, soil particle stress feedback generally lags behind root failure. This study provides a refined modeling method for root-soil mechanical behavior during agricultural equipment operations, and introduces a computational method based on FBM theory to elucidate the mechanisms of root failure during the composite disturbance process, with potential applications in tillage protection and root-soil stability studies.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110452"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent decision support for drought stress (IDSDS): An integrated remote sensing and artificial intelligence-based pipeline for quantifying drought stress in plants","authors":"Arpan Kumar Maji ,&nbsp;Sumanta Das ,&nbsp;Sudeep Marwaha ,&nbsp;Sudhir Kumar ,&nbsp;Suman Dutta ,&nbsp;Malini Roy Choudhury ,&nbsp;Alka Arora ,&nbsp;Mrinmoy Ray ,&nbsp;Anbukkani Perumal ,&nbsp;Viswanathan Chinusamy","doi":"10.1016/j.compag.2025.110477","DOIUrl":"10.1016/j.compag.2025.110477","url":null,"abstract":"<div><div>Drought is a major abiotic stress that adversely affects plant growth, physiology, and crop yield. Conventional methods for assessing drought stress tend to be fragmented, targeting either leaves, canopies, or roots, and are often expensive, low-throughput, and lack the ability to provide real-time, whole-plant insights. Addressing these limitations, this study presents a novel, integrated pipeline titled <em>Intelligent Decision Support for Drought Stress (IDSDS)</em> that leverages remote sensing and artificial intelligence (AI) for accurate, real-time monitoring of drought stress across entire plants. The IDSDS pipeline employs low-cost RGB images collected at various growth stages and uses a deep learning-based model to reconstruct hyperspectral data, which is typically costly and complex to obtain. This reconstructed data enables the extraction of key physiological traits, including greenness, saturation, and pigment content. A novel phenotyping metric—<em>Greenness Coefficient (GC)</em>, was also proposed, offering precise spatial analysis of drought impact within the plant. The hyperspectral reconstruction model was validated using standard performance metrics such as the correlation coefficient, mean squared error, standard deviation of squared error, and spectral angle mapper (SAM). IDSDS further calculates a comprehensive set of spectral indices (e.g., greenness, leaf pigment, water content) that are closely linked to drought-induced changes. Finally, by integrating these indices with machine learning-based classification models, IDSDS accurately stratifies plant drought stress into seven distinct categories. The results showed that the proposed hyperspectral reconstruction model effectively converts RGB plant images into accurate hyperspectral data, achieving a SAM value between 0.14 and 0.30. This indicates strong spectral similarity, meaning the reconstructed pixel spectra closely align with the reference spectra. The GC, along with other reconstructed spectral indices, supports visual interpretation and enhances the traceability of the system’s outputs, thereby increasing transparency. Additionally, the findings demonstrate statistically significant results (p &lt; 0.001) for these indices in detecting plant drought stress, with a high classification accuracy of 99 % and an average area under the curve (AUC) of 1.00, reflecting precise differentiation of stress across the entire plant. Overall, the study introduces a breakthrough in drought stress monitoring, combining high-throughput and cost-effective RGB imaging with AI to support both scientific research and practical crop management. The IDSDS pipeline lays the groundwork for informed, drought-adaptive decision-making of agricultural crops.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110477"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and evaluation of a novel sensor for noninvasively investigating corn ear dehydration","authors":"Yang Xiang ,&nbsp;Liu-Deng Zhang ,&nbsp;Hai-Ying Zheng ,&nbsp;Ao-Wen Wang ,&nbsp;Ke-Lei Xia ,&nbsp;Zhong-Yi Wang ,&nbsp;Lan Huang ,&nbsp;Li-Feng Fan","doi":"10.1016/j.compag.2025.110437","DOIUrl":"10.1016/j.compag.2025.110437","url":null,"abstract":"<div><div>Noninvasive investigation of corn ear dehydration is of great significance for breeding corn varieties, mechanized harvesting, and post-harvest storage, especially before physiological maturation. However, it remains a challenge to noninvasively monitor the moisture content of corn kernel layers with husk cover in situ during the R5-R6 maturation period. In this study a method that eliminates the impact of the corn husk by using the difference in the fringe field area of two measuring electrodes is proposed. In addition, a lumped LC circuit model of a quarter-wavelength transmission line was established to minimize the sensor probe. A continuous moisture monitoring sensor system for in situ corn ear kernels was then developed and calibrated to investigate corn ear dehydration in a greenhouse over a 30-d period. The results showed that within the range of 19–55% moisture content in the corn ear kernel layer, the linear fitting R² of the two sensors were 0.8046 and 0.8257, respectively, and the moisture measurement errors were 8.6% and 8.2% at the 95% confidence level. Diurnal physiological variations in corn ear moisture content have been observed in situ, and corn ear moisture content has been continuously monitored to investigate corn ear dehydration before physiological maturation. In summary, this study provided a new method for investigating corn ear dehydration for corn breeding.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110437"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced canopy size estimation in strawberry production: a machine learning approach using YOLOv11 and SAM","authors":"Zijing Huang ,&nbsp;Won Suk Lee ,&nbsp;Peng Yang ,&nbsp;Yiannis Ampatzidis ,&nbsp;Agehara Shinsuke ,&nbsp;Natalia A. Peres","doi":"10.1016/j.compag.2025.110501","DOIUrl":"10.1016/j.compag.2025.110501","url":null,"abstract":"<div><div>This study presents a novel approach for estimating strawberry canopy size by integrating the Segment Anything Model (SAM) with YOLOv11 detection, enhancing accuracy and efficiency in precision agriculture. Traditional methods of canopy size estimation are labor-intensive and frequently inaccurate, posing considerable limitations in agricultural applications. To overcome these issues, our research introduces an innovative integration of SAM’s zero-shot segmentation capabilities with YOLOv11′s advanced detection accuracy, underpinned by a novel prompt selection algorithm. This algorithm automates prompt optimization by using precise detection outputs from YOLOv11 to guide SAM, eliminating the need for extensively annotated datasets required by conventional and supervised segmentation methods. The prompt selection algorithm is proposed in two innovative variants: vanilla and refined. The vanilla approach employs bounding box detections from YOLOv11 plant detection alongside strategically chosen point prompts from fruit detection outputs to enhance segmentation specificity. The refined approach further advances this concept by introducing a hollow concentric structure algorithm to selectively choose background points from regions overlapping fruit detections and preliminary SAM masks. This refinement reduces segmentation errors by identifying non-canopy points, thus improving segmentation reliability. Experimental validation demonstrated that the vanilla approach achieved an Intersection over Union (IoU) of 0.913, while the refined approach reached an even higher IoU of 0.924. Additionally, we integrated Depth Anything v2 (DAv2) to transition from 2D segmentation to robust 3D canopy volume estimation. This comprehensive framework not only improves upon existing segmentation methods but also provides a practical, scalable solution for precision agriculture, showcasing significant advancements in automated canopy analysis.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110501"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and experiment of a simulated electronic corn ear based on multi-sensor information fusion","authors":"Shulun Xing ,&nbsp;Tao Cui ,&nbsp;Dongxing Zhang ,&nbsp;Li Yang ,&nbsp;Xiantao He ,&nbsp;Chuan Li ,&nbsp;Jiaqi Dong ,&nbsp;Yeyuan Jiang ,&nbsp;Wei Wu ,&nbsp;Chuankuo Zhang","doi":"10.1016/j.compag.2025.110482","DOIUrl":"10.1016/j.compag.2025.110482","url":null,"abstract":"<div><div>To explore the mechanism of grain breakage during the threshing of high-moisture corn ears, this paper designed a simulated electronic corn ear (SECE), which could be threshed. It was embedded with a ultra-wideband (UWB) module, a inertial measurement unit (IMU) module, and a flexible film pressure sensor. The UWB/IMU coupled positioning algorithm, UWB ranging outlier removal algorithm and impact force detection algorithm were proposed to detect the kinematic and dynamic parameters of SECE during threshing. To verify the working performance of SECE, we conducted tests on dynamic impact force detection, static force detection, spatial positioning, and corn threshing. The dynamic impact force detection test results indicated an average detection error of 0.91 N, a maximum error of 2.25 N, and an average detection accuracy of 98.15 %. The static force detection test results showed an average detection error of 2.47 N, a maximum average detection error of 7.25 N, and an average <em>R</em>² of 0.9874. The spatial positioning test results indicated that the UWB ranging outlier removal algorithm could effectively reduce the impact of non-line-of-sight (NLOS) on the positioning accuracy of SECE, and the UWB-IMU coupled positioning algorithm could further improve the positioning accuracy. The unscented kalman filter (UKF) tightly coupled algorithm had the highest positioning accuracy, followed by the extended kalman filter (EKF) tightly coupled algorithm, and the kalman filter (KF) loosely coupled algorithm. Using the UKF algorithm, the root mean square error (RMSE) of the <em>X</em> ,<em>Y</em>, and <em>Z</em> axes position of SECE could all be within 0.12 m, with a probability of exceeding 85 % for errors less than 0.15 m. The corn threshing test results showed that the SECE could effectively detect the motion trajectory, dynamic impact force and static force within the threshing device. This research provided a new technical means for analyzing the kinematic and dynamic parameters of corn ears under threshing conditions and offered a new method for studying the principles of grain breakage.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110482"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An electric-driven maize seeding system: improving the quality of accelerate seeding using Tracking Differential Filtering-Optimal Tracking Control (TDF-OTC) method","authors":"Chengkun Zhai ,&nbsp;Caiyun Lu ,&nbsp;Hongwen Li ,&nbsp;Jin He ,&nbsp;Qingjie Wang ,&nbsp;Chao Wang ,&nbsp;Wenlong Jin ,&nbsp;Liyu Chen ,&nbsp;Fangle Chang ,&nbsp;Jinshuo Bi","doi":"10.1016/j.compag.2025.110488","DOIUrl":"10.1016/j.compag.2025.110488","url":null,"abstract":"<div><div>In light of the growing conflicts between human activities and land use, enhancing the precision of seeding control throughout the entire maize seeding process is crucial for ensuring seeding quality and increasing yield per unit area. However, current research on maize seeding control methods has predominantly focused on the uniform speed seeding stage. Little attention has been paid to the acceleration stage, where speed variations are more complex and impose higher requirements for speed measurement and real-time control. To address this issue, this paper develops a maize seeding control system based on the Tracking Differentiator Filter-Optimal Tracking Control (TDF-OTC) method, aiming to improve the seeding quality during the acceleration stage from both input and output perspectives of the control system. An electric-driven seeding system was built on a pneumatic precision high-speed maize planter to provide the hardware platform for implementing the TDF-OTC method. A nonlinear tracking differentiator (NLTD) based on TDF was designed to address the filtering problem of oscillatory speed measurement signals, leveraging its ability to balance tracking speed and noise reduction. This ensures accurate forward speed input for the control system. Additionally, a linear quadratic tracker (LQT) based on OTC was designed to minimize error performance metrics and compel the system’s actual output to track the target output trajectory. This resolved the rapid tracking of the drastically changing target rotational speed of seed metering drive motor, ensuring accurate motor speed output for the control system. Considering the real-world conditions of accelerated seeding operations, the parameters of NLTD and LQT were determined using MATLAB Simulink to ensure optimal performance. A series of tests was conducted to evaluate the performance of the proposed method. The TDF test results demonstrated that the NLTD effectively filtered and reduced noise from oscillatory speed input signals. The accelerated response test results of OTC showed that the designed LQT outperformed PID controllers in acceleration tracking capability. Accelerated seeding test in the field, where the planter accelerated from a standstill to approximately 3.5–4.0 m/s, revealed that the TDF-OTC method achieved an average seeding qualification rate (<em>ASQR</em>) of 90.63% and an average coefficient of variation of seeding spacing (<em>ACVSP</em>) of 21.66%. Compared to the PID method, these results represented a year-on-year improvement of 12.28% in <em>ASQR</em> and a reduction of 14.99% in <em>ACVSP</em>, affirming the effectiveness of the proposed method in improving seeding quality during the acceleration stage. This study provides a valuable reference for advancements in precision seeding.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110488"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-performance prediction of soil organic carbon using automatic hyperparameter optimization method in the yellow river delta of China","authors":"Yingqiang Song ,&nbsp;Feng Wang ,&nbsp;Weihao Yang ,&nbsp;Ruilin Liang ,&nbsp;Dexi Zhan ,&nbsp;Meiyan Xiang ,&nbsp;Xiaohang Yang ,&nbsp;Rui Xu ,&nbsp;Miao Lu","doi":"10.1016/j.compag.2025.110490","DOIUrl":"10.1016/j.compag.2025.110490","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Using machine learning (ML) and deep learning (DL) models to predict the spatial variability of soil organic carbon (SOC) is crucial for advancing carbon emission reduction strategies. However, inadequate hyperparameter tuning remains a key limitation, reducing the model fitting performance and prediction accuracy. Notably, high-performance models enabled by automatic hyperparameter optimization (AHPO) represent a novel approach to explain the complex relationships between environmental factors and SOC. In this study, we analyzed the prediction performance of ML models, such as gradient boosting decision tree (GBDT) and extreme gradient boosting (XGB), and DL models, including deep forest (DF) and convolutional neural network (CNN). These models were optimized using nature-inspired algorithms (grey wolf optimization (GWO) and hunter-prey optimization (HPO)) and mathematical-approximation algorithms (Bayesian optimization (BO) and tree-structured Parzen estimator (TPE). Furthermore, we derived the linear and nonlinear driving effects of environmental factors (soil, vegetation, texture, climate, and terrain) on SOC. We also identified direct and indirect response pathways using SHapley additive interpretation (SHAP), variogram decomposition (VD), hierarchical partitioning (HP), and structural equation model (SEM). Our results show that prediction models optimized with mathematical approximation algorithms, such as BO-DF (R&lt;sup&gt;2&lt;/sup&gt; = 0.76) and TPE-DF (R&lt;sup&gt;2&lt;/sup&gt; = 0.82), demonstrated the strongest nonlinear fitting ability between environmental factors and SOC. AHPO algorithms significantly improved the prediction performance of DL models, with R&lt;sup&gt;2&lt;/sup&gt; values for the four optimization methods increasing from 0.72 to 0.82. The generalization verification results indicate that the TPE-optimized model demonstrates strong robustness and achieves the highest accuracy (R&lt;sup&gt;2&lt;/sup&gt; &gt; 0.7) for SOC prediction. The AHPO prediction model’s hyperparameter combination achieves a balance between similarity and distinctiveness, where key performance-determining hyperparameters exhibit significant variation (i.e. non-similarity), enabling high-performance SOC predictions. The spatial mapping using the TPE-DF model revealed that areas with high SOC content are primarily concentrated in the southern and northeastern regions of the study area. Moreover, when the model’s prediction accuracy (R&lt;sup&gt;2&lt;/sup&gt;) exceeds 0.75, SHAP analysis identifies SoilAN, SoilAP, SoilAK, TMP, and PRE as the most influential environmental factors driving nonlinear changes in SOC. Similarly, VD and HP analyses highlight a synergistic linear contribution of soil and climate factors, accounting for 99.1 % of the variability in SOC. Interestingly, the path analysis further indicates that regional climate warming leads to surface soil desiccation and salinization, which significantly alters the SOC decomposition environment. High salt stress negatively affects microo","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110490"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital twin-driven system for efficient tomato harvesting in greenhouses","authors":"Yining Lang ,&nbsp;Yanqi Zhang ,&nbsp;Tan Sun ,&nbsp;Xiujuan Chai ,&nbsp;Ning Zhang","doi":"10.1016/j.compag.2025.110451","DOIUrl":"10.1016/j.compag.2025.110451","url":null,"abstract":"<div><div>Efficient and low-damage harvesting remains a major challenge in modern greenhouse tomato production, particularly in dense planting environments. To address limitations such as restricted camera views, occluded fruits, and complex fruiting patterns, our study presents a digital twin-driven system for intelligent tomato harvesting. Using a slidable depth camera mounted on the robot, we reconstruct a high-fidelity 3D digital twin of the greenhouse that accurately captures the spatial distribution and growth states of tomatoes. Based on this virtual environment, a learning-based framework is developed to optimize harvesting strategies, including robot positioning, arm trajectory planning, fruit selection priority, and adaptive operation modes. The proposed system integrates both a complete algorithmic workflow and a practical hardware platform. Experimental results show that our method significantly improves harvesting performance, reducing the average harvesting time by 34.95% (to 7.4 s per fruit), arm movement distance by 20.93%, and collision occurrences by 45.16%. While tailored for tomato harvesting, this framework demonstrates strong potential for generalization to other greenhouse crops in precision agriculture.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110451"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Organ segmentation and phenotypic information extraction of cotton point clouds based on the CotSegNet network and machine learning","authors":"Jiangzheng Song ,&nbsp;Benxue Ma ,&nbsp;Ying Xu ,&nbsp;Guowei Yu ,&nbsp;Yongchuang Xiong","doi":"10.1016/j.compag.2025.110466","DOIUrl":"10.1016/j.compag.2025.110466","url":null,"abstract":"<div><div>The precise segmentation of crop organs plays a crucial role in optimizing crop cultivation strategies and enhancing yield potential. This study proposes a novel deep learning network, CotSegNet, which enables precise and non-destructive segmentation of cotton organs facilitating the extraction of phenotypic characteristics. In CotSegNet, an improved attention mechanism known as CGLUConvFormer is designed. This mechanism significantly improves segmentation accuracy by emphasizing important features while diminishing redundant information. Furthermore, CotSegNet integrates the SegNext attention mechanism. This mechanism facilitates the efficient extraction and integration of multi-scale features, thereby significantly enhancing the ability of CotSegNet to comprehend and segment point cloud data. To address issues related to leaf adhesion and coplanarity that lead to over-segmentation problems, this study proposes an improved region-growing algorithm. This algorithm enhances the accuracy of leaf instance segmentation through the incorporation of distance constraints. In comparative experiments with five advanced deep learning networks (PointNet, PointNet++, DGCNN, SPoTr and CurveNet), CotSegNet demonstrated outstanding performance. Its Precision, Recall, F1-score, and IoU reached 95.06 %, 93.32 %, 94.61 %, and 89.80 %, respectively. The experimental results demonstrated that the proposed method effectively extracted the phenotypic parameters of stem height, leaf length, leaf width, and leaf area in cotton plants. These measurements exhibited a high degree of consistency with manual assessments, yielding determination coefficients of 0.947, 0.948, 0.955, and 0.961 for each parameter respectively. The corresponding root mean square errors were recorded as 0.852 cm, 0.492 cm, 0.551 cm, and 1.674 cm² respectively. The research findings demonstrate that this approach offers essential technical support for the collection and analysis of high throughput phenotyping data in field crops.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"236 ","pages":"Article 110466"},"PeriodicalIF":7.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}