首页 > 最新文献

Smart agricultural technology最新文献

英文 中文
WeedsSORT: A weed tracking-by-detection framework for laser weeding applications within precision agriculture
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-13 DOI: 10.1016/j.atech.2025.100883
Tao Jin, Kun Liang, Mengxuan Lu, Yingshuai Zhao, Yangrui Xu
In precision agriculture, the application of artificial intelligence and high-power laser technology for weed control offers significant efficiency and accuracy advantages. However, it still encounters numerous challenges in the detection and tracking of weed targets. In terms of object detection, the variability in the size and specifications of weeds can result in the missed detection of smaller weed targets. Regarding tracking prediction, the similarity in weed shapes may result in reduced pose estimation accuracy, and the random motion of cameras within laser weeding systems further increases the risk of tracking failures. To address these challenges, this study introduces a spatial attention mechanism to enhance weed detection accuracy. It employs optimized multi-feature layer extraction and optimal feature matching algorithms to derive motion estimation results. Ultimately, an adaptive extended Kalman filtering algorithm is integrated to establish a weed tracking algorithm that correlates temporal and spatial information, ultimately achieving rapid and precise detection and tracking of weeds in laser weeding scenarios. The detection accuracy of the optimized algorithm was tested on both publicly available datasets and self-collected detection datasets, achieving a mean Average Precision (mAP) of 97.29% and 85.83%, respectively. Furthermore, tracking performance was evaluated using the LettuceMOT dataset and the self-collected WeedsMOT dataset, demonstrating improvements in Higher-Order Tracking Accuracy (HOTA) accuracy of 12.01% and 8.75% when compared to the ByteTrack and DeepOCSORT algorithms. The experimental findings substantiate the efficacy of the proposed weed detection and tracking algorithm, offering a valuable reference for the progression of laser weeding technology within precision agriculture.
{"title":"WeedsSORT: A weed tracking-by-detection framework for laser weeding applications within precision agriculture","authors":"Tao Jin,&nbsp;Kun Liang,&nbsp;Mengxuan Lu,&nbsp;Yingshuai Zhao,&nbsp;Yangrui Xu","doi":"10.1016/j.atech.2025.100883","DOIUrl":"10.1016/j.atech.2025.100883","url":null,"abstract":"<div><div>In precision agriculture, the application of artificial intelligence and high-power laser technology for weed control offers significant efficiency and accuracy advantages. However, it still encounters numerous challenges in the detection and tracking of weed targets. In terms of object detection, the variability in the size and specifications of weeds can result in the missed detection of smaller weed targets. Regarding tracking prediction, the similarity in weed shapes may result in reduced pose estimation accuracy, and the random motion of cameras within laser weeding systems further increases the risk of tracking failures. To address these challenges, this study introduces a spatial attention mechanism to enhance weed detection accuracy. It employs optimized multi-feature layer extraction and optimal feature matching algorithms to derive motion estimation results. Ultimately, an adaptive extended Kalman filtering algorithm is integrated to establish a weed tracking algorithm that correlates temporal and spatial information, ultimately achieving rapid and precise detection and tracking of weeds in laser weeding scenarios. The detection accuracy of the optimized algorithm was tested on both publicly available datasets and self-collected detection datasets, achieving a mean Average Precision (mAP) of 97.29% and 85.83%, respectively. Furthermore, tracking performance was evaluated using the LettuceMOT dataset and the self-collected WeedsMOT dataset, demonstrating improvements in Higher-Order Tracking Accuracy (HOTA) accuracy of 12.01% and 8.75% when compared to the ByteTrack and DeepOCSORT algorithms. The experimental findings substantiate the efficacy of the proposed weed detection and tracking algorithm, offering a valuable reference for the progression of laser weeding technology within precision agriculture.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100883"},"PeriodicalIF":6.3,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Unmanned aerial systems (UAS)-based field high throughput phenotyping (HTP) as plant breeders’ toolbox: A comprehensive review
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-08 DOI: 10.1016/j.atech.2025.100888
Ittipon Khuimphukhieo , Jorge A. da Silva
It is projected that food demand will exceed its supply in 2050 due to global population growth if the production rate remains the same. Replacement of natural vegetation by cropland is unsustainable as it could cause global warming worse. Increasing the rate of genetic gain through artificial selection, also known as plant breeding, is a sustainable approach. Phenotyping, a process of measuring plant characteristics (traits), is unavoidable in plant breeding regardless of which methods (molecular or conventional) being used. Traditional phenotyping of a complex trait has been a bottleneck due to its labor-intensive and time-consuming nature. In recent years, there has been a massive scientific investigation on utilizing an unmanned aerial system (UAS) for agricultural application, as well as high throughput phenotyping (HTP) platform. Although there have been existing literature reviews on UAS-based HTP, a review discussing the pipeline of implementing this tool and in what situations or applications plant breeders could utilize it as a tool is still limited. Consequently, this paper overviews (1) a potential bottleneck in plant breeding pipeline, (2) necessary equipment and regular pipeline for implementing UAS-based HTP, (3) various plant phenotyping tasks that could be accomplished by using UAS-based HTP, including a trait-direct measurement, predictive breeding, application of UAS-based HTP as a marker and, identification of quantitative trait loci (QTLs), (4) contributions of UAS-based HTP on improving the rate of genetic gain, and (5) an outline of the future direction of plant breeding in the high throughput era alongside with artificial intelligence. This comprehensive review would be beneficial to plant breeders, especially those who are considering adopting this technology to their programs.
据预测,如果生产率保持不变,到 2050 年,由于全球人口增长,粮食将供不应求。用耕地取代天然植被是不可持续的,因为这会导致全球变暖加剧。通过人工选择(也称为植物育种)提高基因增殖率是一种可持续的方法。表型分析是测量植物特征(性状)的过程,在植物育种过程中,无论使用哪种方法(分子方法或传统方法),表型分析都是不可避免的。传统的复杂性状表型由于耗费大量人力和时间,一直是一个瓶颈。近年来,利用无人机系统(UAS)进行农业应用以及高通量表型(HTP)平台的科学研究方兴未艾。虽然已有关于基于无人机系统的高通量表型分析的文献综述,但讨论实施这一工具的管道以及植物育种人员在何种情况下或应用中可以利用这一工具的综述仍然有限。因此,本文概述了:(1)植物育种流程中的潜在瓶颈;(2)实施基于 UAS 的 HTP 所需的必要设备和常规流程;(3)利用基于 UAS 的 HTP 可以完成的各种植物表型任务,包括性状直接测量、预测性育种、(4) 基于 UAS 的 HTP 对提高遗传增益率的贡献,以及 (5) 概述高通量时代植物育种与人工智能的未来发展方向。这篇全面的综述将对植物育种者,尤其是那些正在考虑在其项目中采用这项技术的育种者大有裨益。
{"title":"Unmanned aerial systems (UAS)-based field high throughput phenotyping (HTP) as plant breeders’ toolbox: A comprehensive review","authors":"Ittipon Khuimphukhieo ,&nbsp;Jorge A. da Silva","doi":"10.1016/j.atech.2025.100888","DOIUrl":"10.1016/j.atech.2025.100888","url":null,"abstract":"<div><div>It is projected that food demand will exceed its supply in 2050 due to global population growth if the production rate remains the same. Replacement of natural vegetation by cropland is unsustainable as it could cause global warming worse. Increasing the rate of genetic gain through artificial selection, also known as plant breeding, is a sustainable approach. Phenotyping, a process of measuring plant characteristics (traits), is unavoidable in plant breeding regardless of which methods (molecular or conventional) being used. Traditional phenotyping of a complex trait has been a bottleneck due to its labor-intensive and time-consuming nature. In recent years, there has been a massive scientific investigation on utilizing an unmanned aerial system (UAS) for agricultural application, as well as high throughput phenotyping (HTP) platform. Although there have been existing literature reviews on UAS-based HTP, a review discussing the pipeline of implementing this tool and in what situations or applications plant breeders could utilize it as a tool is still limited. Consequently, this paper overviews (1) a potential bottleneck in plant breeding pipeline, (2) necessary equipment and regular pipeline for implementing UAS-based HTP, (3) various plant phenotyping tasks that could be accomplished by using UAS-based HTP, including a trait-direct measurement, predictive breeding, application of UAS-based HTP as a marker and, identification of quantitative trait loci (QTLs), (4) contributions of UAS-based HTP on improving the rate of genetic gain, and (5) an outline of the future direction of plant breeding in the high throughput era alongside with artificial intelligence. This comprehensive review would be beneficial to plant breeders, especially those who are considering adopting this technology to their programs.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100888"},"PeriodicalIF":6.3,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143591895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research progress of non-destructive testing techniques in moisture content determination
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-08 DOI: 10.1016/j.atech.2025.100878
Song Daihao , Wang Min , Li Yanjun , Xu Lei , Lou Zhichao
Accurate measurement of moisture content is crucial in various industries for improving product quality, ensuring safety, optimizing production processes, and protecting the environment. However, traditional moisture measuring methods often damage the sample and are complex and time-consuming, making it challenging to meet the high demands of modern industries for efficiency, precision, and real-time monitoring. Non-destructive testing (NDT), an advanced technology, can rapidly and accurately assess the characteristics and conditions of materials without damaging their structure, morphology, chemical components, and physical properties, making it suitable for moisture content testing. This paper provides an overview of traditional drying methods for moisture content detection and a comprehensive review of the theoretical basis of electrical resistive, capacitive, and microwave methods, including their applicable detection materials. Moreover, we analyze the advantages and disadvantages of each method. Additionally, the paper highlights that combining non-destructive moisture content detection with machine learning can significantly improve both detection efficiency and accuracy. Finally, we address the challenges associated with non-destructive moisture content detection and explore potential future developments to support the further advancement and adoption of NDT technologies.
{"title":"Research progress of non-destructive testing techniques in moisture content determination","authors":"Song Daihao ,&nbsp;Wang Min ,&nbsp;Li Yanjun ,&nbsp;Xu Lei ,&nbsp;Lou Zhichao","doi":"10.1016/j.atech.2025.100878","DOIUrl":"10.1016/j.atech.2025.100878","url":null,"abstract":"<div><div>Accurate measurement of moisture content is crucial in various industries for improving product quality, ensuring safety, optimizing production processes, and protecting the environment. However, traditional moisture measuring methods often damage the sample and are complex and time-consuming, making it challenging to meet the high demands of modern industries for efficiency, precision, and real-time monitoring. Non-destructive testing (NDT), an advanced technology, can rapidly and accurately assess the characteristics and conditions of materials without damaging their structure, morphology, chemical components, and physical properties, making it suitable for moisture content testing. This paper provides an overview of traditional drying methods for moisture content detection and a comprehensive review of the theoretical basis of electrical resistive, capacitive, and microwave methods, including their applicable detection materials. Moreover, we analyze the advantages and disadvantages of each method. Additionally, the paper highlights that combining non-destructive moisture content detection with machine learning can significantly improve both detection efficiency and accuracy. Finally, we address the challenges associated with non-destructive moisture content detection and explore potential future developments to support the further advancement and adoption of NDT technologies.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100878"},"PeriodicalIF":6.3,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A non-linear dynamic model for agricultural vehicles constructed in digital space
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-08 DOI: 10.1016/j.atech.2025.100891
Yue Yu , Yong-joo Kim , Noboru Noguchi
In response to the shortage of agricultural labor due to an aging population, the concept of "smart agriculture" has emerged, which attaches great importance to the accurate modeling of real agricultural information in digital space, to realize higher-level intelligent management and control. As an important smart agricultural technology, accurate simulation of agricultural off-road vehicles in digital space can help enhance agricultural productivity, such as optimizing farming task schedule. To achieve this smart agriculture technology, it is necessary to construct high-precision agricultural vehicle models suitable for various agricultural environments in digital space. However, constructing highly precise, realistically performing dynamic models for agricultural vehicles in digital space remains a challenge. The performance of simple kinematic models and traditional linear dynamic models of agricultural vehicles is very limited: these models are only accurate under small side slip conditions, but not suitable for environments that would cause large side slip of agricultural vehicles, such as wet or soft soil. To solve this problem, we here propose a non-linear dynamic model for agricultural vehicles in digital space. First, we combine a simplified non-linear tire model and side slip angle estimation method to make a lateral force-estimation method. We then use the lateral force estimation and the Unity physics engine to construct a non-linear dynamic model for agricultural vehicles in digital space. The validation tests of both digital space and real-world experiments prove that: (1) The proposed model can accurately simulate the status of real tractors even with a simplified set of parameters. (2) The proposed non-linear model has a wider range of environmental applicability than that of traditional linear model, especially for those environments that may cause large side slip. (3) The proposed non-linear model has strong practicality and can cope with the changing agricultural environments by simply tuning the model parameters.
{"title":"A non-linear dynamic model for agricultural vehicles constructed in digital space","authors":"Yue Yu ,&nbsp;Yong-joo Kim ,&nbsp;Noboru Noguchi","doi":"10.1016/j.atech.2025.100891","DOIUrl":"10.1016/j.atech.2025.100891","url":null,"abstract":"<div><div>In response to the shortage of agricultural labor due to an aging population, the concept of \"smart agriculture\" has emerged, which attaches great importance to the accurate modeling of real agricultural information in digital space, to realize higher-level intelligent management and control. As an important smart agricultural technology, accurate simulation of agricultural off-road vehicles in digital space can help enhance agricultural productivity, such as optimizing farming task schedule. To achieve this smart agriculture technology, it is necessary to construct high-precision agricultural vehicle models suitable for various agricultural environments in digital space. However, constructing highly precise, realistically performing dynamic models for agricultural vehicles in digital space remains a challenge. The performance of simple kinematic models and traditional linear dynamic models of agricultural vehicles is very limited: these models are only accurate under small side slip conditions, but not suitable for environments that would cause large side slip of agricultural vehicles, such as wet or soft soil. To solve this problem, we here propose a non-linear dynamic model for agricultural vehicles in digital space. First, we combine a simplified non-linear tire model and side slip angle estimation method to make a lateral force-estimation method. We then use the lateral force estimation and the Unity physics engine to construct a non-linear dynamic model for agricultural vehicles in digital space. The validation tests of both digital space and real-world experiments prove that: (1) The proposed model can accurately simulate the status of real tractors even with a simplified set of parameters. (2) The proposed non-linear model has a wider range of environmental applicability than that of traditional linear model, especially for those environments that may cause large side slip. (3) The proposed non-linear model has strong practicality and can cope with the changing agricultural environments by simply tuning the model parameters.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100891"},"PeriodicalIF":6.3,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Dynamic growth tomato inflorescence modeling with elastic mechanics data
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-07 DOI: 10.1016/j.atech.2025.100884
Siyao Liu , Subo Tian , Zhen Zhang , Lingfei Liu , Tianlai Li
Current crop modeling methods can not simulate crop dynamic growth containing physical characteristics data, while the study of physical production management such as pollination of tomato requires the elastic force and dynamic growth process analysis of the inflorescence. Therefore, this study proposes a tomato inflorescence modeling method to meet the modeling demands of combining the growth process and elastic mechanics data. With the model promoted in this study, after measuring the size of tomato inflorescence key structures, the growth progress of inflorescence can be predicted, and elastic mechanics data of inflorescence at various sizes can be obtained. Firstly, based on plant topology theory, tomato inflorescence was divided into structural skeleton and tomato flower (or fruit). Where the structural skeleton was divided into four parts, that are peduncle, primary flower stalk, secondary flower stalk, and pedicel. Then, the diameters, lengths, growth coefficients and elastic coefficients of tomato inflorescence key structures were measured at different growth stages, the principle between key structures size and the elastic coefficient was established. Finally, a software interface is designed based on the MFC framework with the OpenGL library, which can generate dynamically growing inflorescence model, which contain the elastic mechanics data of inflorescence model. The experimental results show that the average prediction error of inflorescence size in the established model is 8.35 %, and the average estimation error of elasticity coefficient is 7.41 %. The study result lays the foundation for the establishment of tomato inflorescence modeling method, which can help to achieve the study of tomato physical production management. The modeling method proposed in this study also provides new ideas and methods for plant modeling that simultaneously simulate crop dynamic growth and contain physical characteristics data.
{"title":"Dynamic growth tomato inflorescence modeling with elastic mechanics data","authors":"Siyao Liu ,&nbsp;Subo Tian ,&nbsp;Zhen Zhang ,&nbsp;Lingfei Liu ,&nbsp;Tianlai Li","doi":"10.1016/j.atech.2025.100884","DOIUrl":"10.1016/j.atech.2025.100884","url":null,"abstract":"<div><div>Current crop modeling methods can not simulate crop dynamic growth containing physical characteristics data, while the study of physical production management such as pollination of tomato requires the elastic force and dynamic growth process analysis of the inflorescence. Therefore, this study proposes a tomato inflorescence modeling method to meet the modeling demands of combining the growth process and elastic mechanics data. With the model promoted in this study, after measuring the size of tomato inflorescence key structures, the growth progress of inflorescence can be predicted, and elastic mechanics data of inflorescence at various sizes can be obtained. Firstly, based on plant topology theory, tomato inflorescence was divided into structural skeleton and tomato flower (or fruit). Where the structural skeleton was divided into four parts, that are peduncle, primary flower stalk, secondary flower stalk, and pedicel. Then, the diameters, lengths, growth coefficients and elastic coefficients of tomato inflorescence key structures were measured at different growth stages, the principle between key structures size and the elastic coefficient was established. Finally, a software interface is designed based on the MFC framework with the OpenGL library, which can generate dynamically growing inflorescence model, which contain the elastic mechanics data of inflorescence model. The experimental results show that the average prediction error of inflorescence size in the established model is 8.35 %, and the average estimation error of elasticity coefficient is 7.41 %. The study result lays the foundation for the establishment of tomato inflorescence modeling method, which can help to achieve the study of tomato physical production management. The modeling method proposed in this study also provides new ideas and methods for plant modeling that simultaneously simulate crop dynamic growth and contain physical characteristics data.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100884"},"PeriodicalIF":6.3,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A novel application with explainable machine learning (SHAP and LIME) to predict soil N, P, and K nutrient content in cabbage cultivation
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-06 DOI: 10.1016/j.atech.2025.100879
Thilina Abekoon , Hirushan Sajindra , Namal Rathnayake , Imesh U. Ekanayake , Anuradha Jayakody , Upaka Rathnayake
Cabbage (Brassica oleracea var. capitata) is commonly cultivated in high altitudes and features dense, tightly packed leaves. The Green Coronet variety is well-known for its robust growth and culinary versatility. Maximizing yield is crucial for food sustainability. It is essential to predict the soil's major nutrients (nitrogen, phosphorus, and potassium) to maximize the yield. Artificial intelligence is widely used for non-linear predictions with explainability. This research assessed the predictive capabilities of soil nitrogen, phosphorus, and potassium levels with explainable machine learning methods over an 85-day cabbage growth period. Experiments were conducted on cabbage plants grown in central hills of Sri Lanka. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used to clarify the model's predictions. SHAP analysis showed that high feature values of the number of days and plant average leaf area negatively impacted for nutrient predictions, while high feature values of leaf count and plant height had a positive effect on the nutrient predictions. To validate the results, 15 greenhouse-grown cabbage plants at various growth stages were selected. The nitrogen, phosphorus, and potassium levels were measured and compared with the predicted values. These insights help refine predictive models and optimize agricultural practices. A user-friendly application was developed to improve the accessibility and interpretation of predictions. This tool is a user-friendly platform for end-users, enabling effective use of the model's predictive capabilities.
{"title":"A novel application with explainable machine learning (SHAP and LIME) to predict soil N, P, and K nutrient content in cabbage cultivation","authors":"Thilina Abekoon ,&nbsp;Hirushan Sajindra ,&nbsp;Namal Rathnayake ,&nbsp;Imesh U. Ekanayake ,&nbsp;Anuradha Jayakody ,&nbsp;Upaka Rathnayake","doi":"10.1016/j.atech.2025.100879","DOIUrl":"10.1016/j.atech.2025.100879","url":null,"abstract":"<div><div>Cabbage (<em>Brassica oleracea</em> var. capitata) is commonly cultivated in high altitudes and features dense, tightly packed leaves. The Green Coronet variety is well-known for its robust growth and culinary versatility. Maximizing yield is crucial for food sustainability. It is essential to predict the soil's major nutrients (nitrogen, phosphorus, and potassium) to maximize the yield. Artificial intelligence is widely used for non-linear predictions with explainability. This research assessed the predictive capabilities of soil nitrogen, phosphorus, and potassium levels with explainable machine learning methods over an 85-day cabbage growth period. Experiments were conducted on cabbage plants grown in central hills of Sri Lanka. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used to clarify the model's predictions. SHAP analysis showed that high feature values of the number of days and plant average leaf area negatively impacted for nutrient predictions, while high feature values of leaf count and plant height had a positive effect on the nutrient predictions. To validate the results, 15 greenhouse-grown cabbage plants at various growth stages were selected. The nitrogen, phosphorus, and potassium levels were measured and compared with the predicted values. These insights help refine predictive models and optimize agricultural practices. A user-friendly application was developed to improve the accessibility and interpretation of predictions. This tool is a user-friendly platform for end-users, enabling effective use of the model's predictive capabilities.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100879"},"PeriodicalIF":6.3,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
YSD-BPTrack: A multi-object tracking framework for calves in occluded environments
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-06 DOI: 10.1016/j.atech.2025.100876
Wangli Hao, Chao Ren, Yulong Fan, Meng Han, Fuzhong Li
The accurate tracking of individual calves is essential for health monitoring. However, existing multi tracking frameworks often encounter frequent ID abnormal switching issues during occlusion. To address these challenges, we propose a novel multi-object tracking framework named YSD-BPTrack for calves in occluded environments on cattle farms in this paper. This framework mainly consists of two stages: detection and tracking. Concerning the detection phase, the DCNv4 is integrated into the YOLOv8s model to capture spatial deformation features caused by occlusion, thereby enhancing detection performance under occlusion. Additionally, the Star operation of StarNet is also applied to the model to achieve excellent detection performance with lower computational costs. Concerning the tracking stage, we first propose an innovative rematching algorithm (Rematching module) and a new trajectory removal strategy (Trajectory removal module). The Rematching module performs rematching with detection boxes utilizing extended trajectory prediction boxes in cases of occlusion, resulting in a reduced probability of ID switch errors. Moreover, the Trajectory Removal module dynamically adjusts the removal time for lost matching trajectories, which decreases the likelihood of trajectories being mistakenly removed. Specifically, our proposed novel framework achieves a HOTA (Higher Order Tracking Accuracy) of 91.6%, surpassing other frameworks in both track accuracy and efficiency. Experimental results also validate the superiority of the YSD-BPTrack, with HOTA increasing by 17.6%, MOTA (Multiple Object Tracking Accuracy) by 13.9%, MOTP (Multiple Object Tracking Precision) by 1.8%, IDF1 (Identification F1 Score) by 15.4%, and reducing parameters by 49.1%, IDSw (Identification Switches) by 88.9%, and computational overhead by 39.2% compared to the other frameworks. Overall, the proposed multi-object tracking framework has great potential to revolutionize the tracking of calves.
{"title":"YSD-BPTrack: A multi-object tracking framework for calves in occluded environments","authors":"Wangli Hao,&nbsp;Chao Ren,&nbsp;Yulong Fan,&nbsp;Meng Han,&nbsp;Fuzhong Li","doi":"10.1016/j.atech.2025.100876","DOIUrl":"10.1016/j.atech.2025.100876","url":null,"abstract":"<div><div>The accurate tracking of individual calves is essential for health monitoring. However, existing multi tracking frameworks often encounter frequent ID abnormal switching issues during occlusion. To address these challenges, we propose a novel multi-object tracking framework named YSD-BPTrack for calves in occluded environments on cattle farms in this paper. This framework mainly consists of two stages: detection and tracking. Concerning the detection phase, the DCNv4 is integrated into the YOLOv8s model to capture spatial deformation features caused by occlusion, thereby enhancing detection performance under occlusion. Additionally, the Star operation of StarNet is also applied to the model to achieve excellent detection performance with lower computational costs. Concerning the tracking stage, we first propose an innovative rematching algorithm (Rematching module) and a new trajectory removal strategy (Trajectory removal module). The Rematching module performs rematching with detection boxes utilizing extended trajectory prediction boxes in cases of occlusion, resulting in a reduced probability of ID switch errors. Moreover, the Trajectory Removal module dynamically adjusts the removal time for lost matching trajectories, which decreases the likelihood of trajectories being mistakenly removed. Specifically, our proposed novel framework achieves a HOTA (Higher Order Tracking Accuracy) of 91.6%, surpassing other frameworks in both track accuracy and efficiency. Experimental results also validate the superiority of the YSD-BPTrack, with HOTA increasing by 17.6%, MOTA (Multiple Object Tracking Accuracy) by 13.9%, MOTP (Multiple Object Tracking Precision) by 1.8%, <span><math><mi>ID</mi><msub><mrow><mi>F</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span> (Identification <span><math><msub><mrow><mi>F</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span> Score) by 15.4%, and reducing parameters by 49.1%, IDSw (Identification Switches) by 88.9%, and computational overhead by 39.2% compared to the other frameworks. Overall, the proposed multi-object tracking framework has great potential to revolutionize the tracking of calves.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100876"},"PeriodicalIF":6.3,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Analysis and prediction of backfat thickness in gestating sows using machine learning algorithms
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-05 DOI: 10.1016/j.atech.2025.100875
Xuewu Peng , Yaxin Song , Yuanfei Zhou , Hongkui Wei , Siwen Jiang , Fukang Wei , Xinran Li , Jian Peng
Sow backfat (BF) thickness is a key indicator for predicting the nutrient requirements and influencing on reproductive performance of gestating sows. The purpose of this study was to determine feature importance for healthy piglets, define the optimal BF at farrowing and change trend of BF during gestation, as well as to establish the prediction models of BF in gestating sows using 10 machine learning (ML) models. A database with 64,298 observations including 3 categorical and 18 numerical features was used for data analysis and modeling. Compared to other features, BF at farrowing was the most important feature for healthy piglets. The optimal BF at farrowing of parity 1, 2, and ≥3 was 18 mm, 16 mm, and 16 mm, respectively, and the early to middle stage of gestation was the best period for body condition restoration. The eXtreme gradient boosting regression (XGBR) and gradient boosting regression (GBR) exhibited best prediction performance with lowest RMSE (30d, 60d, 90d and farrowing of gestation were 1.17, 1.09, 1.01 and 0.81 mm, respectively) and MAPE (30d, 60d, 90d and farrowing of gestation were 5.57 %, 4.93 %, 4.44 % and 3.54 %, respectively), showing best accuracy and stability among the 10 ML models. The analysis and prediction of BF during gestation based on ML methods provide technical support for accurately predicting nutrient requirements and formulating precise feeding strategy of gestating sows.
{"title":"Analysis and prediction of backfat thickness in gestating sows using machine learning algorithms","authors":"Xuewu Peng ,&nbsp;Yaxin Song ,&nbsp;Yuanfei Zhou ,&nbsp;Hongkui Wei ,&nbsp;Siwen Jiang ,&nbsp;Fukang Wei ,&nbsp;Xinran Li ,&nbsp;Jian Peng","doi":"10.1016/j.atech.2025.100875","DOIUrl":"10.1016/j.atech.2025.100875","url":null,"abstract":"<div><div>Sow backfat (BF) thickness is a key indicator for predicting the nutrient requirements and influencing on reproductive performance of gestating sows. The purpose of this study was to determine feature importance for healthy piglets, define the optimal BF at farrowing and change trend of BF during gestation, as well as to establish the prediction models of BF in gestating sows using 10 machine learning (ML) models. A database with 64,298 observations including 3 categorical and 18 numerical features was used for data analysis and modeling. Compared to other features, BF at farrowing was the most important feature for healthy piglets. The optimal BF at farrowing of parity 1, 2, and ≥3 was 18 mm, 16 mm, and 16 mm, respectively, and the early to middle stage of gestation was the best period for body condition restoration. The eXtreme gradient boosting regression (XGBR) and gradient boosting regression (GBR) exhibited best prediction performance with lowest RMSE (30d, 60d, 90d and farrowing of gestation were 1.17, 1.09, 1.01 and 0.81 mm, respectively) and MAPE (30d, 60d, 90d and farrowing of gestation were 5.57 %, 4.93 %, 4.44 % and 3.54 %, respectively), showing best accuracy and stability among the 10 ML models. The analysis and prediction of BF during gestation based on ML methods provide technical support for accurately predicting nutrient requirements and formulating precise feeding strategy of gestating sows.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100875"},"PeriodicalIF":6.3,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143591987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Integrating thermal infrared and RGB imaging for early detection of water stress in lettuces with comparative analysis of IoT sensors
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-05 DOI: 10.1016/j.atech.2025.100881
Georgios Fevgas , Thomas Lagkas , Petros Papadopoulos , Panagiotis Sarigiannidis , Vasileios Argyriou
Early water stress detection is important for water use yield and sustainability. Traditional methods using the Internet of Things (IoT), such as soil moisture sensors, usually do not provide timely alerts, causing inefficient water use and, in some cases, crop damage. This research presents an innovative early water stress detection method in lettuce plants using Thermal Infrared (TIR) and RGB images in a controlled lab setting. The proposed method integrates advanced image processing techniques, including background elimination via Hue-Saturation-Value (HSV) thresholds, wavelet denoising for thermal image enhancement, RGB-TIR fusion using Principal Component Analysis (PCA), and Gaussian Mixture Model (GMM) clustering to segment stress regions. The leaves stressed areas annotated in the RGB image through yellow pseudo-coloring. This approach is predicated on the fact that when stomata close, transpiration decreases, which causes an increase in the temperature of the affected area. Experimental results reveal that this new approach can detect water stress up to 84 h earlier than conventional soil humidity sensors. Also, a comparative analysis was conducted where key components of the proposed hybrid framework were omitted. The results show inconsistent and inaccurate stress detection when excluding wavelet denoising and PCA fusion. A comparative analysis of image processing performed on a single-board computer (SBC) and through cloud computing over 5 G showed that SBC was 8.27% faster than cloud computing over a 5 G connection. The proposed method offers a more timely and accurate identification of water stress and promises significant benefits in improving crop yield and reducing water usage in indoor farming.
{"title":"Integrating thermal infrared and RGB imaging for early detection of water stress in lettuces with comparative analysis of IoT sensors","authors":"Georgios Fevgas ,&nbsp;Thomas Lagkas ,&nbsp;Petros Papadopoulos ,&nbsp;Panagiotis Sarigiannidis ,&nbsp;Vasileios Argyriou","doi":"10.1016/j.atech.2025.100881","DOIUrl":"10.1016/j.atech.2025.100881","url":null,"abstract":"<div><div>Early water stress detection is important for water use yield and sustainability. Traditional methods using the Internet of Things (IoT), such as soil moisture sensors, usually do not provide timely alerts, causing inefficient water use and, in some cases, crop damage. This research presents an innovative early water stress detection method in lettuce plants using Thermal Infrared (TIR) and RGB images in a controlled lab setting. The proposed method integrates advanced image processing techniques, including background elimination via Hue-Saturation-Value (HSV) thresholds, wavelet denoising for thermal image enhancement, RGB-TIR fusion using Principal Component Analysis (PCA), and Gaussian Mixture Model (GMM) clustering to segment stress regions. The leaves stressed areas annotated in the RGB image through yellow pseudo-coloring. This approach is predicated on the fact that when stomata close, transpiration decreases, which causes an increase in the temperature of the affected area. Experimental results reveal that this new approach can detect water stress up to 84 h earlier than conventional soil humidity sensors. Also, a comparative analysis was conducted where key components of the proposed hybrid framework were omitted. The results show inconsistent and inaccurate stress detection when excluding wavelet denoising and PCA fusion. A comparative analysis of image processing performed on a single-board computer (SBC) and through cloud computing over 5 G showed that SBC was 8.27% faster than cloud computing over a 5 G connection. The proposed method offers a more timely and accurate identification of water stress and promises significant benefits in improving crop yield and reducing water usage in indoor farming.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100881"},"PeriodicalIF":6.3,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Applications of remote sensing for crop residue cover mapping
IF 6.3 Q1 AGRICULTURAL ENGINEERING Pub Date : 2025-03-05 DOI: 10.1016/j.atech.2025.100880
Lilian Yang , Bing Lu , Margaret Schmidt , Sowmya Natesan , David McCaffrey
Crop residue is critical for the health of soils and crops as it can maintain soil moisture, reduce soil erosion, support soil nutrient cycling, and increase soil carbon sequestration. Monitoring crop residue cover (CRC) is thus essential for understanding the distribution and amount of crop residues in the field and for developing corresponding management strategies. Remote sensing is a powerful geospatial technique that enables the collection of images covering large areas repeatedly, which can contribute greatly to CRC mapping. This paper reviews the use of remote sensing in estimating CRC, focusing on different remote sensing platforms (e.g., satellites and drones), sensors (e.g., multispectral, hyperspectral, non-optical) and analytical methods (e.g., spectral unmixing, image classification). A total of 101 studies were selected based on their relevance to the scope of this review. The review found that while remote sensing technologies have shown great potential in accurately monitoring CRC, challenges remain in data integration, sensor selection, and computational demands, pointing to the need for ongoing research to optimize crop residue monitoring. This review is expected to bring more insights to agricultural researchers and practitioners and promote developing effective techniques for CRC mapping and management.
{"title":"Applications of remote sensing for crop residue cover mapping","authors":"Lilian Yang ,&nbsp;Bing Lu ,&nbsp;Margaret Schmidt ,&nbsp;Sowmya Natesan ,&nbsp;David McCaffrey","doi":"10.1016/j.atech.2025.100880","DOIUrl":"10.1016/j.atech.2025.100880","url":null,"abstract":"<div><div>Crop residue is critical for the health of soils and crops as it can maintain soil moisture, reduce soil erosion, support soil nutrient cycling, and increase soil carbon sequestration. Monitoring crop residue cover (CRC) is thus essential for understanding the distribution and amount of crop residues in the field and for developing corresponding management strategies. Remote sensing is a powerful geospatial technique that enables the collection of images covering large areas repeatedly, which can contribute greatly to CRC mapping. This paper reviews the use of remote sensing in estimating CRC, focusing on different remote sensing platforms (e.g., satellites and drones), sensors (e.g., multispectral, hyperspectral, non-optical) and analytical methods (e.g., spectral unmixing, image classification). A total of 101 studies were selected based on their relevance to the scope of this review. The review found that while remote sensing technologies have shown great potential in accurately monitoring CRC, challenges remain in data integration, sensor selection, and computational demands, pointing to the need for ongoing research to optimize crop residue monitoring. This review is expected to bring more insights to agricultural researchers and practitioners and promote developing effective techniques for CRC mapping and management.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100880"},"PeriodicalIF":6.3,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Smart agricultural technology
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1