Computers and Electronics in Agriculture最新文献

{"title":"The effect of soil water content and crop canopy on passive UHF-RFID wireless links","authors":"Carol L. Baumbauer ,&nbsp;David A. Baumbauer ,&nbsp;Ana C. Arias","doi":"10.1016/j.compag.2025.110506","DOIUrl":"10.1016/j.compag.2025.110506","url":null,"abstract":"<div><div>High spatial density agricultural sensors that monitor soil fertility and moisture levels are quickly developing and could revolutionize precision agriculture once they are integrated with wireless communication systems. Passive Ultra High Frequency Radio Frequency Identification (UHF-RFID) is a wireless communication protocol for battery-free sensor nodes which could enable continuous soil monitoring. Soil texture, soil water content, and crop canopy impact the vertical read range between a passive RFID tag near the soil and a reader raised above the crop. Here, we evaluated these impacts and found that increases in soil water content decreased read range by 30–40 cm compared to dry soil. Adding 3.4 cm of distance between the wet soil and the tag increased the read range by 1–1.4 m. Crop canopy did not have a significant impact on read range once the soil water content had been accounted for.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110506"},"PeriodicalIF":7.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072430","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":"FiVOS: A fish segmentation algorithm based on interactive video object segmentation and filter enhancement","authors":"Yuqing Duan,&nbsp;Song Zhang,&nbsp;Shili Zhao,&nbsp;Xiaoyi Gu,&nbsp;Yan Meng,&nbsp;Daoliang Li,&nbsp;Ran Zhao","doi":"10.1016/j.compag.2025.110438","DOIUrl":"10.1016/j.compag.2025.110438","url":null,"abstract":"<div><div>With the continuous expansion of aquaculture, precise and efficient monitoring of fish behavior has become increasingly critical for improving farming efficiency and reducing economic losses. In particular, with the ongoing enhancement of computational capabilities in deep learning models, vision-based fish segmentation methods are garnering growing attention. By analyzing video segmentation results, fish behavior can be effectively tracked, thereby providing reliable data support for the precise regulation of aquaculture environments. However, existing deep learning-based video segmentation methods for aquaculture scenarios often overlook the dynamic correlations between video frames. In contrast, Interactive Video Object Segmentation (IVOS) employs an interaction-propagation scheme to achieve high-precision segmentation while minimizing user effort, thereby enhancing monitoring efficiency. Yet, IVOS applications in aquaculture remain limited due to data scarcity, and are susceptible to error accumulation and mask loss over long sequence propagation due to high intra-class similarity. In response, this paper proposes an improved interactive video object segmentation method (FiVOS) and constructs two fish-specific datasets. FiVOS utilizes a mask block filter to enable early detection and correction of erroneous propagated mask blocks, enhancing filtering accuracy through a rule-based thresholding approach. Additionally, it serializes noise filters to further eliminate erroneous mask noise, thereby improving model robustness. Experimental results demonstrate that FiVOS achieves state-of-the-art (SOTA) performance in fish video segmentation tasks, providing robust technical support for fish behavior research.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110438"},"PeriodicalIF":7.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072429","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":"Header parameters optimization for quinoa mechanical harvesting using neural network and approximation modeling","authors":"Leilei Chang ,&nbsp;Ruijie Shi ,&nbsp;Fei Dai ,&nbsp;Wuyun Zhao ,&nbsp;Hucun Wang ,&nbsp;Yiming Zhao","doi":"10.1016/j.compag.2025.110472","DOIUrl":"10.1016/j.compag.2025.110472","url":null,"abstract":"<div><div>Quinoa has received widespread global attention due to its high nutritional value. As one of the primary cultivation regions, China has experienced continuous growth in both planting area and yield; however, the advancement of mechanized harvesting equipment remains insufficient. To improve the level of mechanized quinoa harvesting and to address common issues such as stem breakage, lodging, feeding inefficiencies, and significant grain loss during harvest, this study integrates the Discrete Element Method (DEM), neural network techniques, and approximation modeling to propose a multi-objective optimization approach tailored for agricultural machinery experiment design. The feasibility of the proposed method was validated through field trials. Forward speed, raking teeth speed, and divider width were selected as experimental factors, while the average stem movement speed and maximum stem force served as evaluation indicators for the multi-parameter optimization of the quinoa header. Among the three neural network models evaluated (GA-BP, DBO-BP, and NGO-BP), the NGO-BP model demonstrated superior prediction accuracy, stability, and optimization efficiency when addressing complex nonlinear parameter interactions. Field validation results showed that when the forward speed was 1.26 m/s, the raking teeth speed was 1.47 m/s, and the divider width was 235.8 mm, the grain shedding rate was reduced to only 1.802 %, which significantly outperformed conventional harvesting equipment. This study not only substantially improves the efficiency of mechanized quinoa harvesting but also offers innovative insights for the design and optimization of harvesting machinery for other crops.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110472"},"PeriodicalIF":7.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070360","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":"ET-PatchNet: A low-memory, efficient model for Multi-view Stereo with a case study on the 3D reconstruction of fruit tree branches","authors":"Hao Wan ,&nbsp;Xilei Zeng,&nbsp;Zeming Fan,&nbsp;Qinhu Chen,&nbsp;Ke Zhang,&nbsp;Han Zhang","doi":"10.1016/j.compag.2025.110459","DOIUrl":"10.1016/j.compag.2025.110459","url":null,"abstract":"<div><div>The achievement of robotic fruit harvesting in intelligent farming depends heavily on the precise reconstruction of tree branch structures that direct harvesting arm movements. However, existing research in this field often grapples with computational inefficiencies and high costs. In response, we designed <strong>ET-PatchNet</strong>, a low-memory neural network for generating depth maps within the Multi-view Stereo (MVS) process, enabling efficient 3D reconstruction of branches. This highly <strong>Efficient network</strong> is based on <strong>Transformer</strong> and <strong>Patchmatchnet</strong>. ET-PatchNet incorporates an efficient backbone that includes self-attention and cross-attention mechanisms based on Transformer, which enriches global and 3D consistency information and enhances depth prediction accuracy and generalization performance. Furthermore, an adaptive depth resampling method has been developed, which is embedded in a iterative, coarse-to-fine, depth regression architecture based on learnable patches to minimize memory usage. To further amplify the representation capacity of depth characteristics, an auxiliary task has been integrated. Experimental results show that ET-PatchNet outperforms its competitors in completeness, computational efficiency, and low memory usage in evaluating the DTU and Tanks&amp;Temples datasets. When predicting a single depth map at a resolution of 1152 × 864 pixels, it only took 0.13 <span><math><mi>s</mi></math></span> to inference, with a memory usage of just <span><math><mrow><mn>2824</mn><mspace></mspace><mi>MB</mi></mrow></math></span>. Moreover, the 3D structure of observable branches on apple trees has been effectively reconstructed by fine-tuning our model on the BlendedMVS dataset. The mean and variance of distances between our reconstructed branch points and reference points are only <span><math><mrow><mn>0</mn><mo>.</mo><mn>0292</mn><mspace></mspace><mi>mm</mi></mrow></math></span> and <span><math><mrow><mn>0</mn><mo>.</mo><mn>0187</mn><mspace></mspace><msup><mrow><mi>mm</mi></mrow><mrow><mn>2</mn></mrow></msup></mrow></math></span>. In conclusion, ET-PatchNet is ideal for integration into mobile embedded fruit harvesting equipment and exhibits significant potential for a wide range of applications.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110459"},"PeriodicalIF":7.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072431","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":"ITreeForeCast: An integrated modeling software to simulate tree level growth and forest carbon storage","authors":"Ange-Lionel Toba,&nbsp;Rajiv Paudel,&nbsp;Cleve Davis,&nbsp;Damon S. Hartley,&nbsp;Rohit Venkat Gandhi Mendadhala","doi":"10.1016/j.compag.2025.110495","DOIUrl":"10.1016/j.compag.2025.110495","url":null,"abstract":"<div><div>Healthy trees in forest act as a natural carbon sink, capturing carbon. As they grow, they store carbon in their trunks, leaves and roots. Not all trees store carbon at the same rate, or in the same quantities, as it depends on a variety of biophysical and climatic factors. Although carbon estimation in trees can be complex, the precision of estimates is tightly linked to trees growth, both in diameter and height. However, the simulation of carbon uptake by forest and forest growth has each been modeled separately, and independently at differing levels of detail and spatial resolution. In this paper, we introduce ITreeForeCast, a simulation model combining the two types of modeling on a unified platform, enabling the investigation of impacts of management strategies on carbon sequestration and wood products. ITreeForeCast is a user-extendable framework that offers new opportunities to model, simulate, and visualize the dynamics of individual trees in a forest, simulate management strategies over time, and carbon uptake.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110495"},"PeriodicalIF":7.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069961","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":"Performance evaluation of Sentinel-2 imagery, agronomic and climatic data for sugarcane yield estimation","authors":"Rafaella Pironato Amaro ,&nbsp;Pierre Todoroff ,&nbsp;Mathias Christina ,&nbsp;Daniel Garbellini Duft ,&nbsp;Ana Cláudia dos Santos Luciano","doi":"10.1016/j.compag.2025.110522","DOIUrl":"10.1016/j.compag.2025.110522","url":null,"abstract":"<div><div>Given the importance of the sugarcane sector, machine learning techniques are being used as an important tool to improve yield estimation. This study aims to select the most relevant predictors from Sentinel-2 imagery, agronomic, and climatic data, using the Random Forest algorithm (RF), to estimate sugarcane yield before the harvest in a mill in the west of São Paulo state. We used radiometric bands (<span><math><msub><mtext>Red-edge</mtext><mn>1</mn></msub></math></span> to <span><math><msub><mtext>Red-edge</mtext><mn>3</mn></msub></math></span>, Red, NIR, <span><math><msub><mtext>SWIR</mtext><mn>1</mn></msub></math></span>, and <span><math><msub><mtext>SWIR</mtext><mn>2</mn></msub></math></span>) and vegetation indices from Sentinel-2 multispectral reflectance data (<span><math><msub><mtext>NDVIRE</mtext><mn>1</mn></msub></math></span> to <span><math><msub><mtext>NDVIRE</mtext><mn>3</mn></msub></math></span>, EVI, <span><math><msub><mtext>CIRE</mtext><mn>1</mn></msub></math></span> to <span><math><msub><mtext>CIRE</mtext><mn>3</mn></msub></math></span>, NDVI, <span><math><msub><mrow><mtext>ND</mtext><mtext>WI</mtext></mrow><mn>1</mn></msub></math></span>, <span><math><msub><mrow><mtext>ND</mtext><mtext>WI</mtext></mrow><mn>2</mn></msub></math></span>, SIWSI, NDMI, SAVI); agronomic data (soil type, number of harvests, variety, slope); climatic and agroclimatic data (temperature, precipitation, radiation, and crop water balance). We built four datasets to create yield estimation models for the mill: (i) the first dataset included all variables; (ii) in the second dataset, the strongly correlated variables from the dataset (i) were removed; (iii) the third dataset included the variables identified by feature selection within the 2nd dataset using RF algorithm’s impurity index (best model results); (iv) the fourth dataset, consisting of the 20 highest ranked variables from dataset 1 selected by SHapley Additive exPlanations (SHAP). The models showed R² values ranging from 0.58 to 0.70 with dataset 3, and the d-Willmott index ranged from 0.83 to 0.89. The most relevant variables for estimating sugarcane yield were the number of harvests, climatic data and vegetation indices that used Red-edge, near-infrared narrow, red and SWIR bands.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110522"},"PeriodicalIF":7.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069964","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":"Structural design and optimization of crushing and strip-laying device based on discrete element method with wet-adhesive flexible straw model","authors":"Fubin Zhang,&nbsp;Zhitao Luo,&nbsp;Weixun Li,&nbsp;Enlai Zheng,&nbsp;Dongchuan Pan,&nbsp;Jin Qian,&nbsp;Haoping Yao,&nbsp;Xiaochan Wang","doi":"10.1016/j.compag.2025.110537","DOIUrl":"10.1016/j.compag.2025.110537","url":null,"abstract":"<div><div>In this paper, to improve the operational performance of crushing and strip-laying device in no-till planter, both the logarithmic helix curved shell and parabolic guide structures are first designed. Then, a lightweight discrete element particle model of flexible wet-adhesive rice straw is developed and the corresponding calibration method of contact model parameters is also proposed. Furthermore, a discrete element model of the whole straw-crushing and strip-laying device based on the JKR contact model is also established. It’s demonstrated that compared to the traditional straw model, the laying strip mass predicted by the developed straw model agrees better with experimental results. Moreover, the parabolic guide structure can reduce the variation coefficient of straw mass in the strip by 24.16 %, and the steady state flow of straw in the outlet area of the device is 0.205 kg/s. Finally, the response surface method is employed to determine the optimal crusher shaft speed (1617 rpm), inlet clearance (30 mm) and ground clearance (189 mm) of the straw-crushing and strip-laying device. A comparative analysis of bench test also reveals the optimization design can further reduce the variation coefficient of straw mass in the laying strip by 2.34 % and increase the cleanliness rate in the seed strip by 2.89 %.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110537"},"PeriodicalIF":7.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069992","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":"FTO-SORT: a fast track-id optimizer for enhanced multi-object tracking with SORT in unseen pig farm environments","authors":"Seunghyun Yu ,&nbsp;Hwapyeong Baek ,&nbsp;Seungwook Son ,&nbsp;Jongwoong Seo ,&nbsp;Yongwha Chung","doi":"10.1016/j.compag.2025.110540","DOIUrl":"10.1016/j.compag.2025.110540","url":null,"abstract":"<div><div>As the importance of animal welfare and agricultural automation continues to grow, advancements in real-time multi-object tracking technology within pig farm environments have become essential. In commercial farms (unseen datasets) differing from the trained dataset, various factors, such as light flares, object overlap, and ambiguous boundaries between the foreground and background, pose challenges that reduce detection accuracy. Although methods using large models or ensemble detectors exist, they often suffer from slower execution speeds. While other studies focus on improving accuracy on seen datasets, this can result in lower accuracy when applied to different farm environments. To address this, our study introduces a new data augmentation method called FBDA (Foreground-Background Separation and Data Augmentation) using SAM and LaMa to enhance performance without affecting execution speed. We also implemented a new weighting technique in the existing loss function to handle overlaps or ambiguous boundaries, termed OFBL (Overlap and Foreground-Background Difference Loss), which improves detection performance while maintaining YOLO’s speed. To further improve tracking performance, we introduced a new module, FTO (Farm Track-id Optimizer), into the BoT-SORT (Bag of Tricks for MOT Simple Online and Realtime Tracking) model, resulting in FTO-SORT (Farm Track-id Optimizer with SORT). Using our proposed method, we achieved significant improvements in tracking performance on unseen datasets, increasing IDF1 from 75.1% to 90.2% with YOLOv8 and from 68.7% to 86.7% with YOLOv11, representing gains of 15.1% and 18.0%, respectively. Additionally, by removing the Re-ID module from FTO-SORT, the FPS on the TX2 board increased, achieving speeds that were approximately 10.3 times faster (from 0.6 to 6.2 FPS) and 11.1 times faster (from 0.6 to 6.7 FPS), significantly enhancing processing speed. We shared our tracking dataset at <span><span>https://github.com/YuSeungHyun97/fto-sort</span><svg><path></path></svg></span> for precision livestock farming research community.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110540"},"PeriodicalIF":7.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070362","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":"Multi-objective optimization of pressure in self-pressurized irrigation networks based on meta-heuristic algorithm with valve openings","authors":"Qinggang Liu ,&nbsp;Zhenhua Wang ,&nbsp;Jinzhu Zhang ,&nbsp;Ningning Liu ,&nbsp;Rui Chen ,&nbsp;Pengcheng Luo","doi":"10.1016/j.compag.2025.110542","DOIUrl":"10.1016/j.compag.2025.110542","url":null,"abstract":"<div><div>To ensure effective management and safe operation of self-pressurized irrigation systems, this study proposes a pressure regulation model that employs <em>meta</em>-heuristic algorithms and controlled valve settings. This model aims to enhance system balance, reliability, and safety. This study developed a pressure regulation model that uses valve opening as the decision variable to optimize for both pressure balance and network reliability. To enhance algorithm efficiency, Taguchi’s method was applied to fine-tune the initial parameters of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Multi-Objective Particle Swarm Optimization (MOPSO). Indoor simulation tests were performed to determine the relationship between valve opening and the valve loss coefficient. Furthermore, based on real engineering cases, the performance of the two algorithms was comprehensively evaluated, using metrics such as computation time, number of Pareto solutions, maximum expansion index, spacing, and average ideal distance, in conjunction with the TOPSIS method. The results indicate that the NSGA-II score of 0.5011 outperforms the MOPSO score of 0.4989, demonstrating superior performance in solving the proposed problem. This model verification is based solely on simulation and a single case. It does not account for complex terrain, buried pipe conditions, or a comparison of multiple algorithms. Further on-site verification and algorithm optimization are required. Consequently, this research offers theoretical insights and technical guidance for the optimal regulation of pressure systems in self-pressurized irrigation networks.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110542"},"PeriodicalIF":7.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070361","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":"Calibration of the Edinburgh Elasto-Plastic Adhesion contact model for modelling clay-moist soil with high moisture content","authors":"Xuan Deng ,&nbsp;Wencheng Wu ,&nbsp;Jiawei You ,&nbsp;Rui Jiang ,&nbsp;Mengliang Li ,&nbsp;Ju Li ,&nbsp;Youfeng Tao ,&nbsp;Hong Cheng ,&nbsp;Wei Zhou ,&nbsp;Fei Deng ,&nbsp;Yong Chen ,&nbsp;Wanjun Ren ,&nbsp;Xiaolong Lei","doi":"10.1016/j.compag.2025.110518","DOIUrl":"10.1016/j.compag.2025.110518","url":null,"abstract":"<div><div>The discrete element method (DEM) has demonstrated significant advantages in simulating soil-tool interaction and an appropriate contact model notable affected the simulation accuracy. The accuracy of numerical simulation is compromised due to the variations in soil properties when tillage implements are employed in clay-moist soil conditions. This study aims to establish a discrete element model of clay-moist soil based on the Edinburgh Elasto-Plastic Adhesion (EEPA) contact model. Calibration tests using a combination of direct shear tests and cone penetration tests were conducted to identify sensitive parameters that need to be calibrated in the model and analyze the effects of each parameter. The results indicated that contact plasticity ratio and surface energy had significant influence on representing the mechanical properties of clay-moist soil. Then, by utilizing scanning technology to acquire furrow shape data, soil bin test was conducted to validate the reliability of the calibration parameters. Using sensitive parameters as variables, the actual value of clay-moist soil with a moisture content of 33 % as the target value obtained from experimental tests. The optimal combination was: the coefficient of static friction of 0.45, the coefficient of rolling friction of 0.18, and the surface energy of 27.95 J·m⁻², the contact plasticity ratio of 0.59. The relative error between the simulated draft force value and the actual measured value was 7.98 %, and the relative errors in the furrow type parameters did not exceed 5 %. The accuracy of the calibration results was verified through comparative analysis of simulation and empirical results. This study provides a scientific approach for employing DEM in modeling clay-moist soil-tool interaction.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"237 ","pages":"Article 110518"},"PeriodicalIF":7.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069967","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}