Computers and Electronics in Agriculture最新文献

{"title":"Integrating reinforcement learning and large language models for crop production process management optimization and control through a new knowledge-based deep learning paradigm","authors":"Dong Chen ,&nbsp;Yanbo Huang","doi":"10.1016/j.compag.2025.110028","DOIUrl":"10.1016/j.compag.2025.110028","url":null,"abstract":"<div><div>Efficient and sustainable crop production process management is crucial to meet the growing global demand for food, fuel, and feed while minimizing environmental impacts. Traditional crop management practices, often developed through empirical experience, face significant challenges in adapting to the dynamic nature of modern agriculture, which is influenced by factors such as climate change, soil variability, and market conditions. Recently, reinforcement learning (RL) and large language models (LLMs) bring transformative potential, with RL providing adaptive methodologies to learn optimal strategies and LLMs offering vast, superhuman knowledge across agricultural domains, enabling informed, context-specific decision-making. This paper systematically examines how the integration of RL and LLMs into crop management decision support systems (DSSs) can drive advancements in agricultural practice. We explore recent advancements in RL and LLM algorithms, their application within crop management, and the use of crop management simulators to develop these technologies. The convergence of RL and LLMs with crop management DSSs presents new opportunities to optimize agricultural practices through data-driven, adaptive solutions that can address the uncertainties and complexities of crop production. However, this integration also brings challenges, particularly in real-world deployment. We discuss these challenges and propose potential solutions, including the use of offline RL and enhanced LLM integration, to maximize the effectiveness and sustainability of crop management. Our findings emphasize the need for continued research and innovation to unlock the full potential of these advanced tools in transforming agricultural systems into optimal and controllable ones.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110028"},"PeriodicalIF":7.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395725","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 collaborative scheduling and planning method for multiple machines in harvesting and transportation operations-Part Ⅰ: Harvester task allocation and sequence optimization","authors":"Ning Wang ,&nbsp;Shunda Li ,&nbsp;Jianxing Xiao ,&nbsp;Tianhai Wang ,&nbsp;Yuxiao Han ,&nbsp;Hao Wang ,&nbsp;Man Zhang ,&nbsp;Han Li","doi":"10.1016/j.compag.2025.110060","DOIUrl":"10.1016/j.compag.2025.110060","url":null,"abstract":"<div><div>In the scenario of harvesting-transportation operation, the collaborative scheduling of harvesters and grain trucks is crucial for addressing the challenge of scheduling different types of agricultural machinery in farm areas. During the harvest, the harvesters and grain trucks must cooperate within a short time window. This study is divided into two parts (Part Ⅰ and Part Ⅱ), focusing on the collaborative scheduling problem of the harvesters, and operation coordination between harvesters and grain trucks, respectively. In this paper (Part I), we focus on addressing the problem of harvester task allocation and path planning. First, the topological map method was used to define the topological structure and construct an electronic map of the farm. Then, a multi-harvester task allocation model was built, and a greedy minimum–maximum load balancing algorithm based on the nearest-neighbor heuristic (GMM-LB-NNH) algorithm was proposed to solve the model and obtain the task sequence for the harvesters. Finally, based on the task sequence, the whole-process path planning for the harvester was completed. We conducted simulation tests of harvester task allocation and whole-process path planning experiments for harvesters using the electronic map we developed. The results demonstrate that the proposed method effectively achieves harvester task allocation and path planning. Additionally, it significantly reduces overall operation time by an average of 29.8 min compared to the Ant Colony Optimization algorithm and by 12.6 min compared to the Genetic Algorithm, providing a novel approach for the scheduling and planning of the same types of agricultural machinery.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110060"},"PeriodicalIF":7.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395106","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":"Pixel-level spectral reconstruction and compressed projection based on deep learning in detecting aflatoxin B1","authors":"Hongfei Zhu ,&nbsp;Yifan Zhao ,&nbsp;Longgang Zhao ,&nbsp;Ranbing Yang ,&nbsp;Zhongzhi Han","doi":"10.1016/j.compag.2025.110071","DOIUrl":"10.1016/j.compag.2025.110071","url":null,"abstract":"<div><div>Aflatoxin, a highly toxic substance posing a substantial threat to food safety, necessitates a reliable detection method. This paper introduces a pioneering aflatoxin detection approach based on spectral reconstruction and projection compression model. The proposed method effectively addresses data imbalance by reconstructing aflatoxin spectra. The reconstructed spectra achieve remarkable performance, with a training RMSE (root-mean-square error) of 0.0242 and a test RMSE of 0.0214. Subsequently, the LSTM (Long Short Term Memory) model is trained on a dataset comprising 25% reconstructed AFB1 spectra and 75% original spectra, resulting in a testing accuracy of 98.55% and a testing loss of 0.0611. To further enhance the model performance, PCA (Principal Component Analysis) and compression projection are employed to reduce the LSTM model’s parameters. Despite reducing the LSTM internal parameters, the fine-tuned LSTM achieves an outstanding testing accuracy of 98.30%. This research presents a practical and efficient aflatoxin detection approach, offering improved accuracy and significantly reduced model complexity. The proposed algorithm holds great potential for enhancing the detection capabilities of intelligent sorting equipment.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110071"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387961","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":"CustomBottleneck-VGGNet: Advanced tomato leaf disease identification for sustainable agriculture","authors":"Mohamed Zarboubi ,&nbsp;Abdelaaziz Bellout ,&nbsp;Samira Chabaa ,&nbsp;Azzedine Dliou","doi":"10.1016/j.compag.2025.110066","DOIUrl":"10.1016/j.compag.2025.110066","url":null,"abstract":"<div><div>In recent years, sustainable agriculture has become increasingly important due to challenges such as climate change, population growth, and the need for food security. Tomato plants, being highly susceptible to various diseases, require accurate and timely diagnosis to maintain crop quality. Deep learning, particularly convolutional neural networks (CNNs), has shown great potential in addressing this challenge. This study introduces an advanced method for identifying tomato diseases using the CustomBottleneck-VGGNet model, enhanced through transfer learning techniques. The objective is to develop a highly accurate and computationally efficient model that can be deployed on resource-constrained devices for real-time disease detection. The proposed model achieves a remarkable accuracy of 99.12% with just 1.4 million parameters, outperforming classical models such as MobileNetV2, ResNet50, GoogleNet, VGG16, and VGG19 in terms of accuracy, precision, recall, and F1-score. Additionally, a mobile application has been developed to deploy this model, enabling real-time disease detection using a smartphone camera or images from the gallery, even in offline environments. The study also introduces a novel method for model comparison, focusing on differences between models trained under identical conditions to ensure fair evaluations.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110066"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378701","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":"Study on seeding delay time and lag distance of automatic section control system for maize seeder","authors":"Lin Ling ,&nbsp;Hanqing Li ,&nbsp;Yuejin Xiao ,&nbsp;Weiqiang Fu ,&nbsp;Jianjun Dong ,&nbsp;Liwei Li ,&nbsp;Rui Liu ,&nbsp;Xinguang Huang ,&nbsp;Guangwei Wu ,&nbsp;Zhijun Meng ,&nbsp;Bingxin Yan","doi":"10.1016/j.compag.2025.110068","DOIUrl":"10.1016/j.compag.2025.110068","url":null,"abstract":"<div><div>Automatic section control (ASC) can effectively reduce the double-seeded area by controlling start and stop seeding automatically, thereby saving seeds and increasing yields. Seeding delay time (SDT) and seeding lag distance (SLD) are core factors that affect the accuracy and reliability of ASC systems. To explore the influence factors and variation patterns of SDT and SLD, this study developed an ASC system for maize seeder. The system can determine the position of each seed metering device based on a GNSS antenna, and automatically control the status of the motor of the seed metering device based on relative position between the seed metering device and the field. Theoretical analysis revealed that the angle between the seed and the seed drop point caused the start seeding delay time and start seeding lag distance (STLD) to be greater than the stop seeding delay time and stop seeding lag distance (SPLD), and the difference between the two lag distances is one seed spacing. The constructed SDT and SLD models showed that both SDT and SLD were also related to GNSS frequency and operational speed. To verify the accuracy of the model, field experiments were carried out based on GNSS frequencies (1, 5, 10 Hz) and operational speeds (4, 5, 6, 7, 8 km/h) with a seed spacing of 0.2 m. The field experiments showed that STLD was 0.703–2.191 m, and SPLD was 0.559–2.626 m, with STLD generally greater than SPLD, a difference of nearly one seed spacing. SLD was negatively correlated with GNSS frequencies and positively correlated with operational speed. GNSS frequency and operational speed had significant influences (<em>p</em> &lt; 0.001) on SLD. The correlation coefficients between SLD and the SLD model ranged from 0.54 to 0.90. Seed bouncing and seeder vibration caused a relative error of 4.51 % to 21.69 % in the SLD model. In conclusion, the SLD model can well describe the variation patterns and the significant influence of the actual SLD. The validation results of the SLD model indirectly supported the validity of the SDT model. The methods and results of this study can provide a reference for the development and optimization of ASC systems.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110068"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379120","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":"Utilizing CMIP6-SSP scenarios with the VIC model to enhance agricultural and ecological water consumption predictions and deficit assessments in arid regions","authors":"Qingling Bao ,&nbsp;Jianli Ding ,&nbsp;Jinjie Wang ,&nbsp;Lijing Han ,&nbsp;Jiao Tan","doi":"10.1016/j.compag.2025.110083","DOIUrl":"10.1016/j.compag.2025.110083","url":null,"abstract":"<div><div>Essential for economic development and ecological restoration in arid regions, water resources are currently facing unprecedented scarcity. Although future changes in surface water resources have been extensively examined, there has been limited focus on the balance between agricultural and ecological water consumption and water deficits, particularly in arid basins. A novel approach to estimating agricultural and ecological water consumption was introduced in this study using a physical process model (Variable Infiltration Capacity model, VIC) incorporating the latest Coupled Model Intercomparison Project Phase 6 (CMIP6) Shared Socioeconomic Pathway (SSPs) scenarios. Water consumption trends and deficits were analysed using historical data (1961–2014) and projected under the SSP126, SSP245, SSP370, and SSP585 scenarios for 2015–2100 in the Lake Ebinur basin. There was a significant increase in agricultural and ecological water consumption along with a growing water supply deficit, particularly under the SSP245 and SSP585 scenarios. Agricultural water consumption is projected to increase by 8.00% to 43.13%, ecological water consumption is expected to rise by 13.31% to 49.11%, and the water supply deficit is projected to increase by 45% to 113% relative to the baseline period. The average annual mean error of raw meteorological variables was reduced by 71.66% after applying bias correction, leading to an improvement of approximately 86.79% in the simulation accuracy of the VIC model compared with the uncorrected scenario. An increase in precipitation ranging from 4.00% to 33.56%, a maximum temperature increase of 230.88%, and a decrease in wind speed of 6.45% were projected for the mid-to-late 21st century under the SSP585 scenario. The water supply deficit was estimated to increase under the SSP245 scenario, with deficits projected to reach 1.35 billion m³ per year in the medium term and 1.59 billion m³ per year in the late term. Given the projected increase in agricultural and ecological water consumption and the growing future water supply deficit, quantifying these changes can provide critical insights into water resource management and sustainable development in arid regions.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110083"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388043","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 hybrid remotely operated underwater vehicle for maintenance operations in aquaculture: Practical insights from Greek fish farms","authors":"Marios Vasileiou ,&nbsp;George Vlontzos","doi":"10.1016/j.compag.2025.110045","DOIUrl":"10.1016/j.compag.2025.110045","url":null,"abstract":"<div><div>Aquaculture serves a pivotal function in catering to the increasing global need for seafood while simultaneously tackling the predicaments posed by the dwindling wild fish reserves. Underwater vehicles have contributed to the expansion of aquaculture by enabling underwater inspections, data collection, and improved maintenance procedures. In addition, underwater vehicles facilitate the acquisition of subsea data, enabling researchers to enhance aquaculture procedures and participate in initiatives aimed at attaining food security. The aim of this work is to design, develop, and evaluate underwater systems for the inspection and maintenance of net cages in aquaculture facilities. The research focuses on developing an underwater vehicle for aquaculture inspection along with the integration of a manipulator to perform maintenance tasks such as removing objects stuck on nets, collecting fish morts, and repairing net tears. This paper provides thorough research on the design of these systems and their applications in aquaculture in Greece. The subsequent focus is directed towards the development of a hybrid remotely operated vehicle, accentuating its software frameworks, modeling, mobility implementation, and navigational capabilities. This system can operate as a tetherless autonomous underwater vehicle for inspection tasks and as a tethered remotely operated vehicle with semi-automatic capabilities for maintenance tasks. In light of this, a tool manipulator is introduced, analyzing its underlying design principles, manipulator capabilities, and electronic integration. The effectiveness and operational capabilities of the underwater vehicle models are substantiated through experimental assessments carried out in Kefalonia fish farms in Greece, resulting in successful missions. The final remarks encapsulate the principal findings obtained from this study, examine their implications, and offer perspectives on forthcoming avenues for subaquatic robotics.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110045"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Yield estimation in precision viticulture by combining deep segmentation and depth-based clustering","authors":"Rosa Pia Devanna ,&nbsp;Laura Romeo ,&nbsp;Giulio Reina ,&nbsp;Annalisa Milella","doi":"10.1016/j.compag.2025.110025","DOIUrl":"10.1016/j.compag.2025.110025","url":null,"abstract":"<div><div>Grapevine phenotyping, that is the process of determining the physical properties (e.g., size, shape, and number) of grape bunches, provides valuable information for growth and health monitoring, yield estimation and efficient crop management in precision viticulture. Currently, grape bunch counting and sizing is done manually, which is labor intensive and often impractical for large-scale field applications. This paper describes a novel framework to automatically detect, count and estimate the volume/weight of grape bunches using RGB and depth data acquired in the field by a farmer robot. The proposed pipeline starts with the semantic segmentation of RGB images based on a pre-trained MANet architecture with EfficientnetB3 backbone to separate fruit from non-fruit regions. The segmented fruit mask is then projected onto the co-registered depth image to recover a depth mask, allowing for three-dimensional (3D) data association. After a pre-processing step to correct anomalies, such as corrupted and missing values, and to remove outliers, a depth gradient-based clustering algorithm is applied that detects individual grape bunch clusters. This enables the separation of adjacent and partially overlapping bunches. In addition, a method to reconstruct the whole 3D shape of a bunch is introduced, so as to provide an estimate of volume and weight. Experiments performed in a commercial vineyard in Italy are presented showing that, despite the low quality and high variability of the input images, the proposed approach is able to count grape bunch clusters with an average error of about 12% with respect to visual ground-truth and an average error less than 30% with respect to manual weight measurements. It is also shown that the processing framework can be applied to geo-referenced image sequences acquired by the farmer robot while traversing vineyard rows, thus providing an automated pipeline for the generation of high-resolution yield maps for precision viticulture applications.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110025"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing an IoT-driven delta robot to stimulate the growth of mulberry branch cuttings cultivated aeroponically using machine vision technology","authors":"Osama Elsherbiny ,&nbsp;Jianmin Gao ,&nbsp;Ming Ma ,&nbsp;Waqar Ahmed Qureshi ,&nbsp;Abdallah H. Mosha","doi":"10.1016/j.compag.2025.110111","DOIUrl":"10.1016/j.compag.2025.110111","url":null,"abstract":"<div><div>Machine vision plays a pivotal role in automatically monitoring the growth of mulberry branch cuttings (Mbc) in aeroponic systems, ensuring productivity, quality, and sustainability. However, the challenge lies in the varying bud growth rates, with some taking longer to break dormancy, leading to inconsistent development and delays in root formation. This paper aims to develop an Internet of Things (IoT)-integrated delta robot, equipped with advanced camera data acquisition and intelligent processing. It is intended to enhance aeroponic systems by precisely and rapidly detecting the Mbc growth state and applying growth stimulation. The system framework requires tiny machine learning models specifically designed to function efficiently on IoT hardware with limited power and resources, such as the lightweight versions of Tiny-YOLO, including YOLOv8-world, YOLOv9, YOLOv10, and YOLOv11. These models were trained on 3,000 images captured from three distinct camera perspectives—side view, elevated view, and angled view—during the growth of Mbc. Further optimization was achieved by progressively refining the weights through stepwise training. Artificial neural networks, for instance Back-Propagation Neural Networks (BPNN) and Elastic Net (ELNET), were deployed to compute the X, Y, and Z coordinates of the robot arm. Alongside, the look-up table approach efficiently identified the Mbc locations by referencing pre-stored data corresponding to the target coordinates. The experimental outcomes indicated that the optimized Tiny-YOLOv9 (Pr = 98.3 %, Re = 98.5 %, Fm = 98.4 %, mAP_50–90 = 87.3 %) outperformed other models in both classification and localization of mulberry branches. Data fusion from three cameras with BPNN and ELNET models substantially outshined the use of a single camera. Moreover, the BPNN models for the arm axes (X, Y, Z) exhibited superior accuracy compared to ELNET. The BPNN recorded R² values of 0.999 for all three axes (X, Y, and Z), with corresponding RMSE values of 0.005 (MAE = 0.004), 0.006 (MAE = 0.005), and 0.013 (MAE = 0.010), respectively. This work can assist the agricultural community in monitoring plant growth, enabling timely and effective management decisions. It also holds great promise for expanding our methodology to include other crops in future aeroponic systems.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110111"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388042","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":"Forest biomass carbon stock estimates via a novel approach: K-nearest neighbor-based weighted least squares multiple birth support vector regression coupled with whale optimization algorithm","authors":"Niannian Deng ,&nbsp;Renpeng Xu ,&nbsp;Ying Zhang ,&nbsp;Haoting Wang ,&nbsp;Chen Chen ,&nbsp;Huiru Wang","doi":"10.1016/j.compag.2025.110020","DOIUrl":"10.1016/j.compag.2025.110020","url":null,"abstract":"<div><div>Multiple birth support vector regression (MBSVR) provides fast computation and superior performance but overlooks local sample information and has challenges in parameter selection. The traditional least squares models boast fast computational speed but lack robustness and may struggle with noise and outliers. The carbon storage estimates are easily affected by noise and interference points. MBSVR and least squares models are only partially effective in carbon storage estimates. Consequently, we propose least squares multiple birth support vector regression (LSMBSVR) and K-nearest neighbor-based (KNN) weighted least squares multiple birth support vector regression (WLSMBSVR), which have the following merits. Firstly, both models inherit the strengths of MBSVR. Secondly, they exhibit enhanced fitting accuracy, robust stability, and remarkable anti-interference capability. Thirdly, LSMBSVR offers a faster training speed and maintains a comparable regression performance to MBSVR. Fourthly, WLSMBSVR considers the local information, enhancing its anti-interference capability. Lastly, we employ the whale optimization algorithm (WOA) to improve the effectiveness of parameter selection. Experiment results indicate that our models can be more effective on carbon storage, synthetic, and UCI datasets than compared models, verifying the broad application value of our models.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"232 ","pages":"Article 110020"},"PeriodicalIF":7.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379118","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}