[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3054":3,"related-3054":64},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":63},3054,"Assessment of mechanical damage in canola using X-ray radiography and deep learning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112350","Mechanical damage during post-harvest handling and processing can drastically impair the quality, germination potential, and market value of canola ( Brassica napus L.) seeds. Traditional visual inspection methods are subjective and limited to detecting external defects, often missing internal damage. This study presents a non-destructive approach for classifying mechanical damage in canola seeds using X-ray radiography combined with artificial intelligence techniques. Seeds at three moisture contents (6 %, 8 %, and 12 %) were subjected to four levels of impact energy (0, 3, 3.7, and 4.3 mJ), generating 3,029 radiographic images labelled into four levels of varying mechanical damage (no damage, low damage, medium damage, and high damage). Two analytical pipelines were developed. The first involved machine learning with 37 extracted features, including intensity-based metrics, texture descriptors, frequency-domain features, and Fast Fourier Transform (FFT) features. Support vector machine (SVM) and random forest (RF) models were developed and evaluated; the SVM achieved the highest accuracy of 74.01 % after feature selection. The second pipeline implemented deep learning via transfer learning on five pre-trained convolutional neural networks: MobileNetV2, EfficientNet-B0, Xception, ResNet50, and DenseNet121. Among these, MobileNetV2 achieved the highest accuracy of 91.42 %, outperforming all traditional machine learning models. The results demonstrate the potential of integrating radiographic imaging with artificial intelligence methods for rapid, reliable, and non-destructive classification of mechanical damage in canola seeds, paving the way for intelligent quality control systems in the oilseed supply chain.","油菜（Brassica napus L.）种子在采后处理和加工过程中的机械损伤会严重损害其品质、发芽潜力和市场价值。传统的视觉检测方法主观性强，且仅限于检测外部缺陷，往往无法发现内部损伤。本研究提出了一种利用X射线成像结合人工智能技术对油菜种子机械损伤进行无损分类的方法。将三种含水率（6%、8%和12%）的种子分别施加四个水平的冲击能量（0、3、3.7和4.3 mJ），共生成3,029张射线图像，并标注为四个不同程度的机械损伤等级（无损伤、低损伤、中等损伤和高损伤）。研究开发了两条分析流程。第一条采用机器学习方法，提取了37个特征，包括基于强度的指标、纹理描述符、频域特征以及快速傅里叶变换（FFT）特征，开发并评估了支持向量机（SVM）和随机森林（RF）模型，其中SVM在特征选择后达到了74.01%的最高准确率。第二条流程通过迁移学习在五个预训练卷积神经网络上实现深度学习：MobileNetV2、EfficientNet-B0、Xception、ResNet50和DenseNet121。其中，MobileNetV2达到了91.42%的最高准确率，优于所有传统机器学习模型。结果表明，将射线成像与人工智能方法相结合，有望实现对油菜种子机械损伤的快速、可靠且无损的分类，为油料种子供应链中的智能质量控制系统的建立奠定了基础。",null,"Computers and Electronics in Agriculture","2026-09-20T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"将X射线成像与深度学习结合用于油菜籽内部机械损伤无损分级，方法新颖、数据规模可观，对油料供应链智能质控有参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","无损检测","油菜","种子质量",[32,33],"X射线 油菜籽 机械损伤","MobileNetV2 种子 无损检测","X射线油菜籽机械损伤-3054",0,"10.1016\u002Fj.compag.2026.112350",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":6,"card":56,"direction":60,"ingested_from":62},"W7213778300",[40,42,45,47,50,53],{"name":41,"orcid":9},"M. Buragohain",{"name":43,"orcid":44},"L. G. Divyanth","https:\u002F\u002Forcid.org\u002F0000-0002-1121-1642",{"name":46,"orcid":9},"Taranveer Singh",{"name":48,"orcid":49},"Muhammad Mudassir Arif Chaudhry","https:\u002F\u002Forcid.org\u002F0000-0001-5316-4701",{"name":51,"orcid":52},"Jitendra Paliwal","https:\u002F\u002Forcid.org\u002F0000-0002-1665-3626",{"name":54,"orcid":55},"Mohammad Nadimi","https:\u002F\u002Forcid.org\u002F0000-0002-4550-7572",{"tldr":57,"method":58,"finding":59,"direction":60,"opportunity":61},"用X射线成像结合机器学习与深度学习，无损分类油菜籽机械损伤等级。","3029张X射线图像，提取37个特征训练SVM\u002FRF，并用五种预训练CNN迁移学","MobileNetV2准确率达91.42%，显著优于传统机器学习最高74.01%。","农业人工智能与决策模型","可拓展至多作物种子内部损伤实时检测，并融合高光谱或近红外实现便携式在线分选。","openalex","2026-09-21T23:30:02.090869Z",{"total":65,"page":21,"page_size":65,"items":66},6,[67,109,140,185,228,259],{"id":68,"title":69,"url":70,"summary":71,"summary_zh":72,"content":9,"source_name":73,"source_url":70,"published_at":74,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":75,"score_detail":76,"sources":81,"tags":83,"search_phrases":86,"slug":89,"view_count":35,"doi":90,"paper":91,"created_at":108},3017,"Automated seedling vigor estimation in cucumbers using digital image processing","https:\u002F\u002Fdoi.org\u002F10.65764\u002Ftjas.2026.267412","Background and Objective: Farmers often rely on experience rather than quantitative indicators to determine seedling quality, resulting in inefficiencies in resource allocation. This study aimed to (1) compare seedling vigor and growth characteristics between open-pollinated (OP) and F1 hybrid cucumber seed types, and (2) develop a non-destructive predictive model for seedling vigor estimation based on digital image analysis.Methodology: Seedling images were acquired under controlled LED lighting using a 5 MP digital camera positioned 30 cm above 14-day-old seedlings. A YOLOv8-based object detection model was applied to detect and isolate true leaf regions, from which pixel count and RGB color values were extracted as input features for a multiple linear regression model to predict the seedling vigor index (SVI).Main Results: The YOLOv8 object detection model achieved a mean average precision (mAP@0.5) of 96.00%, precision of 93.40%, and recall of 94.40% in detecting true leaves. Multiple linear regression analysis was conducted using the Scikit-learn library in Python. Scikit-learn provides regression-based machine learning algorithms, including multiple linear regression. The equation was then applied to the training and test sets, using the pixel values of true leaves as the independent variable and SVI as the dependent variable. Using multiple regression analysis, the trained model generated the equation SVI = -2.27 + (2.84 × 10-5 × pixel) + (3.48 × 10-5 × R) + (-7.49 × 10-2 × G) + (2.06 × 10-1 × B), R2 = 0.57 and RMSE = 1.10. The model achieved the test set, r = 0.79 and RMSE = 1.34. The model performance showed a correlation coefficient of 0.85 for OP data and 0.91 for F1 hybrid data.Conclusions: The results demonstrate that digital image processing combined with object detection provides a non-destructive and effective approach to estimate seedling vigor quality. The predictive models developed from OP and F1 hybrid datasets indicate potential application in precision agriculture for automated seedling quality assessment and transplanting decision support.","背景与目标：农民通常依赖经验而非定量指标来判断幼苗质量，导致资源配置效率低下。本研究旨在（1）比较开放授粉（OP）与F1杂交黄瓜种子类型之间的幼苗活力和生长特性，（2）基于数字图像分析开发一种用于幼苗活力评估的无损预测模型。方法：使用500万像素数码相机置于14日龄幼苗上方30 cm处，在受控LED光照下获取幼苗图像。应用基于YOLOv8的目标检测模型检测并分离真叶区域，从中提取像素计数和RGB颜色值作为多元线性回归模型的输入特征，以预测幼苗活力指数（SVI）。主要结果：YOLOv8目标检测模型在检测真叶时达到了96.00%的平均精度均值（mAP@0.5）、93.40%的精确率和94.40%的召回率。使用Python中的Scikit-learn库进行多元线性回归分析。Scikit-learn提供基于回归的机器学习算法，包括多元线性回归。随后将该方程应用于训练集和测试集，以真叶像素值作为自变量，SVI作为因变量。通过多元回归分析，训练模型生成的方程为SVI = -2.27 + (2.84 × 10-5 × 像素) + (3.48 × 10-5 × R) + (-7.49 × 10-2 × G) + (2.06 × 10-1 × B)，R2 = 0.57，RMSE = 1.10。该模型在测试集上达到r = 0.79，RMSE = 1.34。模型性能显示，OP数据的相关系数为0.85，F1杂交数据的相关系数为0.91。结论：结果表明，数字图像处理结合目标检测为评估幼苗活力质量提供了一种无损且有效的方法。基于OP和F1杂交数据集开发的预测模型表明，其在精准农业中具有用于自动化幼苗质量评估和移栽决策支持的潜在应用。","Thai Journal of Agricultural Science","2026-09-19T00:00:00Z",71,{"impact":77,"substance":78,"depth":79,"authority":77,"freshness":20,"relevant":21,"comment":80},12,21,17,"基于YOLOv8与多元回归的黄瓜幼苗活力无损估测，方法具体、指标完整，对智慧育苗有参考价值，但属细分作物研究，影响范围有限。",[82],{"name":73,"url":70},[26,27,28,84,85],"图像识别","黄瓜育苗",[87,88],"黄瓜 幼苗活力 图像处理","YOLOv8 幼苗 检测","黄瓜幼苗活力图像处理-3017","10.65764\u002Ftjas.2026.267412",{"doi":90,"openalex_id":92,"authors":93,"venue":73,"cited_by_count":35,"oa_url":70,"card":102,"direction":107,"ingested_from":62},"W7213631983",[94,96,98,100],{"name":95,"orcid":9},"Thanabodee Withunchettanan",{"name":97,"orcid":9},"Raksak Sermsak",{"name":99,"orcid":9},"Pichittra Kaewsorn",{"name":101,"orcid":9},"Kriengkri Kaewtrakulpong",{"tldr":103,"method":104,"finding":105,"direction":60,"opportunity":106},"用YOLOv8检测黄瓜真叶并结合多元回归，实现幼苗活力指数无损预测。","LED下拍摄14天幼苗，YOLOv8分割真叶，提取像素与RGB做多元线性回归。","YOLOv8检测mAP@0.5达96%，模型测试r=0.79，F1杂交种相关性达0.91。","可扩展多品种、多环境数据，融合时序图像与深度学习提升活力预测泛化性。","数字乡村与农业信息化","2026-09-20T23:30:26.929607Z",{"id":110,"title":111,"url":112,"summary":113,"summary_zh":9,"content":9,"source_name":114,"source_url":9,"published_at":115,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":116,"score_detail":117,"sources":121,"tags":123,"search_phrases":126,"slug":129,"view_count":35,"doi":9,"paper":130,"created_at":139},3000,"Plant-GeoAT：几何感知3D植物点云器官身份解析用于器官级表型分析","https:\u002F\u002Fwww.mdpi.com\u002F2073-4395\u002F16\u002F18\u002F1809","四川农业大学吴俊杰等提出Plant-GeoAT几何感知解析网络，在RGB融合前编码局部相对-XYZ邻域并将空间邻域与特征空间关系耦合用于密集点预测。在自建油菜数据集、基于图像的大豆数据集、激光扫描Pheno4D玉米和番茄数据集上评估，5个随机种子下mIoU分别达92.26±0.28%、82.50±0.24%、99.74±0.05%、94.75±0.15%，玉米Stem IoU达99.57±0.09%。","MDPI Agronomy 16(18):1809","2026-09-15T00:00:00Z",78,{"impact":17,"substance":118,"depth":17,"authority":119,"freshness":65,"relevant":21,"comment":120},23,13,"方法新颖、多作物多数据集验证且精度数据扎实，属器官级表型分析细分领域的重要技术进展，值得进入每日精选。",[122],{"name":114,"url":112},[26,27,29,124,125],"高通量表型","三维点云",[127,128],"四川农业大学 植物点云 器官识别","Plant-GeoAT 表型分析","四川农业大学植物点云器官识别-3000",{"doi":9,"openalex_id":9,"authors":131,"venue":9,"cited_by_count":35,"oa_url":9,"card":132,"direction":136,"ingested_from":138},[],{"tldr":133,"method":134,"finding":135,"direction":136,"opportunity":137},"提出几何感知网络Plant-GeoAT，实现3D植物点云器官身份解析与器官级表型分析。","编码局部相对XYZ邻域并耦合空间与特征空间关系，在油菜、大豆、玉米、番茄点云数据","五个数据集mIoU最高达99.74%，玉米茎IoU达99.57%，验证了几何感知对器官分割的有效性。","农业遥感与作物表型","可探索跨物种、跨传感器的轻量化几何感知模型，并推动器官级表型与基因型关联分析。","agent","2026-09-20T00:03:08.094512Z",{"id":141,"title":142,"url":143,"summary":144,"summary_zh":145,"content":9,"source_name":10,"source_url":143,"published_at":146,"category":12,"cover_url":9,"hotness":13,"is_selected":147,"score":148,"score_detail":149,"sources":154,"tags":156,"search_phrases":159,"slug":162,"view_count":21,"doi":163,"paper":164,"created_at":184},1755,"A non-destructive watermelon sweetness classification via vision transformer with cross-modal knowledge distillation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112393","A non-destructive watermelon sweetness classification via vision transformer with cross-modal knowledge distillation。Computers and Electronics in Agriculture","基于视觉Transformer与跨模态知识蒸馏的非破坏性西瓜甜度分类方法。计算机与农业电子学","2026-09-05T00:00:00Z",true,70,{"impact":150,"substance":151,"depth":17,"authority":150,"freshness":152,"relevant":21,"comment":153},15,20,2,"提出基于视觉Transformer与跨模态知识蒸馏的无损西瓜甜度分级方法，发表于权威期刊，方法新颖，对农产品品质检测有参考价值。",[155],{"name":10,"url":143},[26,27,28,157,158],"西瓜","模型蒸馏",[160,161],"农业人工智能 无损检测 智慧农业 模型蒸馏","农业人工智能 无损检测","农业人工智能无损检测智慧农业模型蒸馏-1755","10.1016\u002Fj.compag.2026.112393",{"doi":163,"openalex_id":165,"authors":166,"venue":10,"cited_by_count":35,"oa_url":9,"card":179,"direction":60,"ingested_from":62},"W7208829728",[167,170,173,176],{"name":168,"orcid":169},"Mustafa Kareem Hadi","https:\u002F\u002Forcid.org\u002F0000-0001-6469-3799",{"name":171,"orcid":172},"Siti Khairunniza Bejo","https:\u002F\u002Forcid.org\u002F0000-0002-4972-1701",{"name":174,"orcid":175},"Abdul Rashid Mohamed Shariff","https:\u002F\u002Forcid.org\u002F0000-0003-4626-4995",{"name":177,"orcid":178},"Nazmi Mat Nawi","https:\u002F\u002Forcid.org\u002F0000-0002-5916-5745",{"tldr":180,"method":181,"finding":182,"direction":60,"opportunity":183},"提出用视觉Transformer结合跨模态知识蒸馏，实现西瓜甜度的无损分类。","视觉Transformer与跨模态知识蒸馏，利用光谱数据辅助图像模型训练。","跨模态蒸馏可提升图像模型对西瓜甜度的分类精度，实现无损检测。","可探索将跨模态蒸馏用于其他水果内部品质（如糖度、酸度）的无损检测，或结合多传感器数据提升模型泛化性。","2026-09-06T23:30:01.479655Z",{"id":186,"title":187,"url":188,"summary":189,"summary_zh":190,"content":9,"source_name":191,"source_url":188,"published_at":192,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":75,"score_detail":193,"sources":196,"tags":198,"search_phrases":200,"slug":202,"view_count":35,"doi":203,"paper":204,"created_at":227},1536,"A Non-Invasive Approach for Detecting Water Adulteration in Orange Juice Using Computer Vision and Deep Learning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.jfca.2026.109484","Food fraud due to water adulteration in orange juice is a significant concern for the beverage industry. This study aimed to develop a rapid and non-invasive computer-vision method based on deep learning to detect and classify water-adulteration levels ranging from 1% to 15% in three orange juice products representing freshly squeezed juice, juice from concentrate, and orange nectar. High-resolution images were acquired under two shutter-speed-based exposure conditions: the higher-exposure acquisition condition (1\u002F30 s) and the lower-exposure acquisition condition (1\u002F250 s), while maintaining constant scene illumination, and were analyzed using ResNet50 convolutional neural networks. In the image-level hold-out test, the model trained with images acquired at 1\u002F250 s achieved an accuracy of 88.3%, whereas the model trained at 1\u002F30 s reached 83.1%. To provide a more stringent assessment of sample-level transferability, the previously trained and fixed 1\u002F250 s model was subsequently evaluated using 240 independently prepared and blindly coded samples obtained from subsequent purchases of the same commercial products. This independent blind validation achieved a 24-class accuracy of 86.7%. Misclassifications occurred predominantly between adjacent or closely related water-adulteration levels within the same juice product. When the independent-validation predictions were collapsed into a binary pure-versus-adulterated screening task, the model achieved 100.0% sensitivity, 93.3% specificity, 99.2% accuracy, and 96.7% balanced accuracy. These findings support the feasibility of the method as a rapid pre-screening tool for detecting visible-image patterns associated with controlled water dilution and show that detecting the presence of adulteration is more reliable than assigning an exact value to closely spaced adulteration levels. The independent validation provides evidence of transferability to newly prepared samples from subsequent purchases of the same products. However, further validation across additional brands, production batches, orange origins, seasons, and acquisition environments is required before broader applicability can be established.","橙汁中因掺水导致的食品欺诈是饮料行业关注的重要问题。本研究旨在开发一种基于深度学习的快速、非侵入性计算机视觉方法，用于检测和分类三种橙汁产品（鲜榨汁、浓缩还原汁和橙汁饮料）中1%至15%的掺水水平。在保持场景照明恒定的条件下，分别以两种基于快门速度的曝光条件采集高分辨率图像：高曝光采集条件（1\u002F30秒）和低曝光采集条件（1\u002F250秒），并使用ResNet50卷积神经网络进行分析。在图像级留出测试中，以1\u002F250秒采集图像训练的模型准确率达到88.3%，而以1\u002F30秒训练的模型准确率为83.1%。为对样本级可迁移性进行更严格的评估，先前训练并固定的1\u002F250秒模型随后被用于评估240个独立制备、盲法编码的样本，这些样本来自后续购买的同款商业产品。该独立盲法验证实现了24类别86.7%的准确率。误分类主要发生在同一果汁产品内相邻或相近的掺水水平之间。当独立验证预测结果被合并为二元纯正与掺假筛查任务时，模型实现了100.0%的灵敏度、93.3%的特异度、99.2%的准确率和96.7%的平衡准确率。这些发现支持该方法作为快速预筛查工具的可行性，用于检测与受控水稀释相关的可见图像模式，并表明检测掺假的存在比精确赋值于间隔较小的掺水水平更为可靠。独立验证提供了该方法对后续购买同款产品新制备样本具有可迁移性的证据。然而，在确立更广泛的适用性之前，仍需在更多品牌、生产批次、橙子产地、季节和采集环境中进行进一步验证。","Journal of Food Composition and Analysis","2026-09-01T00:00:00Z",{"impact":77,"substance":151,"depth":17,"authority":19,"freshness":194,"relevant":21,"comment":195},7,"研究提出基于深度学习的橙汁掺水无损检测方法，独立验证准确率高，对食品安全监管有参考价值。",[197],{"name":191,"url":188},[26,27,28,199],"食品安全",[201,161],"农业人工智能 无损检测 智慧农业 食品安全","农业人工智能无损检测智慧农业食品安全-1536","10.1016\u002Fj.jfca.2026.109484",{"doi":203,"openalex_id":205,"authors":206,"venue":191,"cited_by_count":35,"oa_url":221,"card":222,"direction":60,"ingested_from":62},"W7204957864",[207,209,211,214,216,218],{"name":208,"orcid":9},"Ana M. Pérez-Calabuig",{"name":210,"orcid":9},"Sandra Pradana‐López",{"name":212,"orcid":213},"John C. Cancilla","https:\u002F\u002Forcid.org\u002F0000-0003-3645-7224",{"name":215,"orcid":9},"María Luz Mena",{"name":217,"orcid":9},"Carlos López-Pingarrón",{"name":219,"orcid":220},"José S. Torrecilla","https:\u002F\u002Forcid.org\u002F0000-0003-1209-203X","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0889157526006277\u002Fpdf",{"tldr":223,"method":224,"finding":225,"direction":60,"opportunity":226},"用深度学习计算机视觉检测橙汁掺水，实现非侵入式快速筛查。","采集不同曝光图像，用ResNet50分类掺水等级，独立盲样验证。","掺水检测准确率高，区分精确等级较难，模型可迁移至新样本。","可扩展至其他食品掺假检测，需跨品牌、批次、季节等验证，或开发便携设备。","2026-09-03T23:30:50.596809Z",{"id":229,"title":230,"url":231,"summary":232,"summary_zh":9,"content":9,"source_name":233,"source_url":9,"published_at":234,"category":12,"cover_url":9,"hotness":13,"is_selected":147,"score":235,"score_detail":236,"sources":240,"tags":242,"search_phrases":247,"slug":250,"view_count":35,"doi":9,"paper":251,"created_at":258},3125,"Full-Season Agentic Farm System FAIRY: Event-Driven Multi-Agent Orchestration for Soybean Production（FAIRY 全季节智能体农场系统：大豆生产的事件驱动多智能体编排）","https:\u002F\u002Faiagentstore.ai\u002Fai-agent-news\u002Ftopic\u002Fagriculture-food\u002F2026-08-11","哈尔滨工业大学研究人员发布并部署全栈、事件驱动的智能体引擎 FAIRY 于中国运行中的大豆研究农场。FAIRY 集成传感器、无人机、卫星植被产品、机械 API、作物过程模型与多智能体编排层，执行起垄→播种→灌溉→病虫害防治→收获→干燥→存储工作流，并在 64 垄研究场上跨 100 个全季节场景评估 9 个智能体控制器。这是智能体系统能够在大农业时间尺度和延迟结果下进行推理的最清晰演示之一，将农业中的智能体工作从实验室演示推进到全过程评估。同期 arXiv 推出 HarvestBench 基准将 LLM 驱动智能体置于农场网格世界（拖拉机面临动物选择绕行或碾压），结果显示模型差异巨大、对道德简报高度敏感、避免意愿具有可衡量的价格弹性。","Harbin Institute of Technology \u002F arXiv","2026-09-18T00:00:00Z",89,{"impact":237,"substance":118,"depth":238,"authority":19,"freshness":20,"relevant":21,"comment":239},24,19,"哈工大在真实大豆农场部署全季节事件驱动多智能体系统并配套 HarvestBench 基准，是农业智能体从演示走向全过程评估的标志性进展，专业深度与信息增量俱佳。",[241],{"name":233,"url":231},[26,243,27,244,245,246],"无人农场","农业遥感","多智能体","大豆生产",[248,249],"哈工大 FAIRY 大豆","HarvestBench 智能体 农场","哈工大FAIRY大豆-3125",{"doi":9,"openalex_id":9,"authors":252,"venue":9,"cited_by_count":35,"oa_url":9,"card":253,"direction":60,"ingested_from":138},[],{"tldr":254,"method":255,"finding":256,"direction":60,"opportunity":257},"部署全季节事件驱动多智能体系统FAIRY，在大豆农场完成从起垄到存储的全流程评估。","集成传感器、无人机、卫星、作物模型与机械API，用9个智能体控制器在64垄100","智能体系统能在大农业时间尺度下推理，模型差异大且对道德简报敏感。","可研究多智能体在长周期、延迟反馈农业任务中的鲁棒性与伦理约束机制。","2026-09-22T00:05:38.611717Z",{"id":260,"title":261,"url":262,"summary":263,"summary_zh":9,"content":9,"source_name":264,"source_url":9,"published_at":234,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":116,"score_detail":265,"sources":267,"tags":269,"search_phrases":273,"slug":276,"view_count":35,"doi":9,"paper":277,"created_at":285},3120,"Autonomous Agricultural Machinery for Smart Agriculture: An Integrated Framework of Observation, Heterogeneity, and Intelligent Infrastructure（智慧农业自主农机：观测、异质性与智能基础设施一体化框架）","https:\u002F\u002Fwww.jstage.jst.go.jp\u002Farticle\u002Frdj\u002F5\u002F0\u002F5_576\u002F_article\u002F-char\u002Fen","Hongjin Li & Chunjiang Gao 在 Journal of Agricultural Information 5: 576-596 发表综述文章（J-STAGE 平台 2026-09-18 上线）：针对农业 4.0 时代自主农机核心问题——如何在复杂动态田间条件下将异构环境信息转化为可靠自适应可扩展的机器自主性，系统综述自主农机的技术基础、应用领域、性能优势与采用约束，并构建围绕\"观测、异质性、基础设施\"的一体化框架。研究不再按机器类型分类技术，而是考察多模态感知、AI 决策、自主导航控制、精准执行、多机协同之间的耦合关系，特别关注环境不确定性、实时决策、互操作性和系统级可扩展性的挑战。识别从孤立任务自动化向数据驱动自适应网络化农业自主性的渐进过渡，强调个体组件改进未必带来系统级性能提升，除非具备兼容的计算、通信、机械和制度基础设施。","J-STAGE \u002F Research Disclosure Journal",{"impact":17,"substance":78,"depth":79,"authority":119,"freshness":20,"relevant":21,"comment":266},"核心期刊综述，提出观测-异质性-基础设施一体化框架，对智慧农业自主农机研究有参考价值，但属学术综述、产业影响有限。",[268],{"name":264,"url":262},[26,27,270,271,272],"多模态感知","自主农机","农业4.0",[274,275],"自主农机 智慧农业 一体化框架","Hongjin Li Chunjiang Gao 自主农机","自主农机智慧农业一体化框架-3120",{"doi":9,"openalex_id":9,"authors":278,"venue":9,"cited_by_count":35,"oa_url":9,"card":279,"direction":283,"ingested_from":138},[],{"tldr":280,"method":281,"finding":282,"direction":283,"opportunity":284},"综述自主农机技术，提出观测、异质性、基础设施一体化框架。","系统综述多模态感知、AI决策、导航控制与多机协同的耦合关系。","组件改进未必提升系统性能，需兼容的计算、通信、机械与制度基础设施。","智慧农业 \u002F 农业物联网","可研究异构农机互操作协议与边缘计算架构，填补系统级可扩展性验证空白。","2026-09-22T00:05:38.042546Z"]