Pub Date : 2024-11-09DOI: 10.1016/j.compag.2024.109619
Érica Souza Gomes , Gustavo Roberto Fonseca de Oliveira , Arthur Almeida Rodrigues , Camila Graziela Corrêa , Eduardo de Almeida , Hudson Wallace Pereira de Carvalho , Valter Arthur , Edvaldo Aparecido Amaral da Silva , Arthur I. Novikov , Clíssia Barboza Mastrangelo
Strategies to increase the concentration of essential micronutrients for the plant cycle have made a remarkable contribution to agriculture. Ultrasonic waves have the potential to increase cell wall permeability and enhance the chemical composition of seed tissues. In this context, the aim of this study was to verify if it is possible to increase the zinc (Zn) supplementation of soybean seeds through their controlled exposure to ultrasonic waves with improvements in the photosynthetic efficiency (Fv/Fm) of the resulting seedlings. Initially, we investigated the impact of ultrasonic waves on the physical, physiological and spectral parameters of soybean seeds. Next, the seeds were treated with Zn and analyzed by X-ray fluorescence spectroscopy to better understand the kinetics of Zn uptake. Finally, we evaluated the germination, vigor, pigments and photosynthetic performance of seedlings. The main results showed that ultrasound modifies the structure of the seed coat without interfering with the dynamics of water absorption and the germination capacity of the seeds. The changes promoted by the technology favor Zn supplementation of more than 100 % in the seeds. In addition, the resulting seedlings show Fv/Fm values 92.7 % higher than the control, and an increase in chlorophyll fluorescence, initial fluorescence, and anthocyanin. We show that ultrasonic wave technology combined with Zn treatment improves the performance of soybean seeds, producing seedlings with superior photosynthetic efficiency.
提高植物循环所必需的微量营养元素浓度的策略为农业做出了卓越的贡献。超声波具有增加细胞壁渗透性和提高种子组织化学成分的潜力。在这种情况下,本研究的目的是验证是否有可能通过控制大豆种子暴露于超声波来增加其锌(Zn)的补充量,从而提高秧苗的光合效率(Fv/Fm)。首先,我们研究了超声波对大豆种子的物理、生理和光谱参数的影响。接着,用锌处理种子并用 X 射线荧光光谱分析,以更好地了解锌的吸收动力学。最后,我们评估了幼苗的发芽率、活力、色素和光合作用性能。主要结果表明,超声波改变了种皮结构,但不会干扰种子的吸水动力学和发芽能力。该技术促进的变化有利于种子中锌的补充量超过 100%。此外,秧苗的 Fv/Fm 值比对照组高 92.7%,叶绿素荧光、初始荧光和花青素也有所增加。我们的研究表明,超声波技术与锌处理相结合可改善大豆种子的性能,培育出光合效率更高的幼苗。
{"title":"Ultrasound technology supplements zinc in soybean seeds and increases the photosynthetic efficiency of seedlings","authors":"Érica Souza Gomes , Gustavo Roberto Fonseca de Oliveira , Arthur Almeida Rodrigues , Camila Graziela Corrêa , Eduardo de Almeida , Hudson Wallace Pereira de Carvalho , Valter Arthur , Edvaldo Aparecido Amaral da Silva , Arthur I. Novikov , Clíssia Barboza Mastrangelo","doi":"10.1016/j.compag.2024.109619","DOIUrl":"10.1016/j.compag.2024.109619","url":null,"abstract":"<div><div>Strategies to increase the concentration of essential micronutrients for the plant cycle have made a remarkable contribution to agriculture. Ultrasonic waves have the potential to increase cell wall permeability and enhance the chemical composition of seed tissues. In this context, the aim of this study was to verify if it is possible to increase the zinc (Zn) supplementation of soybean seeds through their controlled exposure to ultrasonic waves with improvements in the photosynthetic efficiency (Fv/Fm) of the resulting seedlings. Initially, we investigated the impact of ultrasonic waves on the physical, physiological and spectral parameters of soybean seeds. Next, the seeds were treated with Zn and analyzed by X-ray fluorescence spectroscopy to better understand the kinetics of Zn uptake. Finally, we evaluated the germination, vigor, pigments and photosynthetic performance of seedlings. The main results showed that ultrasound modifies the structure of the seed coat without interfering with the dynamics of water absorption and the germination capacity of the seeds. The changes promoted by the technology favor Zn supplementation of more than 100 % in the seeds. In addition, the resulting seedlings show Fv/Fm values 92.7 % higher than the control, and an increase in chlorophyll fluorescence, initial fluorescence, and anthocyanin. We show that ultrasonic wave technology combined with Zn treatment improves the performance of soybean seeds, producing seedlings with superior photosynthetic efficiency.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109619"},"PeriodicalIF":7.7,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661780","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}
Pub Date : 2024-11-07DOI: 10.1016/j.compag.2024.109591
Guoxing Chen, Guoqiang Zhang, Li Rong
Maintaining proper interior thermal condition during transportation is vital for animal welfare and sustainability of livestock supply chain. This study investigated the air temperatures inside a multi-deck naturally ventilated vehicle when transporting weaner pigs under warmer weather condition by using computational fluid dynamics (CFD). Predictive models of interior air temperatures were developed by using response surface methodology (RSM) and gradient boosting machine (GBM) with the inputs of exterior air temperature, vehicle speed, wind speed, incident wind angle and opening height of shutter based on the dataset generated from CFD simulations and validated as well. The results showed that predictive models developed by RSM were sufficient for predicting the interior air temperatures of moving naturally ventilated livestock vehicle, and GMB could improve the prediction accuracy moderately. RSM models indicated that the interior temperatures increased linearly with the increase in exterior air temperature, opening height and wind speed while insensitive to vehicle speed. GMB model indicated that the plane-average air temperature of front compartments was 2.2 °C higher than those of the other two compartments at the same deck, and the air temperature increased slightly from the bottom to the upper deck. High spatial variations in air temperature were observed inside the moving livestock vehicle, which poses a challenge on monitoring interior air temperatures. The developed models are expected to predict the interior air temperatures and provide suggestion on regulating ventilation systems in advance. Further study could be conducted to investigate the optimum control of opening for improving the natural ventilation potential.
{"title":"Predictive models of air temperatures inside a naturally ventilated vehicle transporting weaner pigs","authors":"Guoxing Chen, Guoqiang Zhang, Li Rong","doi":"10.1016/j.compag.2024.109591","DOIUrl":"10.1016/j.compag.2024.109591","url":null,"abstract":"<div><div>Maintaining proper interior thermal condition during transportation is vital for animal welfare and sustainability of livestock supply chain. This study investigated the air temperatures inside a multi-deck naturally ventilated vehicle when transporting weaner pigs under warmer weather condition by using computational fluid dynamics (CFD). Predictive models of interior air temperatures were developed by using response surface methodology (RSM) and gradient boosting machine (GBM) with the inputs of exterior air temperature, vehicle speed, wind speed, incident wind angle and opening height of shutter based on the dataset generated from CFD simulations and validated as well. The results showed that predictive models developed by RSM were sufficient for predicting the interior air temperatures of moving naturally ventilated livestock vehicle, and GMB could improve the prediction accuracy moderately. RSM models indicated that the interior temperatures increased linearly with the increase in exterior air temperature, opening height and wind speed while insensitive to vehicle speed. GMB model indicated that the plane-average air temperature of front compartments was 2.2 °C higher than those of the other two compartments at the same deck, and the air temperature increased slightly from the bottom to the upper deck. High spatial variations in air temperature were observed inside the moving livestock vehicle, which poses a challenge on monitoring interior air temperatures. The developed models are expected to predict the interior air temperatures and provide suggestion on regulating ventilation systems in advance. Further study could be conducted to investigate the optimum control of opening for improving the natural ventilation potential.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109591"},"PeriodicalIF":7.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661772","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}
Pub Date : 2024-11-07DOI: 10.1016/j.compag.2024.109605
Daoming She , Zhichao Yang , Yudan Duan , Michael G. Pecht
Combine harvester gearboxes operate for extended periods under variable operating conditions, making it costly to gather sufficient fault data. A meta transfer learning-driven fault diagnosis method for combine harvester gearboxes is proposed to solve the complex operating conditions and scarce fault samples. The meta learning is employed to train the model so that the performance of the proposed method is not contingent upon the quantity of training data. The multi-step loss optimization (MSL) method is introduced to improve the inner loop and address the unstable update gradients in training. The enhanced method uses each task to refine the model updating strategy, thus circumventing the gradient explosion and decay. The proposed method employs conditional domain adversarial network to extract deep discriminative features from both domains. The batch feature constraint (BFC) is proposed to balance the features’ transferability and class discriminability. A weight-balancing strategy is employed to reconstruct the training loss function, enabling gearbox fault diagnosis under variable operating conditions with few-shot data. The effectiveness of the proposed method is validated through data collected from the combined harvester gearbox’s fault diagnosis experimental rig.
{"title":"A meta transfer learning-driven few-shot fault diagnosis method for combine harvester gearboxes","authors":"Daoming She , Zhichao Yang , Yudan Duan , Michael G. Pecht","doi":"10.1016/j.compag.2024.109605","DOIUrl":"10.1016/j.compag.2024.109605","url":null,"abstract":"<div><div>Combine harvester gearboxes operate for extended periods under variable operating conditions, making it costly to gather sufficient fault data. A meta transfer learning-driven fault diagnosis method for combine harvester gearboxes is proposed to solve the complex operating conditions and scarce fault samples. The meta learning is employed to train the model so that the performance of the proposed method is not contingent upon the quantity of training data. The multi-step loss optimization (MSL) method is introduced to improve the inner loop and address the unstable update gradients in training. The enhanced method uses each task to refine the model updating strategy, thus circumventing the gradient explosion and decay. The proposed method employs conditional domain adversarial network to extract deep discriminative features from both domains. The batch feature constraint (BFC) is proposed to balance the features’ transferability and class discriminability. A weight-balancing strategy is employed to reconstruct the training loss function, enabling gearbox fault diagnosis under variable operating conditions with few-shot data. The effectiveness of the proposed method is validated through data collected from the combined harvester gearbox’s fault diagnosis experimental rig.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109605"},"PeriodicalIF":7.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661816","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}
Pub Date : 2024-11-07DOI: 10.1016/j.compag.2024.109624
Pengfei Zhao , Xiaojun Gao , Xiaoteng Ju , Pengkun Yang , Qingbin Song , Yuxiang Huang , Zhiqi Zheng
Conventional wheat wide-seedbed strip rotary tillage devices face several disadvantages, including low straw cleaning efficiency, inadequate soil pulverization, inconsistent sowing depth, and high-power consumption. Therefore, this study introduces a novel front-mounted fertilizer pipe wide-seedbed strip rotary tillage device. The fertilizer pipe is strategically positioned within the gap between the rotary tillage blade groups, enabling an integrated operation with the rotary tillage blade assembly. To minimize trenching resistance, the design combines the fertilizer pipe with a sliding knife. Through theoretical analysis, this study analyzes the operating principles of the front-mounted fertilizer pipe wide-seedbed strip rotary tillage device, explores the structural characteristics of the Standard strip rotary tillage blade Group (SG) and Trapezoidal straight blade Group (TG), and examines the sources of power consumption during operation. A corresponding discrete element simulation model is constructed, and its validity is confirmed through soil bin experiments. These experiments underscore the model’s effectiveness. Subsequently, the study compares the effects of the SG and TG on the wide-seedbed strip rotary tillage device based on simulation experiments. Additionally, a regression orthogonal rotation combination experimental design is employed to investigate how the rotation speed of the strip rotary tillage blade group, the forward spacing between the fertilizer pipe and blade shaft, and the types of blades affect straw cleaning and soil crushing. Moreover, response surface methodology is employed to clarify the influence of these factors on the experimental outcomes. Optimization results indicate that under a rotation speed of 270 rpm for the strip rotary tillage blade group, a forward spacing of 30 mm, and a combination of SG and TG, the device performs optimally. Under these conditions, it achieves a theoretical straw cleaning rate of 55.38 %, a soil crushing rate of 79.56 %, and a total power consumption of 3.26 kW. These findings support the development and optimization of wheat wide seedling belt sowing devices.
{"title":"Optimization of the front-mounted fertilizer pipe strip rotary tillage device by modeling the wide-seedbed characteristics and power consumption","authors":"Pengfei Zhao , Xiaojun Gao , Xiaoteng Ju , Pengkun Yang , Qingbin Song , Yuxiang Huang , Zhiqi Zheng","doi":"10.1016/j.compag.2024.109624","DOIUrl":"10.1016/j.compag.2024.109624","url":null,"abstract":"<div><div>Conventional wheat wide-seedbed strip rotary tillage devices face several disadvantages, including low straw cleaning efficiency, inadequate soil pulverization, inconsistent sowing depth, and high-power consumption. Therefore, this study introduces a novel front-mounted fertilizer pipe wide-seedbed strip rotary tillage device. The fertilizer pipe is strategically positioned within the gap between the rotary tillage blade groups, enabling an integrated operation with the rotary tillage blade assembly. To minimize trenching resistance, the design combines the fertilizer pipe with a sliding knife. Through theoretical analysis, this study analyzes the operating principles of the front-mounted fertilizer pipe wide-seedbed strip rotary tillage device, explores the structural characteristics of the Standard strip rotary tillage blade Group (SG) and Trapezoidal straight blade Group (TG), and examines the sources of power consumption during operation. A corresponding discrete element simulation model is constructed, and its validity is confirmed through soil bin experiments. These experiments underscore the model’s effectiveness. Subsequently, the study compares the effects of the SG and TG on the wide-seedbed strip rotary tillage device based on simulation experiments. Additionally, a regression orthogonal rotation combination experimental design is employed to investigate how the rotation speed of the strip rotary tillage blade group, the forward spacing between the fertilizer pipe and blade shaft, and the types of blades affect straw cleaning and soil crushing. Moreover, response surface methodology is employed to clarify the influence of these factors on the experimental outcomes. Optimization results indicate that under a rotation speed of 270 rpm for the strip rotary tillage blade group, a forward spacing of 30 mm, and a combination of SG and TG, the device performs optimally. Under these conditions, it achieves a theoretical straw cleaning rate of 55.38 %, a soil crushing rate of 79.56 %, and a total power consumption of 3.26 kW. These findings support the development and optimization of wheat wide seedling belt sowing devices.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109624"},"PeriodicalIF":7.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661775","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}
Pub Date : 2024-11-07DOI: 10.1016/j.compag.2024.109604
Hongsheng Li, Li Yang, Dongxing Zhang, Cui Tao, Xiantao He, Chunji Xie, Chuan Li, Zhaohui Du, Tianpu Xiao, Zhimin Li, Haoyu Wang
This study designs a pneumatic seed delivery system for a high-speed corn planter based on the Venturi effect, aimed at improving seeding uniformity and efficiency. By utilizing an external blower to generate airflow, the seeds are accelerated within the seed tube, reducing collisions between seeds and achieving stable seed transport. The research adopts a gas–solid two-phase method to explore the effects of airflow rate and pressure on seed acceleration and delivery, revealing the principles of gas dynamics in seed transportation. DEM-CFD simulation technology, which integrates Discrete Element Method and Computational Fluid Dynamics, is employed to more accurately simulate the physical processes within the granular-fluid system, ensuring rapid acceleration and stable transport of seeds. Through response surface methodology (RSM), the structural parameters of the seed tube were optimized, identifying the main factors and optimal levels influencing seed delivery performance. Experimental results demonstrate that the newly designed seed tube significantly enhances seed movement speed and seeding uniformity under high-speed seeding conditions, confirming its potential application in high-precision planting.
{"title":"Design and optimization of a high-speed maize seed guiding device based on DEM-CFD coupling method","authors":"Hongsheng Li, Li Yang, Dongxing Zhang, Cui Tao, Xiantao He, Chunji Xie, Chuan Li, Zhaohui Du, Tianpu Xiao, Zhimin Li, Haoyu Wang","doi":"10.1016/j.compag.2024.109604","DOIUrl":"10.1016/j.compag.2024.109604","url":null,"abstract":"<div><div>This study designs a pneumatic seed delivery system for a high-speed corn planter based on the Venturi effect, aimed at improving seeding uniformity and efficiency. By utilizing an external blower to generate airflow, the seeds are accelerated within the seed tube, reducing collisions between seeds and achieving stable seed transport. The research adopts a gas–solid two-phase method to explore the effects of airflow rate and pressure on seed acceleration and delivery, revealing the principles of gas dynamics in seed transportation. DEM-CFD simulation technology, which integrates Discrete Element Method and Computational Fluid Dynamics, is employed to more accurately simulate the physical processes within the granular-fluid system, ensuring rapid acceleration and stable transport of seeds. Through response surface methodology (RSM), the structural parameters of the seed tube were optimized, identifying the main factors and optimal levels influencing seed delivery performance. Experimental results demonstrate that the newly designed seed tube significantly enhances seed movement speed and seeding uniformity under high-speed seeding conditions, confirming its potential application in high-precision planting.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109604"},"PeriodicalIF":7.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661774","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}
Pub Date : 2024-11-06DOI: 10.1016/j.compag.2024.109584
Yishan Ji , Zehao Liu , Rong Liu , Zhirui Wang , Xuxiao Zong , Tao Yang
Faba bean is a global food legume crop, and it is essential to accurately and timely determine its plant height, above-ground biomass (fresh and dry weight) and yield for enhancing cultivation practices and planning the next planting season. Traditional ground sampling is a time-consuming and labor-intensive approach. However, the utilization of an unmanned aerial vehicle (UAV) as a high-throughput technique offers a promising alternative strategy for estimating crop phenotypic traits. In this study, a two-year experiment was conducted from 2020 to 2022, where UAV-based multimodal data were collected using red–green–blue, multispectral and thermal infrared sensors. The variables derived from these three sensors and their combinations were used to estimate the fresh weight, dry weight and yield of faba bean based on extreme gradient boosting (XGBoost), random forest, multiple linear regression and k-nearest neighbor algorithms. The following findings were obtained: (1) The use of the maximum percentile crop surface model resulted in the highest estimation accuracy for faba bean plant height. (2) Fusion data from multiple sensors increased the estimation accuracy of faba bean fresh weight, dry weight and yield, the coefficient of determination (R2) improved by 14.22%, 1.45%, and 18.76%, respectively, compared with the best estimation accuracy of a single sensor. (3) The XGBoost algorithm outperformed the other algorithms in estimating fresh weight, dry weight and yield of faba bean. These results demonstrate that multiple sensors and appropriate algorithms can be used to effectively estimate faba bean phenotypic traits and provide valuable insights for agricultural remote sensing research.
{"title":"High-throughput phenotypic traits estimation of faba bean based on machine learning and drone-based multimodal data","authors":"Yishan Ji , Zehao Liu , Rong Liu , Zhirui Wang , Xuxiao Zong , Tao Yang","doi":"10.1016/j.compag.2024.109584","DOIUrl":"10.1016/j.compag.2024.109584","url":null,"abstract":"<div><div>Faba bean is a global food legume crop, and it is essential to accurately and timely determine its plant height, above-ground biomass (fresh and dry weight) and yield for enhancing cultivation practices and planning the next planting season. Traditional ground sampling is a time-consuming and labor-intensive approach. However, the utilization of an unmanned aerial vehicle (UAV) as a high-throughput technique offers a promising alternative strategy for estimating crop phenotypic traits. In this study, a two-year experiment was conducted from 2020 to 2022, where UAV-based multimodal data were collected using red–green–blue, multispectral and thermal infrared sensors. The variables derived from these three sensors and their combinations were used to estimate the fresh weight, dry weight and yield of faba bean based on extreme gradient boosting (XGBoost), random forest, multiple linear regression and k-nearest neighbor algorithms. The following findings were obtained: (1) The use of the maximum percentile crop surface model resulted in the highest estimation accuracy for faba bean plant height. (2) Fusion data from multiple sensors increased the estimation accuracy of faba bean fresh weight, dry weight and yield, the coefficient of determination (<em>R</em><sup>2</sup>) improved by 14.22%, 1.45%, and 18.76%, respectively, compared with the best estimation accuracy of a single sensor. (3) The XGBoost algorithm outperformed the other algorithms in estimating fresh weight, dry weight and yield of faba bean. These results demonstrate that multiple sensors and appropriate algorithms can be used to effectively estimate faba bean phenotypic traits and provide valuable insights for agricultural remote sensing research.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109584"},"PeriodicalIF":7.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592562","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}
Pub Date : 2024-11-06DOI: 10.1016/j.compag.2024.109601
Nueraili Aierken , Bo Yang , Yongke Li , Pingan Jiang , Gang Pan , Shijian Li
Cotton is one of the world’s most economically significant crops. Evaluating and monitoring cotton crop growth play vital roles in precision agriculture. Unmanned aerial vehicle (UAV) based remote sensing, when integrated with machine learning technologies, exhibits considerable promise for crop growth management. Despite these technologies’ substantial impact on cotton production, there exists a scarcity of consolidated information regarding various methods used. This paper offers a comprehensive review and analysis focused on methods for monitoring and evaluating cotton growth using UAV-based imagery combined with machine learning techniques. We synthesize the existing research from the past decade within this context, particularly discussing data acquisition strategies, preprocessing methods necessary for handling UAV-acquired images effectively, and a range of machine learning models applied. This investigation offers a comprehensive outlook that could guide future research efforts towards more efficient and sustainable agricultural practices in cotton production, leveraging state-of-the-art technology.
{"title":"A review of unmanned aerial vehicle based remote sensing and machine learning for cotton crop growth monitoring","authors":"Nueraili Aierken , Bo Yang , Yongke Li , Pingan Jiang , Gang Pan , Shijian Li","doi":"10.1016/j.compag.2024.109601","DOIUrl":"10.1016/j.compag.2024.109601","url":null,"abstract":"<div><div>Cotton is one of the world’s most economically significant crops. Evaluating and monitoring cotton crop growth play vital roles in precision agriculture. Unmanned aerial vehicle (UAV) based remote sensing, when integrated with machine learning technologies, exhibits considerable promise for crop growth management. Despite these technologies’ substantial impact on cotton production, there exists a scarcity of consolidated information regarding various methods used. This paper offers a comprehensive review and analysis focused on methods for monitoring and evaluating cotton growth using UAV-based imagery combined with machine learning techniques. We synthesize the existing research from the past decade within this context, particularly discussing data acquisition strategies, preprocessing methods necessary for handling UAV-acquired images effectively, and a range of machine learning models applied. This investigation offers a comprehensive outlook that could guide future research efforts towards more efficient and sustainable agricultural practices in cotton production, leveraging state-of-the-art technology.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109601"},"PeriodicalIF":7.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592561","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}
Pub Date : 2024-11-06DOI: 10.1016/j.compag.2024.109622
Changjoo Lee , Simon Schätzle , Stefan Andreas Lang , Timo Oksanen
Achieving safe and reliable environmental perception is crucial for the success of highly automated or even autonomous agricultural machinery. However, developing such a system is challenging due to the inherent limitations of perception sensors. In certain conditions, these sensors may fail to capture accurate data, leading to erroneous perceptions of the environment and potentially compromising safety. Monitoring the functional insufficiencies of the measurement data is crucial for ensuring the safety and reliability of perception systems.
This article introduces ISO standards, which provide guidelines for ensuring functional safety in highly automated mobile machines and vehicles. It also proposes an Image Quality Safety Model (IQSM) for monitoring the safety of the intended functionality in perception systems. The IQSM estimates the confidence level with which a camera can safely perform a specific object detection task. If the confidence level falls below a predefined threshold, the IQSM can trigger actions, alert operators, and prevent potential safety hazards. The IQSM exhibits remarkable performance, achieving a validation accuracy of about 90%, demonstrating its ability to effectively distinguish the safety of the intended functionality under a variety of image quality conditions.
实现安全可靠的环境感知对于高度自动化甚至自主农业机械的成功至关重要。然而,由于感知传感器固有的局限性,开发这样的系统极具挑战性。在某些条件下,这些传感器可能无法捕捉到准确的数据,从而导致对环境的错误感知,并可能危及安全。监测测量数据的功能缺陷对于确保感知系统的安全性和可靠性至关重要。本文介绍了 ISO 标准,这些标准为确保高度自动化的移动机器和车辆的功能安全提供了指导。文章还提出了一种图像质量安全模型(IQSM),用于监控感知系统中预期功能的安全性。IQSM 可估算摄像头安全执行特定物体检测任务的置信度。如果置信度低于预定阈值,IQSM 就会触发行动,提醒操作人员并防止潜在的安全隐患。IQSM 性能卓越,验证准确率达到约 90%,证明了其在各种图像质量条件下有效区分预期功能安全性的能力。
{"title":"Image quality safety model for the safety of the intended functionality in highly automated agricultural machines","authors":"Changjoo Lee , Simon Schätzle , Stefan Andreas Lang , Timo Oksanen","doi":"10.1016/j.compag.2024.109622","DOIUrl":"10.1016/j.compag.2024.109622","url":null,"abstract":"<div><div>Achieving safe and reliable environmental perception is crucial for the success of highly automated or even autonomous agricultural machinery. However, developing such a system is challenging due to the inherent limitations of perception sensors. In certain conditions, these sensors may fail to capture accurate data, leading to erroneous perceptions of the environment and potentially compromising safety. Monitoring the functional insufficiencies of the measurement data is crucial for ensuring the safety and reliability of perception systems.</div><div>This article introduces ISO standards, which provide guidelines for ensuring functional safety in highly automated mobile machines and vehicles. It also proposes an Image Quality Safety Model (IQSM) for monitoring the safety of the intended functionality in perception systems. The IQSM estimates the confidence level with which a camera can safely perform a specific object detection task. If the confidence level falls below a predefined threshold, the IQSM can trigger actions, alert operators, and prevent potential safety hazards. The IQSM exhibits remarkable performance, achieving a validation accuracy of about 90%, demonstrating its ability to effectively distinguish the safety of the intended functionality under a variety of image quality conditions.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109622"},"PeriodicalIF":7.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592563","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}
Field-road trajectory classification is a crucial task for agricultural machinery behavior mode recognition, aiming to distinguish field operation mode and road driving mode automatically. However, the imbalanced distribution of agricultural machine trajectories brings challenges for the field-road trajectory classification task. Additionally, most existing field-road trajectory classification methods have certain shortcomings. For instance, they encounter difficulties in accurately representing the state of agricultural machinery movement using the current features. The data transformation process often leads to information loss, and the model’s generalization capabilities are limited. The performance of the models is constrained by each of these elements. To address these shortcomings, this paper introduces a general image classification model for agricultural machinery trajectory mode recognition named ATRNet. First, to address the issue of imbalanced field-road proportions in agricultural machinery trajectory data, a Conditional Tabular Generative Adversarial Network (CTGAN) is employed to generate quasi trajectories, balancing the distribution of positive and negative samples in the data. This step aims to eliminate biases during the model training process. Second, to accurately characterize the motion status of agricultural machinery, we propose a multiangle feature enhancement method to extract rich spatiotemporal features from trajectory data. Finally, different from conventional field-road trajectory classification models that primarily rely on spatial and temporal information for identifying trajectories, we present a lossless trajectory data representation paradigm. This paradigm maps each trajectory point into a “feature map” and uses an image classification model to capture latent feature representations of trajectory points for the recognition of different behavior modes of agricultural machinery. This paradigm can generalize image classification networks to the field-road trajectory classification task, providing a general vision model solution for agricultural machinery trajectory mode recognition. To validate the effectiveness of the ATRNet model, experiments were conducted on real corn and wheat harvester trajectory datasets. The results demonstrate that the proposed model achieves remarkable performance improvements over the state-of-the-art (SOTA) models. In the corn harvester trajectory dataset, ATRNet achieves an accuracy of 92.36% and an F1-score of 92.34%, surpassing existing SOTA models by 3.12% and 12.46%, respectively. Similarly, in the wheat harvester trajectory dataset, ATRNet achieves an accuracy of 92.36% and an F1-score of 92.33%, outperforming the existing optimal algorithm by 4.76% and 18.18%, respectively.
{"title":"A general image classification model for agricultural machinery trajectory mode recognition","authors":"Weixin Zhai , Zhi Xu , Jiawen Pan , Zhou Guo , Caicong Wu","doi":"10.1016/j.compag.2024.109629","DOIUrl":"10.1016/j.compag.2024.109629","url":null,"abstract":"<div><div>Field-road trajectory classification is a crucial task for agricultural machinery behavior mode recognition, aiming to distinguish field operation mode and road driving mode automatically. However, the imbalanced distribution of agricultural machine trajectories brings challenges for the field-road trajectory classification task. Additionally, most existing field-road trajectory classification methods have certain shortcomings. For instance, they encounter difficulties in accurately representing the state of agricultural machinery movement using the current features. The data transformation process often leads to information loss, and the model’s generalization capabilities are limited. The performance of the models is constrained by each of these elements. To address these shortcomings, this paper introduces a general image classification model for agricultural machinery trajectory mode recognition named ATRNet. First, to address the issue of imbalanced field-road proportions in agricultural machinery trajectory data, a Conditional Tabular Generative Adversarial Network (CTGAN) is employed to generate quasi trajectories, balancing the distribution of positive and negative samples in the data. This step aims to eliminate biases during the model training process. Second, to accurately characterize the motion status of agricultural machinery, we propose a multiangle feature enhancement method to extract rich spatiotemporal features from trajectory data. Finally, different from conventional field-road trajectory classification models that primarily rely on spatial and temporal information for identifying trajectories, we present a lossless trajectory data representation paradigm. This paradigm maps each trajectory point into a “feature map” and uses an image classification model to capture latent feature representations of trajectory points for the recognition of different behavior modes of agricultural machinery. This paradigm can generalize image classification networks to the field-road trajectory classification task, providing a general vision model solution for agricultural machinery trajectory mode recognition. To validate the effectiveness of the ATRNet model, experiments were conducted on real corn and wheat harvester trajectory datasets. The results demonstrate that the proposed model achieves remarkable performance improvements over the state-of-the-art (SOTA) models. In the corn harvester trajectory dataset, ATRNet achieves an accuracy of 92.36% and an F1-score of 92.34%, surpassing existing SOTA models by 3.12% and 12.46%, respectively. Similarly, in the wheat harvester trajectory dataset, ATRNet achieves an accuracy of 92.36% and an F1-score of 92.33%, outperforming the existing optimal algorithm by 4.76% and 18.18%, respectively.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109629"},"PeriodicalIF":7.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592565","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}
Pub Date : 2024-11-06DOI: 10.1016/j.compag.2024.109599
J. Chelotti , H. Atashi , M. Ferrero , C. Grelet , H. Soyeurt , L. Giovanini , H.L. Rufiner , N. Gengler
Regular monitoring of body condition score (BCS) changes during lactation is an essential management tool in dairy cattle; however, the current BCS measurements are often discontinuous and unevenly spaced in time. The imputation of BCS values is useful for two main reasons: i) achieving completeness of data is necessary to be able to relate BCS to other traits (e.g. milk yield and milk composition) that have been routinely recorded at different times and with a different frequency, and ii) having expected BCS values provides the possibility to trigger early warnings for animals with certain unexpected conditions. The contribution of this study was to propose and evaluate potential methods useful to smooth and impute device-based BCS values recorded during lactation in dairy cattle. In total, 26,207 BCS records were collected from 3,038 cows (9,199 and 14,462 BCS records on 1,546 Holstein and 1,211 Montbéliarde cows respectively, and the rest corresponded to other minority cattle breeds). Six methods were evaluated to predict BCS values: the traditional methods of test interval method (TIM), and multiple-trait procedure (MTP), and the machine learning (ML) methods of multi-layer perceptron (MLP), Elman network (Elman), long-short term memories (LSTM) and bi-directional LSTM (BiLSTM). The performance of each method was evaluated by a hold-out validation approach using statistics of the root mean squared error (RMSE) and Pearson correlation (r). TIM, MTP, MLP, and BiLSTM were assessed for the imputation of intermediate missing values, while MTP, Elman, and LSTM were evaluated for the forecasting of future BCS values. Regarding the machine learning methods, BiLSTM demonstrated the best performance for the intermediate value imputation task (RMSE = 0.295, r = 0.845), while LSTM demonstrated the best performance for the future value forecasting task (RMSE = 0.356, r = 0.751). Among the methods evaluated, MTP showed the best performance for imputation of intermediate missing values in terms of RMSE (0.288) and r (0.856). MTP also achieved the best performance for forecasting of future BCS values in terms of RMSE (0.348) and r (0.760). This study demonstrates the ability of MTP and machine learning methods to impute missing BCS data and provides a cost-effective solution for the application area.
{"title":"Assessing traditional and machine learning methods to smooth and impute device-based body condition score throughout the lactation in dairy cows","authors":"J. Chelotti , H. Atashi , M. Ferrero , C. Grelet , H. Soyeurt , L. Giovanini , H.L. Rufiner , N. Gengler","doi":"10.1016/j.compag.2024.109599","DOIUrl":"10.1016/j.compag.2024.109599","url":null,"abstract":"<div><div>Regular monitoring of body condition score (<strong>BCS</strong>) changes during lactation is an essential management tool in dairy cattle; however, the current BCS measurements are often discontinuous and unevenly spaced in time. The imputation of BCS values is useful for two main reasons: i) achieving completeness of data is necessary to be able to relate BCS to other traits (e.g. milk yield and milk composition) that have been routinely recorded at different times and with a different frequency, and ii) having expected BCS values provides the possibility to trigger early warnings for animals with certain unexpected conditions. The contribution of this study was to propose and evaluate potential methods useful to smooth and impute device-based BCS values recorded during lactation in dairy cattle. In total, 26,207 BCS records were collected from 3,038 cows (9,199 and 14,462 BCS records on 1,546 Holstein and 1,211 Montbéliarde cows respectively, and the rest corresponded to other minority cattle breeds). Six methods were evaluated to predict BCS values: the traditional methods of test interval method (<strong>TIM</strong>), and multiple-trait procedure (<strong>MTP</strong>), and the machine learning (<strong>ML</strong>) methods of multi-layer perceptron (<strong>MLP</strong>), Elman network (<strong>Elman</strong>), long-short term memories (<strong>LSTM)</strong> and bi-directional LSTM (<strong>BiLSTM</strong>). The performance of each method was evaluated by a hold-out validation approach using statistics of the root mean squared error (<strong>RMSE</strong>) and Pearson correlation (r). TIM, MTP, MLP, and BiLSTM were assessed for the imputation of intermediate missing values, while MTP, Elman, and LSTM were evaluated for the forecasting of future BCS values. Regarding the machine learning methods, BiLSTM demonstrated the best performance for the intermediate value imputation task (RMSE = 0.295, r = 0.845), while LSTM demonstrated the best performance for the future value forecasting task (RMSE = 0.356, r = 0.751). Among the methods evaluated, MTP showed the best performance for imputation of intermediate missing values in terms of RMSE (0.288) and r (0.856). MTP also achieved the best performance for forecasting of future BCS values in terms of RMSE (0.348) and r (0.760). This study demonstrates the ability of MTP and machine learning methods to impute missing BCS data and provides a cost-effective solution for the application area.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"227 ","pages":"Article 109599"},"PeriodicalIF":7.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592566","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}