Computers and Electronics in Agriculture最新文献

{"title":"Wheat yield forecasts with seasonal climate models and long short-term memory networks","authors":"Maximilian Zachow ,&nbsp;Stella Ofori-Ampofo ,&nbsp;Harald Kunstmann ,&nbsp;Rıdvan Salih Kuzu ,&nbsp;Xiao Xiang Zhu ,&nbsp;Senthold Asseng","doi":"10.1016/j.compag.2025.110965","DOIUrl":"10.1016/j.compag.2025.110965","url":null,"abstract":"<div><div>The potential of seasonal climate forecasts (SCFs) within machine learning models to forecast crop yields remains unexplored. We propose a workflow for integrating SCF data into a long short-term memory (LSTM) network to forecast wheat yield at the county level across the Great Plains in the United States. Each month, past predictors were filled with observations and future weather predictors were forecasted using the seasonal climate model of the European Centre for Medium-Range Weather Forecasts (SCF approach). This approach was benchmarked with the truncate approach that only used observed predictors. Using all observed predictors at harvest, the model achieved an R² of 0.46, an NRMSE of 0.24, and an MSE of 0.46 t/ha on the test set. The SCF approach and truncate approach performed poorly from January to March. The SCF approach outperformed the truncate approach in April and May. At the beginning of May, three months before harvest, the SCF approach achieved an MSE of 0.6 t/ha, improving the truncate approach by 10 %. In June, the SCF approach further improved but did not outperform the truncate approach. Predictor importance analysis revealed the critical role of SCF data at the beginning of May for the latter half of May. This study suggests that weather forecasts issued at the right time, when both crop development and forecast skill align, could be as short as 16 days and still significantly improve the accuracy of sub-national wheat yield forecasts over other approaches.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110965"},"PeriodicalIF":8.9,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060093","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":"Application and perspectives of plant flexible sensors in precision agriculture: material, fabrication and functional analysis","authors":"Nan Wu ,&nbsp;Jian Xu ,&nbsp;Lili Ren ,&nbsp;Wei Song","doi":"10.1016/j.compag.2025.110991","DOIUrl":"10.1016/j.compag.2025.110991","url":null,"abstract":"<div><div>As an important part of terrestrial ecosystems, the growth and development of plants were regulated by a variety of environmental factors. The rapid development of precision agriculture had put forward higher requirements for real-time monitoring of crop growth environments. Although traditional sensing technology could provide environmental data, it had limitations such as strong invasiveness, large dimensional rigidity, and insufficient long-term monitoring capabilities. The review aimed to systematically review the progress and applications of plant flexible sensors in plant science, highlighting their potential to overcome the limitations of traditional sensors through non-invasive, real-time, and dynamic monitoring of plant physiological and environmental parameters. The review focused on the material systems, fabrication processes, and functional applications of plant flexible sensors. Special attention was given to the roles of conductive polymers, carbon-based materials, and biocompatible substrates in sensor development. Plant flexible sensors, due to their mechanical compliance, functional sensitivity, and energy-efficient operation, offered significant advantages over traditional biosensors. These included in-situ monitoring, long-term operational stability, multi-parameter sensing capabilities, and enhanced adaptability to complex environmental conditions. The reviewed literature demonstrated that plant flexible sensors provided effective and precise monitoring solutions across a wide range of plant physiological processes and environmental conditions. The review provided theoretical guidance and technical reference for the design and application of plant flexible sensors in future agricultural research. The insights gained from this review could facilitate the development of smart agriculture systems, promote advances in plant phenomics, and support sustainable ecological monitoring efforts.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110991"},"PeriodicalIF":8.9,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060096","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":"Vibratory threshing mechanism and multi-species threshing parameter testing of wine grapes based on discrete element method","authors":"Huineng Zhou,&nbsp;Haochao Tan,&nbsp;Congcong Shen,&nbsp;Junlong Ma,&nbsp;Zhaoyang Guo,&nbsp;Zhendong Huang,&nbsp;Liming Xu,&nbsp;Shuai Ma","doi":"10.1016/j.compag.2025.110955","DOIUrl":"10.1016/j.compag.2025.110955","url":null,"abstract":"<div><div>This study aimed to achieve precision harvesting of wine grapes by investigating their vibratory threshing mechanism and measuring key harvesting parameters across eight varieties at different maturity stages. This study measured the geometric and physical parameters as well as the mechanical properties of Marselan bunches. The average values of the fruit detachment force (FDF) and fruit bursting force (FBF) at the optimal ripeness stage were found to be 3.22 N and 8.52 N, respectively. Based on the measurement results, a discrete element flexible model of grape bunches was established using the Bonding V2 Model. A vibration-based threshing parameter testing system for wine grapes was developed, featuring adjustable vibration frequency, angular amplitude, and movement speed, as well as functionality for detecting the vibration intensity of grape bunches. The accuracy of the simulation model was verified by comparing results with bench tests. A multifactor simulation test was conducted on Marselan grapes at the harvestable stage, using a Box-Behnken Design (BBD). The experimental factors included frequency, angular amplitude, movement speed, and sugar content, with threshing rate and breakage rate as response variables. The relative errors between simulation and bench tests were 2.36 % for threshing rate, 7.86 % for breakage rate, and 10.3 % for maximum acceleration amplitude. Analysis revealed two primary forms of berry threshing: impact threshing form, which predominantly affects the breakage rate, and vibratory threshing form, which primarily influences the threshing rate. It was identified that operational parameters (frequency, angular amplitude, and movement speed) and inherent varietal characteristics (FDF, FBF, and berry mass) were key factors affecting threshing quality. Furthermore, the relationships between these parameters and the threshing rate and breakage rate were clarified. The coefficient of breakage (CB) was introduced as an indicator of grape suitability for vibratory threshing for the first time. Grapes with a CB below 0.1 were considered unsuitable for mechanical threshing. Finally, orthogonal tests were conducted to identify the optimal combination of threshing parameters for several varieties at different maturity levels. The results provide a reference for optimizing the mechanized harvesting of wine grapes.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110955"},"PeriodicalIF":8.9,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060094","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":"A novel dual-polarization SAR vegetation index for crop phenology detection","authors":"Xin Bao ,&nbsp;Rui Zhang ,&nbsp;Xu He ,&nbsp;Age Shama ,&nbsp;Gaofei Yin ,&nbsp;Jie Chen ,&nbsp;Hongsheng Zhang ,&nbsp;Guoxiang Liu ,&nbsp;Xianjian Shi","doi":"10.1016/j.compag.2025.110953","DOIUrl":"10.1016/j.compag.2025.110953","url":null,"abstract":"<div><div>Precise crop phenology information is paramount for smart farming and food security. Nevertheless, traditional optical remote sensing methods are susceptible to cloud cover, leading to data discontinuities, which in turn makes the detection of full crop phenology challenging. Synthetic Aperture Radar (SAR) remote sensing technology enjoys the advantage of all-weather observation. However, SAR data has not been systematically employed for comprehensive crop phenological stage detection to date. Consequently, we introduce a novel dual-polarization SAR vegetation index for crop whole phenological stage detection. This method initially unifies SAR data’s covariance elements and intensity information to establish co-polarized principal component parameters (<em>m_cp</em>). Subsequently, a scale parameter (<em>R_cp</em>) is formulated by combining the polarization degree to represent the co-polarization principal component polarization direction within the SAR signal. By combining <em>m_cp</em> and <em>R_cp</em>, a new dual-polarization SAR vegetation index (DRVIs) is devised. Finally, based on time-series DRVIs data, an enhanced shape model fitting technique is utilized to detect the seven phenological stages of winter wheat growth. For validation purpose, this study focuses on the Eastern Henan Plain, employing 89 Sentinel-1 images captured from 2020 to 2022 for experimentation. The results of the experiments manifest that DRVIs exhibit a close correlation with the crop growth process, ranging from approximately 0.2 to 1.0. Winter wheat phenology is detected using DRVIs and NDVI, achieving a remarkable correlation coefficient of 0.94 between the two. Compared with in-situ data, DRVIs are more effective in minimizing phenological detection errors than NDVI. In general, this method effectively delves deeper into the potential of SAR vegetation indices in crop phenology detection, thus broadening the scope of SAR data applications in smart agriculture.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110953"},"PeriodicalIF":8.9,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049454","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":"SE-YOLO: A sobel-enhanced framework for high-accuracy, lightweight real-time tomato detection with edge deployment capability","authors":"Xiao Deng ,&nbsp;Tianlun Huang ,&nbsp;Weijun Wang ,&nbsp;Wei Feng","doi":"10.1016/j.compag.2025.110973","DOIUrl":"10.1016/j.compag.2025.110973","url":null,"abstract":"<div><div>Tomato detection is one of the most crucial steps in automated tomato harvesting. However, detection in agricultural settings faces challenges from complex environments and computational constraints. Here, we propose SE-YOLO, a lightweight framework with fundamentally different technical approach compared to existing methods. While current SOTA methods like RT-DETR rely on complex transformer architectures for global attention and Hyper-YOLO employs hypergraph computation for high-order feature relationships, SE-YOLO introduces a more direct and efficient paradigm through explicit edge perception. This approach includes: (i) SPStem’s integration of Sobel operators at network entry to directly extract edge features—a departure from the conventional approach of implicitly learning edges through multiple convolutional layers used in existing frameworks; (ii) ADown’s efficient channel-split architecture; (iii) SEDFF’s residual-based edge enhancement throughout the backbone that preserves both edge and semantic information; and (iv) WFPIoU’s adaptive spatial supervision that dynamically adjusts loss weights across training phases—contrasting with the static penalty terms in conventional IoU losses like CIoU and EIoU. These innovations create a detection framework specifically optimized for agricultural environments, capturing crucial boundary information for occluded fruits while maintaining minimal computational overhead. SE-YOLO achieves 93.6% [email protected] and 67.3% [email protected]:0.95, outperforming state-of-the-art detectors while using only 4.3% of RT-DETR’s computational cost Subsequently, the developed SE-YOLO model is deployed on standard edge hardware in INT8-quantized form. The deployment achieves 18.7 frames per second (FPS), with an 88.8% [email protected] and a 61.6% [email protected]:0.95, showing gains of 3.2% and 2.4%, respectively, over the YOLO11n model. Finally, the generalization performance of SE-YOLO is tested and validated across other datasets, demonstrating its effectiveness in detecting occluded and partially visible tomatoes, as well as in maturity-related detection tasks.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110973"},"PeriodicalIF":8.9,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049455","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":"Caged broiler aggregation behavior recognition via target detection and label merging","authors":"Chao Yuan ,&nbsp;Zikang Chen ,&nbsp;Yurong Tang ,&nbsp;Ruqian Zhao ,&nbsp;Longshen Liu ,&nbsp;Mingxia Shen","doi":"10.1016/j.compag.2025.110844","DOIUrl":"10.1016/j.compag.2025.110844","url":null,"abstract":"<div><div>In modern broiler farming, precise environmental control is crucial for the health and production efficiency of the flock, particularly during the chick stage where temperature fluctuations can easily induce stress responses. Currently, intensive farming relies on large-scale environmental control systems for climate regulation and is progressively advancing towards intelligent and precision-oriented development. However, the rapid and accurate assessment of broilers’ adaptability to their environment remains a pivotal challenge. This study proposes an automated detection method based on computer vision to recognize the aggregation behavior of caged broilers. The method employs the YOLOv8-CBAM model to detect individual and group areas, combined with an optimization algorithm based on Relative Intersection Ratio (RIR) to enhance the recognition accuracy of broiler aggregation behavior. Subsequently, by extracting the spatial distribution characteristics of the flock, a random forest classifier is utilized to classify the distribution state into three categories: “Dispersed,” “Normal,” and “Aggregated”. The experimental results demonstrate that the method achieves 94.44% accuracy, 93.88% precision, and 96.67% recall in the recognition of aggregation behavior. Furthermore, in the long video analysis test, the detected trends of flock aggregation and dispersion show precise correspondence with actual observations. This study provides an efficient and intelligent solution for monitoring aggregation behavior of broilers in caged environments, contributing to the realization of precise environmental control and the enhancement of farming management standards.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110844"},"PeriodicalIF":8.9,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049456","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":"Exploring the influence of coupling diverse spectral resolutions and feature selection approaches on the estimate of equivalent water thickness in fruit tree leaves","authors":"Jintao Cui ,&nbsp;Mamat Sawut ,&nbsp;Xin Hu ,&nbsp;Areziguli Rouzi ,&nbsp;Jiaxi Liang ,&nbsp;Zijing Xue ,&nbsp;Asiya Manlike ,&nbsp;Ainiwan Aimaier ,&nbsp;Nijat Kasim","doi":"10.1016/j.compag.2025.110983","DOIUrl":"10.1016/j.compag.2025.110983","url":null,"abstract":"<div><div>Accurate and effective acquisition of physiological parameter information from fruit trees plays an important role in the fine management of orchards. The extensive use of hyperspectral remote sensing technology in the field of agriculture provides an effective means for the scientific management of orchards. Accurate estimation of leaf equivalent water thickness (EWT) is crucial for applying hyperspectral remote sensing technology to assess the growth status of fruit trees. However, current research lacks a focus on analyzing the spectral resolution within the feature set to further evaluate its robustness and sensitivity to the inversion of the EWT of fruit tree leaves, and to develop an efficient inversion model specifically for fruit tree leaf EWT. This study aims to investigate the impact of coupling different spectral resolutions with feature selection methods on predicting EWT at the leaf level. Specifically, the leaf spectra of walnut, apricot, and jujube trees were measured using an ASD FieldSpec4 spectrometer in the field in Xinjiang, China’s northwest region, while the EWT of the leaves was determined in the laboratory. The Prospect-D model was utilized to generate a simulated spectral dataset, which was subsequently resampled at nine different resolutions, ranging from 1 to 100 nm. The selection of feature sets in this study was based on this simulated dataset. Secondly, various spectral indices, including three-band spectral indices (TBI1, TBI2, and TBI3) and two-band spectral indices (DSI, NDSI, and RSI), were combined with feature band selection methods, namely Competitive Adaptive Reweighted Sampling (CARS) and Successive Projections Algorithm (SPA), as well as the downscaling method t-distributed stochastic neighbor embedding (t-SNE), to couple different spectral resolutions with feature selection strategies. Finally, WOA-RF models were employed to evaluate model performance. The study aimed to identify the optimal model by validating the model for each fruit tree sample set. The findings of this study revealed the following: (1) The EWT of walnut leaf samples was significantly higher compared to that of apricot and jujube leaf samples, with a Coefficient of Variation (CV) less than that of apricot and jujube datasets (CV &lt; 25.7%). (2) The Random Forest (RF) model optimized using the whale optimization algorithm (WOA) demonstrated superior estimation performance compared to the original model. Specifically, it exhibited higher values for R-squared (R²), relative percent deviation (RPD), and the ratio of performance to interquartile distance (RPIQ), along with a lower mean absolute error (MAE). (3) Validation using a single sample set indicated that, for the middle resolution, the optimal combination based on the WOA-RF model was 20 nm-CARS, achieving R² &gt; 0.881, RPD &gt; 2.021, RPIQ &gt; 1.6418, and MAE &lt; 0.00097. Notably, this model requires only lower spectral resolution and fewer band c","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110983"},"PeriodicalIF":8.9,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049392","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":"Towards the in-situ trunk identification and length measurement of sea cucumbers via Bézier curve modelling","authors":"Shuaixin Liu ,&nbsp;Kunqian Li ,&nbsp;Yilin Ding ,&nbsp;Kuangwei Xu ,&nbsp;Qianli Jiang ,&nbsp;Q.M. Jonathan Wu ,&nbsp;Dalei Song","doi":"10.1016/j.compag.2025.110944","DOIUrl":"10.1016/j.compag.2025.110944","url":null,"abstract":"<div><div>We introduce a novel vision-based framework for in-situ trunk identification and length measurement of sea cucumbers, which plays a crucial role in the monitoring of marine ranching resources and mechanized harvesting. To model sea cucumber trunk curves with varying degrees of bending, we utilize the parametric Bézier curve due to its computational simplicity, stability, and extensive range of transformation possibilities. Then, we propose an end-to-end unified framework that combines parametric Bézier curve modelling with the widely used You-Only-Look-Once (YOLO) pipeline, abbreviated as TISC-Net, and incorporates effective funnel activation and efficient multi-scale attention modules to enhance curve feature perception and learning. Furthermore, we propose incorporating trunk endpoint loss as an additional constraint to effectively mitigate the impact of endpoint deviations on the overall curve. Finally, by utilizing the depth information of pixels located along the trunk curve captured by a binocular camera, we propose accurately estimating the in-situ length of sea cucumbers through space curve integration. We established two challenging benchmark datasets for curve-based in-situ sea cucumber trunk identification. These datasets consist of over 1,000 real-world marine environment images of sea cucumbers, accompanied by Bézier format annotations. We conduct evaluation on SC-ISTI, for which our method achieves mAP50 above 0.9 on both object detection and trunk identification tasks. Extensive length measurement experiments demonstrate that the average absolute relative error is around 0.15. The new benchmarks, source code, and pre-trained models are available on the project homepage: <span><span>https://github.com/OUCVisionGroup/TISC-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110944"},"PeriodicalIF":8.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049432","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":"Numerical analysis and parameter optimization of soil-loosening plow compatible with the shovel-type seedbed preparation machine","authors":"Jianxin Lin ,&nbsp;Yan Kang ,&nbsp;Qingxi Liao ,&nbsp;Wenbin Du ,&nbsp;Lin Li ,&nbsp;Qingsong Zhang","doi":"10.1016/j.compag.2025.110981","DOIUrl":"10.1016/j.compag.2025.110981","url":null,"abstract":"<div><div>The soil-loosening plow (SLP) was mounted in front of the shovel-type seedbed preparation machine (SSPM) to form a combined tillage machine (CTM), which is used for rapeseed seedbed preparation in rice-rapeseed rotation regions. A discrete element method-multibody dynamics (DEM-MBD) simulation model was developed in this manuscript, and the model’s accuracy was validated by comparing the power take-off torque (PT), draft force (DF), and clod crushing rate (CCR) of the SSPM during the simulation and experiment processes. Based on the validated model, the CTM was used as the simulation test implement. Tillage depth, wing installation height, and wing installation angle of the SLP were chosen as simulation factors. Simulation tests were conducted using the CCR and power consumption as evaluation indices. Single-factor experiment results showed that the DF power and total power consumption of the CTM increased progressively with greater tillage depth of the SLP, whereas the PT power consumption exhibited an opposite trend. As the wing installation height increased, the DF power consumption of CTM decreased, while the PT power consumption increased. With increasing wing installation angle, the DF power consumption of CTM first decreased and then increased. With the objective function of minimizing PT power consumption and total power consumption, the optimal parameters were determined to be a tillage depth of 160 mm, a wing installation height of 22 mm, and a wing installation angle of 5°. A comparative simulation was then performed between the CTM configured with these optimal parameters and the SSPM without installing the SLP. The simulation results indicated that, in comparison with the SSPM, the CTM increased the number of broken soil bonds by 10.50 %, the average tillage resistance on shovel and PT were reduced by 35.26 % and 31.06 %, respectively. These results indicated that the optimized SLP effectively lowered the PT requirement and tillage resistance on shovel during CTM operation. The experiments conducted on fields following rice harvest confirmed these simulation results. After CTM operation, the tillage depth stability coefficient, straw burial rate, and CCR reached 82.39 %, 86.69 %, and 83.54 %, respectively—improvements of 13.78 %, 10.17 %, and 7.89 % over the SSPM.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110981"},"PeriodicalIF":8.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049433","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":"Evaluation of the random forest regression machine learning technique as an alternative to ecoregional based regression taper modelling","authors":"Maria J. Diamantopoulou ,&nbsp;Ramazan Özçelik ,&nbsp;Şerife Kalkanli Genç","doi":"10.1016/j.compag.2025.110964","DOIUrl":"10.1016/j.compag.2025.110964","url":null,"abstract":"<div><div>Ecologically oriented management plans are based upon accurate estimation of stand growth and yield under various climatic and growing environmental conditions. Furthermore, the precise calculation of the volume quantities of the wood classes that can be obtained from a tree is of great importance for the production of forest management plans and projections for the future of the forest products industry. Despite their limitations, stem taper regression models are one of the most widely used methods for estimating tree diameters along the bole and estimating the tree stem volume. In this study, the non-parametric ensemble algorithm <em>RFr</em> was evaluated as an alternative machine learning approach for ecoregion-based taper modelling. <em>RFr</em> models were developed to accurately estimate stem diameters along the tree bole for trees from three distinct ecoregions, yielding precise diameter predictions. A comparative analysis between the <em>RFr</em> models and traditional taper regression models demonstrated that both methods are capable of reliably predicting stem diameters and tree volumes. However, the non-parametric nature of the <em>RFr</em> modelling approach, which effectively reduces the variance of individual regression tree learners, allowed it to outperform the conventional taper regression. The <em>RFr</em> models produced more accurate predictions of both stem diameter and volume and exhibited high reliability in their prediction intervals, as confirmed by uncertainty assessments. Overall, the <em>RFr</em> approach showed superior performance on both training and testing datasets.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"239 ","pages":"Article 110964"},"PeriodicalIF":8.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049476","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}