Artificial Intelligence in Agriculture最新文献_第6页

Technical study on the efficiency and models of weed control methods using unmanned ground vehicles: A review 无人驾驶地面车辆除草效率与模型技术研究综述

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-05-28 DOI: 10.1016/j.aiia.2025.05.003

Evans K. Wiafe, Kelvin Betitame, Billy G. Ram, Xin Sun

As precision agriculture evolves, unmanned ground vehicles (UGVs) have become an essential tool for improving weed management techniques, offering automated and targeted methods that obviously reduce the reliance on manual labor and blanket herbicide applications. Several papers on UGV-based weed control methods have been published in recent years, yet there is no explicit attempt to systematically study these papers to discuss these weed control methods, UGVs adopted, and their key components, and how they impact the environment and economy. Therefore, the objective of this study was to present a systematic review that involves the efficiency and types of weed control methods deployed in UGVs, including mechanical weeding, targeted herbicide application, thermal/flaming weeding, and laser weeding in the last 2 decades. For this purpose, a thorough literature review was conducted, analyzing 68 relevant articles on weed control methods for UGVs. The study found that the research focus on using UGVs in mechanical weeding has been more dominant, followed by target or precision spraying/ chemical weeding, with hybrid weeding systems quickly emerging. The effectiveness of UGVs for weed control is hinged on the accuracy of their navigation and weed detection technologies, which are influenced heavily by environmental conditions, including lighting, weather, uneven terrain, and weed and crop density. Also, there is a shift from using traditional machine learning (ML) algorithms to deep learning neural networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), for weed detection algorithm development due to their potential to work in complex environments. Finally, trials of most UGVs have limited documentation or lack extensive trials under various conditions, such as varying soil types, crop fields, topography, field geometry, and annual weather conditions. This review paper serves as an in-depth update on UGVs in weed management for farmers, researchers, robotic technology industry players, and AI enthusiasts, helping to further foster collaborative efforts to develop new ideas and advance this revolutionary technique in modern agriculture.

随着精准农业的发展，无人驾驶地面车辆（ugv）已成为改善杂草管理技术的重要工具，提供自动化和有针对性的方法，明显减少了对人工劳动和地域性除草剂应用的依赖。近年来，关于基于ugv的杂草控制方法的论文已经发表了一些，但没有明确的尝试系统地研究这些论文，讨论这些杂草控制方法，采用的ugv，及其关键组成部分，以及它们对环境和经济的影响。因此，本研究的目的是对过去20年来ugv中使用的杂草控制方法的效率和类型进行系统回顾，包括机械除草、靶向除草剂施用、热/火焰除草和激光除草。为此，我们进行了全面的文献综述，分析了68篇关于ugv杂草控制方法的相关文章。研究发现，在机械除草中使用ugv的研究已经占据主导地位，其次是目标或精确喷洒/化学除草，混合除草系统迅速出现。ugv的杂草控制效果取决于其导航和杂草检测技术的准确性，而这些技术受环境条件的影响很大，包括光照、天气、不平坦地形、杂草和作物密度。此外，由于杂草检测算法具有在复杂环境中工作的潜力，因此从使用传统机器学习（ML）算法转向使用深度学习神经网络，包括卷积神经网络（cnn）和循环神经网络（rnn）。最后，大多数ugv的试验文件有限，或者缺乏在各种条件下的广泛试验，例如不同的土壤类型、作物田地、地形、田地几何形状和年度天气条件。这篇综述论文为农民、研究人员、机器人技术行业参与者和人工智能爱好者提供了ugv在杂草管理方面的深入更新，有助于进一步促进合作，开发新思路，推进现代农业中这一革命性技术的发展。

{"title":"Technical study on the efficiency and models of weed control methods using unmanned ground vehicles: A review","authors":"Evans K. Wiafe, Kelvin Betitame, Billy G. Ram, Xin Sun","doi":"10.1016/j.aiia.2025.05.003","DOIUrl":"10.1016/j.aiia.2025.05.003","url":null,"abstract":"<div><div>As precision agriculture evolves, unmanned ground vehicles (UGVs) have become an essential tool for improving weed management techniques, offering automated and targeted methods that obviously reduce the reliance on manual labor and blanket herbicide applications. Several papers on UGV-based weed control methods have been published in recent years, yet there is no explicit attempt to systematically study these papers to discuss these weed control methods, UGVs adopted, and their key components, and how they impact the environment and economy. Therefore, the objective of this study was to present a systematic review that involves the efficiency and types of weed control methods deployed in UGVs, including mechanical weeding, targeted herbicide application, thermal/flaming weeding, and laser weeding in the last 2 decades. For this purpose, a thorough literature review was conducted, analyzing 68 relevant articles on weed control methods for UGVs. The study found that the research focus on using UGVs in mechanical weeding has been more dominant, followed by target or precision spraying/ chemical weeding, with hybrid weeding systems quickly emerging. The effectiveness of UGVs for weed control is hinged on the accuracy of their navigation and weed detection technologies, which are influenced heavily by environmental conditions, including lighting, weather, uneven terrain, and weed and crop density. Also, there is a shift from using traditional machine learning (ML) algorithms to deep learning neural networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), for weed detection algorithm development due to their potential to work in complex environments. Finally, trials of most UGVs have limited documentation or lack extensive trials under various conditions, such as varying soil types, crop fields, topography, field geometry, and annual weather conditions. This review paper serves as an in-depth update on UGVs in weed management for farmers, researchers, robotic technology industry players, and AI enthusiasts, helping to further foster collaborative efforts to develop new ideas and advance this revolutionary technique in modern agriculture.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 622-641"},"PeriodicalIF":8.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Picking point localization method based on semantic reasoning for complex picking scenarios in vineyards 基于语义推理的葡萄园复杂采摘场景采摘点定位方法

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-05-26 DOI: 10.1016/j.aiia.2025.05.004

Xuemin Lin , Jinhai Wang , Jinshuan Wang , Huiling Wei , Mingyou Chen , Lufeng Luo

In the complex orchard environment, precise picking point localization is crucial for the automation of fruit picking robots. However, existing methods are prone to positioning errors when dealing with complex scenarios such as short peduncles, partial occlusion, or complete misidentification, which can affect the actual work efficiency of the fruit picking robot. This study proposes an enhanced picking point localization method based on semantic reasoning for complex picking scenarios in vineyard. It innovatively designs three modules: the semantic reasoning module (SRM), the ROI threshold adjustment strategy (RTAS), and the picking point location optimization module (PPOM). The SRM is applied to handle the scenarios of grape peduncles being obstructed by obstacles, partial misidentification of peduncles, and complete misidentification of peduncles. The RTAS addresses the issue of low and short peduncles during the picking process. Finally, the PPOM optimizes the final position of the picking point, allowing the robotic arm to perform the picking operation with greater flexibility. Experimental results show that SegFormer achieves an mIoU (mean Intersection over Union) of 84.54 %, with B_IoU and P_IoU reaching 73.90 % and 75.63 %, respectively. Additionally, the success rate of the improved fruit picking point localization algorithm reached 94.96 %, surpassing the baseline algorithm by 8.12 %. The algorithm's average processing time is 0.5428 ± 0.0063 s, meeting the practical requirements for real-time picking.

在复杂的果园环境中，采摘点的精确定位是实现采摘机器人自动化的关键。然而，现有方法在处理短柄、部分遮挡或完全错认等复杂场景时，容易出现定位误差，影响摘果机器人的实际工作效率。针对复杂的葡萄园采摘场景，提出了一种基于语义推理的增强采摘点定位方法。创新设计了语义推理模块（SRM）、ROI阈值调整策略模块（RTAS）和拾取点位置优化模块（PPOM）三个模块。SRM用于处理葡萄梗被障碍物遮挡、部分错认和完全错认的情况。RTAS解决了采摘过程中花梗低而短的问题。最后，PPOM优化了拾取点的最终位置，使机械臂能够以更大的灵活性进行拾取操作。实验结果表明，SegFormer实现了84.54%的mIoU (average Intersection over Union)，其中B_IoU和P_IoU分别达到73.90%和75.63%。改进的果实采摘点定位算法的成功率达到94.96%，比基线算法高出8.12%。算法的平均处理时间为0.5428±0.0063 s，满足实时采摘的实际要求。

{"title":"Picking point localization method based on semantic reasoning for complex picking scenarios in vineyards","authors":"Xuemin Lin , Jinhai Wang , Jinshuan Wang , Huiling Wei , Mingyou Chen , Lufeng Luo","doi":"10.1016/j.aiia.2025.05.004","DOIUrl":"10.1016/j.aiia.2025.05.004","url":null,"abstract":"<div><div>In the complex orchard environment, precise picking point localization is crucial for the automation of fruit picking robots. However, existing methods are prone to positioning errors when dealing with complex scenarios such as short peduncles, partial occlusion, or complete misidentification, which can affect the actual work efficiency of the fruit picking robot. This study proposes an enhanced picking point localization method based on semantic reasoning for complex picking scenarios in vineyard. It innovatively designs three modules: the semantic reasoning module (SRM), the ROI threshold adjustment strategy (RTAS), and the picking point location optimization module (PPOM). The SRM is applied to handle the scenarios of grape peduncles being obstructed by obstacles, partial misidentification of peduncles, and complete misidentification of peduncles. The RTAS addresses the issue of low and short peduncles during the picking process. Finally, the PPOM optimizes the final position of the picking point, allowing the robotic arm to perform the picking operation with greater flexibility. Experimental results show that SegFormer achieves an mIoU (mean Intersection over Union) of 84.54 %, with B_IoU and P_IoU reaching 73.90 % and 75.63 %, respectively. Additionally, the success rate of the improved fruit picking point localization algorithm reached 94.96 %, surpassing the baseline algorithm by 8.12 %. The algorithm's average processing time is 0.5428 ± 0.0063 s, meeting the practical requirements for real-time picking.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 744-756"},"PeriodicalIF":8.2,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ADeepWeeD: An adaptive deep learning framework for weed species classification ADeepWeeD：一个用于杂草分类的自适应深度学习框架

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-05-22 DOI: 10.1016/j.aiia.2025.04.009

Md Geaur Rahman , Md Anisur Rahman , Mohammad Zavid Parvez , Md Anwarul Kaium Patwary , Tofael Ahamed , David A. Fleming-Muñoz , Saad Aloteibi , Mohammad Ali Moni PhD

Efficient weed management in agricultural fields is essential for attaining optimal crop yields and safeguarding global food security. Every year, farmers worldwide invest significant time, capital, and resources to combat yield losses, approximately USD 75.6 billion, due to weed infestations. Deep Learning (DL) methodologies have been recently implemented to revolutionise agricultural practices, particularly in weed detection and classification. Existing DL-based weed classification techniques, including VGG16 and ResNet50, initially construct a model by implementing the algorithm on a training dataset comprising weed species, subsequently employing the model to identify weed species acquired during training. Given the dynamic nature of crop fields, we argue that existing methods may exhibit suboptimal performance due to two key issues: (i) the unavailability of all training weed species initially, as these species emerge over time, resulting in a progressively expanding training dataset, and (ii) the constrained memory and computational capacity of the system utilised for model development, which hinders the retention of all weed species that manifest over an extended duration. To address the issues, this paper introduces a novel DL-based framework called ADeepWeeD for weed classification that facilitates adaptive (i.e. incremental) learning so that it can handle new weed species by keeping track of historical information. ADeepWeeD is evaluated using two criteria, namely

F_{1}

-Score and classification accuracy, by comparing its performances against four non-incremental and two incremental state-of-the-art methods on three publicly available large datasets. Our experimental results demonstrate that ADeepWeeD outperforms existing techniques used in this study. We believe that our developed model could be used to develop an automation system for weed identification. The code of the proposed method is available on GitHub: https://github.com/grahman20/ADeepWeed.

有效的农田杂草管理对于实现最佳作物产量和保障全球粮食安全至关重要。每年，全世界的农民都要投入大量的时间、资金和资源来应对因杂草肆虐造成的产量损失，损失金额约为756亿美元。深度学习（DL）方法最近被应用于农业实践，特别是在杂草检测和分类方面。现有的基于dl的杂草分类技术，包括VGG16和ResNet50，首先通过在包含杂草种类的训练数据集上实现该算法来构建模型，然后使用该模型对训练过程中获得的杂草种类进行识别。鉴于农田的动态特性，我们认为现有的方法可能由于两个关键问题而表现出不理想的性能：(i)最初所有训练杂草物种的不可用性，因为这些物种随着时间的推移而出现，导致训练数据集逐渐扩大；（ii）用于模型开发的系统的内存和计算能力有限，这阻碍了所有杂草物种在较长时间内的保留。为了解决这些问题，本文引入了一种新的基于dl的框架，称为ADeepWeeD，用于杂草分类，促进自适应（即增量）学习，以便通过跟踪历史信息来处理新的杂草物种。通过将ADeepWeeD与四种非增量方法和两种增量方法在三个公开的大型数据集上的性能进行比较，使用F1-Score和分类精度两个标准对其进行评估。我们的实验结果表明，ADeepWeeD优于本研究中使用的现有技术。我们相信我们开发的模型可以用于开发杂草识别自动化系统。建议的方法的代码可以在GitHub上获得：https://github.com/grahman20/ADeepWeed。

{"title":"ADeepWeeD: An adaptive deep learning framework for weed species classification","authors":"Md Geaur Rahman , Md Anisur Rahman , Mohammad Zavid Parvez , Md Anwarul Kaium Patwary , Tofael Ahamed , David A. Fleming-Muñoz , Saad Aloteibi , Mohammad Ali Moni PhD","doi":"10.1016/j.aiia.2025.04.009","DOIUrl":"10.1016/j.aiia.2025.04.009","url":null,"abstract":"<div><div>Efficient weed management in agricultural fields is essential for attaining optimal crop yields and safeguarding global food security. Every year, farmers worldwide invest significant time, capital, and resources to combat yield losses, approximately USD 75.6 billion, due to weed infestations. Deep Learning (DL) methodologies have been recently implemented to revolutionise agricultural practices, particularly in weed detection and classification. Existing DL-based weed classification techniques, including VGG16 and ResNet50, initially construct a model by implementing the algorithm on a training dataset comprising weed species, subsequently employing the model to identify weed species acquired during training. Given the dynamic nature of crop fields, we argue that existing methods may exhibit suboptimal performance due to two key issues: (i) the unavailability of all training weed species initially, as these species emerge over time, resulting in a progressively expanding training dataset, and (ii) the constrained memory and computational capacity of the system utilised for model development, which hinders the retention of all weed species that manifest over an extended duration. To address the issues, this paper introduces a novel DL-based framework called ADeepWeeD for weed classification that facilitates adaptive (i.e. incremental) learning so that it can handle new weed species by keeping track of historical information. ADeepWeeD is evaluated using two criteria, namely <span><math><msub><mi>F</mi><mn>1</mn></msub></math></span>-Score and classification accuracy, by comparing its performances against four non-incremental and two incremental state-of-the-art methods on three publicly available large datasets. Our experimental results demonstrate that ADeepWeeD outperforms existing techniques used in this study. We believe that our developed model could be used to develop an automation system for weed identification. The code of the proposed method is available on GitHub: <span><span>https://github.com/grahman20/ADeepWeed</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 590-609"},"PeriodicalIF":8.2,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale cross-modal feature fusion and cost-sensitive loss function for differential detection of occluded bagging pears in practical orchards 多尺度跨模态特征融合与代价敏感损失函数在实际果园闭塞套袋梨鉴别检测中的应用

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-05-18 DOI: 10.1016/j.aiia.2025.05.002

Shengli Yan , Wenhui Hou , Yuan Rao , Dan Jiang , Xiu Jin , Tan Wang , Yuwei Wang , Lu Liu , Tong Zhang , Arthur Genis

In practical orchards, the challenges posed by fruit overlapping, branch and leaf occlusion, significantly impede the successful implementation of automated picking, particularly for bagging pears. To address this issue, this paper introduces the multi-scale cross-modal feature fusion and cost-sensitive classification loss function network (MCCNet), specifically designed to accurately detect bagging pears with various occlusion categories. The network designs a dual-stream convolutional neural network as its backbone, enabling the parallel extraction of multi-modal features. Meanwhile, we propose a novel lightweight cross-modal feature fusion method, inspired by enhancing shared features between modalities while extracting specific features from RGB and depth modalities. The cross-modal method enhances the perceptual capabilities of the model by facilitating the fusion of complementary information from multimodal bagging pear image pairs. Furthermore, we optimize the classification loss function by transforming it into a cost-sensitive loss function, aiming to improve detection classification efficiency and reduce instances of missing and false detections during the picking process. Experimental results on a bagging pear dataset demonstrate that our MCCNet achieves mAP0.5 and mAP0.5:0.95 values of 97.3 % and 80.3 %, respectively, representing improvements of 3.6 % and 6.3 % over the classical YOLOv10m model. When benchmarked against several state-of-the-art detection models, our MCCNet network has only 19.5 million parameters while maintaining superior inference speed.

在实际果园中，果实重叠、枝叶遮挡带来的挑战严重阻碍了自动采摘的成功实施，特别是对梨的装袋。为了解决这一问题，本文引入了多尺度跨模态特征融合和代价敏感分类损失函数网络（MCCNet），专门用于准确检测不同遮挡类别的套袋梨。该网络设计了双流卷积神经网络作为主干，实现了多模态特征的并行提取。同时，我们提出了一种新的轻量级跨模态特征融合方法，该方法的灵感来自增强模态之间的共享特征，同时从RGB和深度模态中提取特定特征。跨模态方法通过促进多模态套袋梨图像对互补信息的融合，增强了模型的感知能力。进一步对分类损失函数进行优化，将其转化为代价敏感的损失函数，以提高检测分类效率，减少拣货过程中的漏检和误检。在梨装袋数据集上的实验结果表明，我们的mcnet模型的mAP0.5和mAP0.5:0.95值分别达到97.3%和80.3%，比经典的YOLOv10m模型分别提高了3.6%和6.3%。当与几个最先进的检测模型进行基准测试时，我们的mcnet网络只有1950万个参数，同时保持了卓越的推理速度。

{"title":"Multi-scale cross-modal feature fusion and cost-sensitive loss function for differential detection of occluded bagging pears in practical orchards","authors":"Shengli Yan , Wenhui Hou , Yuan Rao , Dan Jiang , Xiu Jin , Tan Wang , Yuwei Wang , Lu Liu , Tong Zhang , Arthur Genis","doi":"10.1016/j.aiia.2025.05.002","DOIUrl":"10.1016/j.aiia.2025.05.002","url":null,"abstract":"<div><div>In practical orchards, the challenges posed by fruit overlapping, branch and leaf occlusion, significantly impede the successful implementation of automated picking, particularly for bagging pears. To address this issue, this paper introduces the multi-scale cross-modal feature fusion and cost-sensitive classification loss function network (MCCNet), specifically designed to accurately detect bagging pears with various occlusion categories. The network designs a dual-stream convolutional neural network as its backbone, enabling the parallel extraction of multi-modal features. Meanwhile, we propose a novel lightweight cross-modal feature fusion method, inspired by enhancing shared features between modalities while extracting specific features from RGB and depth modalities. The cross-modal method enhances the perceptual capabilities of the model by facilitating the fusion of complementary information from multimodal bagging pear image pairs. Furthermore, we optimize the classification loss function by transforming it into a cost-sensitive loss function, aiming to improve detection classification efficiency and reduce instances of missing and false detections during the picking process. Experimental results on a bagging pear dataset demonstrate that our MCCNet achieves mAP0.5 and mAP0.5:0.95 values of 97.3 % and 80.3 %, respectively, representing improvements of 3.6 % and 6.3 % over the classical YOLOv10m model. When benchmarked against several state-of-the-art detection models, our MCCNet network has only 19.5 million parameters while maintaining superior inference speed.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 573-589"},"PeriodicalIF":8.2,"publicationDate":"2025-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Accurate Orah fruit detection method using lightweight improved YOLOv8n model verified by optimized deployment on edge device 基于轻量级改进的YOLOv8n模型的Orah水果精确检测方法通过优化部署在边缘设备上的验证

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-05-14 DOI: 10.1016/j.aiia.2025.05.001

Hongwei Li , Yongmei Mo , Jiasheng Chen , Jiqing Chen , Jiabao Li

The replacement of personal computer terminal with edge device is recognized as a portable and cost-effective potential solution in solving equipment miniaturization and achieving high flexibility of robotic fruit harvesting at in-field scale. This study proposes a lightweight improved You Only Look Once version 8n (YOLOv8n) model for detecting Orah fruits and deploying this model on an edge device. First of all, the model size was reduced while maintaining detection accuracy via the introduction of the ADown modules. Subsequently, a Concentrated-Comprehensive Dual Convolution (C3_DualConv) module combining dual convolutional bottlenecks was proposed to enhance the model capability to capture features of Orah fruits obscured by branches and leaves; this practice further reduced the model size. Additionally, a Bidirectional Feature Pyramid Network (BiFPN) that includes a pyramid level 2 high-resolution layer was employed for more efficient multi-scale feature fusion. Besides, three Coordinate Attention (CA) mechanism modules were also added to improve the recognition and capture capability for Orah fruit features. Finally, a more focused minimum points distance intersection over union loss was adopted to boost the detection efficiency of densely occluded Orah fruits. Experimentally demonstrating that the improved YOLOv8n model accurately detected Orah fruits in complex orchard environments, achieving a 97.7 % of precision, an Average Precision at IoU threshold 0.5 ([email protected]) of 98.8 %, and a 96.69 % of F1 score, while maintaining a compact model size of 4.1 MB, under a Windows-based system terminal. This proposed model was optimally deployed on an Nvidia Jetson Orin Nano using TensorRT Python Application Programming Interface (API), the average interface speed exceeds 30 fps, indicating a real-time detection ability. This study can provide technical support for Orah fruit robotic harvesting on the basis of edge device.

边缘设备取代个人计算机终端是解决设备小型化和实现果园自动化采收高灵活性的一种便携、经济的潜在解决方案。本研究提出了一种轻量级的改进You Only Look Once version 8n （YOLOv8n）模型，用于检测Orah水果，并将该模型部署在边缘设备上。首先，通过引入down模块，在保持检测精度的同时减小了模型尺寸。随后，提出了一种结合双卷积瓶颈的集中-综合对偶卷积（C3_DualConv）模块，增强了模型捕捉被枝叶遮挡的桔梗果实特征的能力；这种做法进一步减小了模型的尺寸。此外，采用包含金字塔级2分辨率层的双向特征金字塔网络（Bidirectional Feature Pyramid Network, BiFPN）进行更高效的多尺度特征融合。此外，还增加了三个坐标注意（CA）机制模块，提高了对桔梗果特征的识别和捕获能力。最后，采用更集中的最小点距交点与并集损失交点，提高密集遮挡的奥拉果的检测效率。实验证明，改进的YOLOv8n模型在复杂果园环境下准确地检测了奥拉果，在windows系统终端下，精度达到97.7%，IoU阈值0.5 （[email protected]）下的平均精度达到98.8%，F1分数达到96.69%，同时保持了4.1 MB的紧凑模型大小。采用TensorRT Python应用程序编程接口（API），将该模型优化部署在Nvidia Jetson Orin Nano上，平均接口速度超过30 fps，表明该模型具有实时检测能力。本研究可为基于边缘装置的桔梗果机器人采收提供技术支持。

{"title":"Accurate Orah fruit detection method using lightweight improved YOLOv8n model verified by optimized deployment on edge device","authors":"Hongwei Li , Yongmei Mo , Jiasheng Chen , Jiqing Chen , Jiabao Li","doi":"10.1016/j.aiia.2025.05.001","DOIUrl":"10.1016/j.aiia.2025.05.001","url":null,"abstract":"<div><div>The replacement of personal computer terminal with edge device is recognized as a portable and cost-effective potential solution in solving equipment miniaturization and achieving high flexibility of robotic fruit harvesting at in-field scale. This study proposes a lightweight improved You Only Look Once version 8n (YOLOv8n) model for detecting Orah fruits and deploying this model on an edge device. First of all, the model size was reduced while maintaining detection accuracy via the introduction of the ADown modules. Subsequently, a Concentrated-Comprehensive Dual Convolution (C3_DualConv) module combining dual convolutional bottlenecks was proposed to enhance the model capability to capture features of Orah fruits obscured by branches and leaves; this practice further reduced the model size. Additionally, a Bidirectional Feature Pyramid Network (BiFPN) that includes a pyramid level 2 high-resolution layer was employed for more efficient multi-scale feature fusion. Besides, three Coordinate Attention (CA) mechanism modules were also added to improve the recognition and capture capability for Orah fruit features. Finally, a more focused minimum points distance intersection over union loss was adopted to boost the detection efficiency of densely occluded Orah fruits. Experimentally demonstrating that the improved YOLOv8n model accurately detected Orah fruits in complex orchard environments, achieving a 97.7 % of precision, an Average Precision at IoU threshold 0.5 ([email protected]) of 98.8 %, and a 96.69 % of F1 score, while maintaining a compact model size of 4.1 MB, under a Windows-based system terminal. This proposed model was optimally deployed on an Nvidia Jetson Orin Nano using TensorRT Python Application Programming Interface (API), the average interface speed exceeds 30 fps, indicating a real-time detection ability. This study can provide technical support for Orah fruit robotic harvesting on the basis of edge device.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 707-723"},"PeriodicalIF":8.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decoding canola and oat crop health and productivity under drought and heat stress using bioelectrical signals and machine learning 利用生物电信号和机器学习解码干旱和热胁迫下油菜籽和燕麦作物的健康和生产力

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-04-30 DOI: 10.1016/j.aiia.2025.04.006

Guoqi Wen, Bao-Luo Ma

Abiotic stresses, such as heat and drought, often reduce crop yields by harming plant health. Plants have evolved complex signaling networks to mitigate environmental impacts, making monitoring in-situ biosignals a promising tool for assessing plant health in real time. In this study, needle-like sensors were used to measure electrical potential changes in oat and canola plants under heat and drought stress conditions. Signals were recorded over a 30-min period and segmented into time intervals of 1-, 5-, 10-, 20-, and 30-min. Machine learning algorithms, including Random Forest, K-Nearest Neighbors, and Support Vector Machines, were applied to classify stress conditions and estimate biomass based on 14 extracted bioelectrical features, such as signal amplitude and entropy. Results showed that heat stress primarily altered signal patterns, whereas drought stress affected the signal intensity, possibly due to a reduction in the flow rate of charged ions. Random Forest classifier successfully identified over 85 % of stressed crops within 30 min of signal recording. These signals also explained 58–95 % of the variation in plant aboveground and root biomass, depending on stress intensity and crop genotype. This study demonstrates the potential of using bioelectrical sensing as a rapid and efficient tool for stress detection and biomass estimation. Future research should explore the ability to use biosensors to capture genetic variability to mitigate abiotic stresses and combine this with remote sensing and other emerging precision agriculture technologies.

非生物胁迫，如高温和干旱，往往通过损害植物健康来降低作物产量。植物已经进化出复杂的信号网络来减轻环境影响，这使得监测原位生物信号成为实时评估植物健康的有前途的工具。在本研究中，采用针状传感器测量了高温和干旱胁迫条件下燕麦和油菜植株的电位变化。在30分钟的时间内记录信号，并将其分割为1分钟、5分钟、10分钟、20分钟和30分钟的时间间隔。采用随机森林、k近邻和支持向量机等机器学习算法对应力条件进行分类，并根据提取的14种生物电特征（如信号幅度和熵）估计生物量。结果表明，热胁迫主要改变信号模式，而干旱胁迫影响信号强度，可能是由于带电离子流速的减少。随机森林分类器在信号记录30分钟内成功识别了85%以上的胁迫作物。这些信号还解释了植物地上部和根部生物量的58 - 95%的变化，这取决于胁迫强度和作物基因型。这项研究证明了利用生物电传感作为一种快速有效的应力检测和生物量估计工具的潜力。未来的研究应该探索利用生物传感器捕捉遗传变异以减轻非生物胁迫的能力，并将其与遥感和其他新兴的精准农业技术相结合。

{"title":"Decoding canola and oat crop health and productivity under drought and heat stress using bioelectrical signals and machine learning","authors":"Guoqi Wen, Bao-Luo Ma","doi":"10.1016/j.aiia.2025.04.006","DOIUrl":"10.1016/j.aiia.2025.04.006","url":null,"abstract":"<div><div>Abiotic stresses, such as heat and drought, often reduce crop yields by harming plant health. Plants have evolved complex signaling networks to mitigate environmental impacts, making monitoring in-situ biosignals a promising tool for assessing plant health in real time. In this study, needle-like sensors were used to measure electrical potential changes in oat and canola plants under heat and drought stress conditions. Signals were recorded over a 30-min period and segmented into time intervals of 1-, 5-, 10-, 20-, and 30-min. Machine learning algorithms, including Random Forest, K-Nearest Neighbors, and Support Vector Machines, were applied to classify stress conditions and estimate biomass based on 14 extracted bioelectrical features, such as signal amplitude and entropy. Results showed that heat stress primarily altered signal patterns, whereas drought stress affected the signal intensity, possibly due to a reduction in the flow rate of charged ions. Random Forest classifier successfully identified over 85 % of stressed crops within 30 min of signal recording. These signals also explained 58–95 % of the variation in plant aboveground and root biomass, depending on stress intensity and crop genotype. This study demonstrates the potential of using bioelectrical sensing as a rapid and efficient tool for stress detection and biomass estimation. Future research should explore the ability to use biosensors to capture genetic variability to mitigate abiotic stresses and combine this with remote sensing and other emerging precision agriculture technologies.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 4","pages":"Pages 696-706"},"PeriodicalIF":8.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing maize LAI estimation accuracy using unmanned aerial vehicle remote sensing and deep learning techniques 利用无人机遥感和深度学习技术提高玉米LAI估计精度

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-04-25 DOI: 10.1016/j.aiia.2025.04.008

Zhen Chen , Weiguang Zhai , Qian Cheng

The leaf area index (LAI) is crucial for precision agriculture management. UAV remote sensing technology has been widely applied for LAI estimation. Although spectral features are widely used for LAI estimation, their performance is often constrained in complex agricultural scenarios due to interference from soil background reflectance, variations in lighting conditions, and vegetation heterogeneity. Therefore, this study evaluates the potential of multi-source feature fusion and convolutional neural networks (CNN) in estimating maize LAI. To achieve this goal, field experiments on maize were conducted in Xinxiang City and Xuzhou City, China. Subsequently, spectral features, texture features, and crop height were extracted from the multi-spectral remote sensing data to construct a multi-source feature dataset. Then, maize LAI estimation models were developed using multiple linear regression, gradient boosting decision tree, and CNN. The results showed that: (1) Multi-source feature fusion, which integrates spectral features, texture features, and crop height, demonstrated the highest accuracy in LAI estimation, with the R² ranging from 0.70 to 0.83, the RMSE ranging from 0.44 to 0.60, and the rRMSE ranging from 10.79 % to 14.57 %. In addition, the multi-source feature fusion demonstrates strong adaptability across different growth environments. In Xinxiang, the R² ranges from 0.76 to 0.88, the RMSE ranges from 0.35 to 0.50, and the rRMSE ranges from 8.73 % to 12.40 %. In Xuzhou, the R² ranges from 0.60 to 0.83, the RMSE ranges from 0.46 to 0.71, and the rRMSE ranges from 10.96 % to 17.11 %. (2) The CNN model outperformed traditional machine learning algorithms in most cases. Moreover, the combination of spectral features, texture features, and crop height using the CNN model achieved the highest accuracy in LAI estimation, with the R² ranging from 0.83 to 0.88, the RMSE ranging from 0.35 to 0.46, and the rRMSE ranging from 8.73 % to 10.96 %.

叶面积指数（LAI）是精准农业管理的重要指标。无人机遥感技术在LAI估算中得到了广泛的应用。虽然光谱特征被广泛用于LAI估算，但由于土壤背景反射率、光照条件变化和植被异质性的干扰，其性能在复杂的农业场景下往往受到限制。因此，本研究评估了多源特征融合和卷积神经网络（CNN）在估计玉米LAI中的潜力。为实现这一目标，在中国新乡市和徐州市进行了玉米田间试验。随后，从多光谱遥感数据中提取光谱特征、纹理特征和作物高度，构建多源特征数据集。然后，利用多元线性回归、梯度增强决策树和CNN建立玉米LAI估计模型。结果表明：(1)融合光谱特征、纹理特征和作物高度的多源特征融合对LAI的估计精度最高，R2范围为0.70 ~ 0.83，RMSE范围为0.44 ~ 0.60，rRMSE范围为10.79% ~ 14.57%。此外，多源特征融合对不同生长环境具有较强的适应性。新乡市R2范围为0.76 ~ 0.88，RMSE范围为0.35 ~ 0.50，rRMSE范围为8.73% ~ 12.40%。徐州地区R2范围为0.60 ~ 0.83，RMSE范围为0.46 ~ 0.71，rRMSE范围为10.96% ~ 17.11%。(2) CNN模型在大多数情况下优于传统机器学习算法。此外，利用CNN模型组合光谱特征、纹理特征和作物高度估算LAI的精度最高，R2范围为0.83 ~ 0.88，RMSE范围为0.35 ~ 0.46，rRMSE范围为8.73% ~ 10.96%。

{"title":"Enhancing maize LAI estimation accuracy using unmanned aerial vehicle remote sensing and deep learning techniques","authors":"Zhen Chen , Weiguang Zhai , Qian Cheng","doi":"10.1016/j.aiia.2025.04.008","DOIUrl":"10.1016/j.aiia.2025.04.008","url":null,"abstract":"<div><div>The leaf area index (LAI) is crucial for precision agriculture management. UAV remote sensing technology has been widely applied for LAI estimation. Although spectral features are widely used for LAI estimation, their performance is often constrained in complex agricultural scenarios due to interference from soil background reflectance, variations in lighting conditions, and vegetation heterogeneity. Therefore, this study evaluates the potential of multi-source feature fusion and convolutional neural networks (CNN) in estimating maize LAI. To achieve this goal, field experiments on maize were conducted in Xinxiang City and Xuzhou City, China. Subsequently, spectral features, texture features, and crop height were extracted from the multi-spectral remote sensing data to construct a multi-source feature dataset. Then, maize LAI estimation models were developed using multiple linear regression, gradient boosting decision tree, and CNN. The results showed that: (1) Multi-source feature fusion, which integrates spectral features, texture features, and crop height, demonstrated the highest accuracy in LAI estimation, with the R<sup>2</sup> ranging from 0.70 to 0.83, the RMSE ranging from 0.44 to 0.60, and the rRMSE ranging from 10.79 % to 14.57 %. In addition, the multi-source feature fusion demonstrates strong adaptability across different growth environments. In Xinxiang, the R<sup>2</sup> ranges from 0.76 to 0.88, the RMSE ranges from 0.35 to 0.50, and the rRMSE ranges from 8.73 % to 12.40 %. In Xuzhou, the R<sup>2</sup> ranges from 0.60 to 0.83, the RMSE ranges from 0.46 to 0.71, and the rRMSE ranges from 10.96 % to 17.11 %. (2) The CNN model outperformed traditional machine learning algorithms in most cases. Moreover, the combination of spectral features, texture features, and crop height using the CNN model achieved the highest accuracy in LAI estimation, with the R<sup>2</sup> ranging from 0.83 to 0.88, the RMSE ranging from 0.35 to 0.46, and the rRMSE ranging from 8.73 % to 10.96 %.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 482-495"},"PeriodicalIF":8.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mapping of soil sampling sites using terrain and hydrological attributes 利用地形和水文属性绘制土壤采样点图

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-04-25 DOI: 10.1016/j.aiia.2025.04.007

Tan-Hanh Pham , Kristopher Osterloh , Kim-Doang Nguyen

Efficient soil sampling is essential for effective soil management and research on soil health. Traditional site selection methods are labor-intensive and fail to capture soil variability comprehensively. This study introduces a deep learning-based tool that automates soil sampling site selection using spectral images. The proposed framework consists of two key components: an extractor and a predictor. The extractor, based on a convolutional neural network (CNN), derives features from spectral images, while the predictor employs self-attention mechanisms to assess feature importance and generate prediction maps. The model is designed to process multiple spectral images and address the class imbalance in soil segmentation.

The model was trained on a soil dataset from 20 fields in eastern South Dakota, collected via drone-mounted LiDAR with high-precision GPS. Evaluation on a test set achieved a mean intersection over union (mIoU) of 69.46 % and a mean Dice coefficient (mDc) of 80.35 %, demonstrating strong segmentation performance. The results highlight the model's effectiveness in automating soil sampling site selection, providing an advanced tool for producers and soil scientists. Compared to existing state-of-the-art methods, the proposed approach improves accuracy and efficiency, optimizing soil sampling processes and enhancing soil research.

有效的土壤采样是有效的土壤管理和土壤健康研究的必要条件。传统的选址方法是劳动密集型的，不能全面地捕捉土壤的变异性。本研究介绍了一种基于深度学习的工具，该工具可以使用光谱图像自动选择土壤采样地点。提出的框架由两个关键组件组成：提取器和预测器。基于卷积神经网络（CNN）的提取器从光谱图像中提取特征，而预测器则使用自注意机制来评估特征的重要性并生成预测图。该模型能够处理多光谱图像，解决土壤分割中的类不平衡问题。该模型是在南达科他州东部20个农田的土壤数据集上进行训练的，这些数据集是通过无人机安装的激光雷达和高精度GPS收集的。在测试集上进行评估，平均交联率（mIoU）为69.46%，平均Dice系数（mDc）为80.35%，显示出较强的分割性能。结果表明，该模型在土壤采样点自动化选择中的有效性，为生产者和土壤科学家提供了一种先进的工具。与现有的最先进的方法相比，该方法提高了精度和效率，优化了土壤采样过程，加强了土壤研究。

{"title":"Mapping of soil sampling sites using terrain and hydrological attributes","authors":"Tan-Hanh Pham , Kristopher Osterloh , Kim-Doang Nguyen","doi":"10.1016/j.aiia.2025.04.007","DOIUrl":"10.1016/j.aiia.2025.04.007","url":null,"abstract":"<div><div>Efficient soil sampling is essential for effective soil management and research on soil health. Traditional site selection methods are labor-intensive and fail to capture soil variability comprehensively. This study introduces a deep learning-based tool that automates soil sampling site selection using spectral images. The proposed framework consists of two key components: an extractor and a predictor. The extractor, based on a convolutional neural network (CNN), derives features from spectral images, while the predictor employs self-attention mechanisms to assess feature importance and generate prediction maps. The model is designed to process multiple spectral images and address the class imbalance in soil segmentation.</div><div>The model was trained on a soil dataset from 20 fields in eastern South Dakota, collected via drone-mounted LiDAR with high-precision GPS. Evaluation on a test set achieved a mean intersection over union (mIoU) of 69.46 % and a mean Dice coefficient (mDc) of 80.35 %, demonstrating strong segmentation performance. The results highlight the model's effectiveness in automating soil sampling site selection, providing an advanced tool for producers and soil scientists. Compared to existing state-of-the-art methods, the proposed approach improves accuracy and efficiency, optimizing soil sampling processes and enhancing soil research.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 470-481"},"PeriodicalIF":8.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multimodal behavior recognition for dairy cow digital twin construction under incomplete modalities: A modality mapping completion network approach 不完全模态下奶牛数字孪生构建的多模态行为识别：一种模态映射完成网络方法

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-04-14 DOI: 10.1016/j.aiia.2025.04.005

Yi Zhang , Yu Zhang , Meng Gao , Xinjie Wang , Baisheng Dai , Weizheng Shen

The recognition of dairy cow behavior is essential for enhancing health management, reproductive efficiency, production performance, and animal welfare. This paper addresses the challenge of modality loss in multimodal dairy cow behavior recognition algorithms, which can be caused by sensor or video signal disturbances arising from interference, harsh environmental conditions, extreme weather, network fluctuations, and other complexities inherent in farm environments. This study introduces a modality mapping completion network that maps incomplete sensor and video data to improve multimodal dairy cow behavior recognition under conditions of modality loss. By mapping incomplete sensor or video data, the method applies a multimodal behavior recognition algorithm to identify five specific behaviors: drinking, feeding, lying, standing, and walking. The results indicate that, under various comprehensive missing coefficients (λ), the method achieves an average accuracy of 97.87 % ± 0.15 %, an average precision of 95.19 % ± 0.4 %, and an average F1 score of 94.685 % ± 0.375 %, with an overall accuracy of 94.67 % ± 0.37 %. This approach enhances the robustness and applicability of cow behavior recognition based on multimodal data in situations of modality loss, resolving practical issues in the development of digital twins for cow behavior and providing comprehensive support for the intelligent and precise management of farms.

认识奶牛的行为对提高健康管理、繁殖效率、生产性能和动物福利至关重要。本文解决了多模式奶牛行为识别算法中模态损失的挑战，这可能是由干扰、恶劣环境条件、极端天气、网络波动和农场环境中固有的其他复杂性引起的传感器或视频信号干扰引起的。本研究引入了一个模态映射完成网络，该网络可以映射不完整的传感器和视频数据，以提高在模态丢失条件下的多模态奶牛行为识别。通过映射不完整的传感器或视频数据，该方法应用多模态行为识别算法来识别五种特定行为：喝水、进食、躺着、站立和行走。结果表明，在各种综合缺失系数（λ）下，该方法的平均准确率为97.87%±0.15%，平均精密度为95.19%±0.4%，平均F1分数为94.685±0.375%，总体准确率为94.67%±0.37%。该方法增强了基于多模态数据的奶牛行为识别在模态丢失情况下的鲁棒性和适用性，解决了奶牛行为数字孪生开发中的实际问题，为养殖场的智能化、精准化管理提供全面支持。

{"title":"Multimodal behavior recognition for dairy cow digital twin construction under incomplete modalities: A modality mapping completion network approach","authors":"Yi Zhang , Yu Zhang , Meng Gao , Xinjie Wang , Baisheng Dai , Weizheng Shen","doi":"10.1016/j.aiia.2025.04.005","DOIUrl":"10.1016/j.aiia.2025.04.005","url":null,"abstract":"<div><div>The recognition of dairy cow behavior is essential for enhancing health management, reproductive efficiency, production performance, and animal welfare. This paper addresses the challenge of modality loss in multimodal dairy cow behavior recognition algorithms, which can be caused by sensor or video signal disturbances arising from interference, harsh environmental conditions, extreme weather, network fluctuations, and other complexities inherent in farm environments. This study introduces a modality mapping completion network that maps incomplete sensor and video data to improve multimodal dairy cow behavior recognition under conditions of modality loss. By mapping incomplete sensor or video data, the method applies a multimodal behavior recognition algorithm to identify five specific behaviors: drinking, feeding, lying, standing, and walking. The results indicate that, under various comprehensive missing coefficients (λ), the method achieves an average accuracy of 97.87 % ± 0.15 %, an average precision of 95.19 % ± 0.4 %, and an average F1 score of 94.685 % ± 0.375 %, with an overall accuracy of 94.67 % ± 0.37 %. This approach enhances the robustness and applicability of cow behavior recognition based on multimodal data in situations of modality loss, resolving practical issues in the development of digital twins for cow behavior and providing comprehensive support for the intelligent and precise management of farms.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 459-469"},"PeriodicalIF":8.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143873553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Joint optimization of AI large and small models for surface temperature and emissivity retrieval using knowledge distillation 基于知识蒸馏的地表温度和发射率检索AI大、小模型联合优化

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY

Artificial Intelligence in Agriculture

Pub Date : 2025-04-12 DOI: 10.1016/j.aiia.2025.03.009

Wang Dai , Kebiao Mao , Zhonghua Guo , Zhihao Qin , Jiancheng Shi , Sayed M. Bateni , Liurui Xiao

The rapid advancement of artificial intelligence in domains such as natural language processing has catalyzed AI research across various fields. This study introduces a novel strategy, the AutoKeras-Knowledge Distillation (AK-KD), which integrates knowledge distillation technology for joint optimization of large and small models in the retrieval of surface temperature and emissivity using thermal infrared remote sensing. The approach addresses the challenges of limited accuracy in surface temperature retrieval by employing a high-performance large model developed through AutoKeras as the teacher model, which subsequently enhances a less accurate small model through knowledge distillation. The resultant student model is interactively integrated with the large model to further improve specificity and generalization capabilities. Theoretical derivations and practical applications validate that the AK-KD strategy significantly enhances the accuracy of temperature and emissivity retrieval. For instance, a large model trained with simulated ASTER data achieved a Pearson Correlation Coefficient (PCC) of 0.999 and a Mean Absolute Error (MAE) of 0.348 K in surface temperature retrieval. In practical applications, this model demonstrated a PCC of 0.967 and an MAE of 0.685 K. Although the large model exhibits high average accuracy, its precision in complex terrains is comparatively lower. To ameliorate this, the large model, serving as a teacher, enhances the small model's local accuracy. Specifically, in surface temperature retrieval, the small model's PCC improved from an average of 0.978 to 0.979, and the MAE decreased from 1.065 K to 0.724 K. In emissivity retrieval, the PCC rose from an average of 0.827 to 0.898, and the MAE reduced from 0.0076 to 0.0054. This research not only provides robust technological support for further development of thermal infrared remote sensing in temperature and emissivity retrieval but also offers important references and key technological insights for the universal model construction of other geophysical parameter retrievals.

人工智能在自然语言处理等领域的快速发展促进了各个领域的人工智能研究。本文提出了一种新的策略——AutoKeras-Knowledge Distillation (AK-KD)，该策略集成了知识蒸馏技术，用于热红外遥感地表温度和发射率的大、小模型联合优化。该方法通过使用AutoKeras开发的高性能大型模型作为教师模型，解决了表面温度检索精度有限的挑战，该模型随后通过知识蒸馏增强了精度较低的小型模型。生成的学生模型与大模型交互集成，以进一步提高特异性和泛化能力。理论推导和实际应用验证了AK-KD策略显著提高了温度和发射率的反演精度。例如，用ASTER模拟数据训练的大型模型反演地表温度的Pearson相关系数（PCC）为0.999，平均绝对误差（MAE）为0.348 K。在实际应用中，模型的PCC为0.967，MAE为0.685 K。虽然大模型具有较高的平均精度，但在复杂地形下的精度相对较低。为了改善这一点，大模型作为教师，提高了小模型的局部精度。在地表温度反演中，小模型的PCC由平均0.978提高到0.979，MAE由平均1.065 K降低到0.724 K。在发射率反演中，PCC由平均0.827上升至0.898，MAE由平均0.0076下降至0.0054。该研究不仅为热红外遥感在温度和发射率反演方面的进一步发展提供了强有力的技术支撑，也为其他地球物理参数反演的通用模型构建提供了重要的参考和关键的技术见解。

{"title":"Joint optimization of AI large and small models for surface temperature and emissivity retrieval using knowledge distillation","authors":"Wang Dai , Kebiao Mao , Zhonghua Guo , Zhihao Qin , Jiancheng Shi , Sayed M. Bateni , Liurui Xiao","doi":"10.1016/j.aiia.2025.03.009","DOIUrl":"10.1016/j.aiia.2025.03.009","url":null,"abstract":"<div><div>The rapid advancement of artificial intelligence in domains such as natural language processing has catalyzed AI research across various fields. This study introduces a novel strategy, the AutoKeras-Knowledge Distillation (AK-KD), which integrates knowledge distillation technology for joint optimization of large and small models in the retrieval of surface temperature and emissivity using thermal infrared remote sensing. The approach addresses the challenges of limited accuracy in surface temperature retrieval by employing a high-performance large model developed through AutoKeras as the teacher model, which subsequently enhances a less accurate small model through knowledge distillation. The resultant student model is interactively integrated with the large model to further improve specificity and generalization capabilities. Theoretical derivations and practical applications validate that the AK-KD strategy significantly enhances the accuracy of temperature and emissivity retrieval. For instance, a large model trained with simulated ASTER data achieved a Pearson Correlation Coefficient (PCC) of 0.999 and a Mean Absolute Error (MAE) of 0.348 K in surface temperature retrieval. In practical applications, this model demonstrated a PCC of 0.967 and an MAE of 0.685 K. Although the large model exhibits high average accuracy, its precision in complex terrains is comparatively lower. To ameliorate this, the large model, serving as a teacher, enhances the small model's local accuracy. Specifically, in surface temperature retrieval, the small model's PCC improved from an average of 0.978 to 0.979, and the MAE decreased from 1.065 K to 0.724 K. In emissivity retrieval, the PCC rose from an average of 0.827 to 0.898, and the MAE reduced from 0.0076 to 0.0054. This research not only provides robust technological support for further development of thermal infrared remote sensing in temperature and emissivity retrieval but also offers important references and key technological insights for the universal model construction of other geophysical parameter retrievals.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 407-425"},"PeriodicalIF":8.2,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143837982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0