[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-795":3,"related-795":75},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":44,"search_phrases":69,"slug":72,"view_count":73,"doi":8,"paper":8,"created_at":74},795,"基于静态RGB图像的玉米种子活力早期筛选:一种采用Focal Loss和自动超参数调优的深度学习方法(原标题:Early-stage screening of maize seed vigor from static RGB images: A deep learning approach with Focal Loss and automated hyperparameter tuning)","https:\u002F\u002Fwww.ebiotrade.com\u002Fnewsf\u002F2026-8\u002F20260821002339259.htm","种子活力是种子质量与发芽潜力的关键指标,传统活力检测方法如四唑染色具有破坏性且需3-7天高强度人工操作,成为大规模播前筛选的关键瓶颈。本研究提出SeedFocusNet,集成浅层特征提取模块与基于Focal Loss的分类骨干网络,旨在增强对难以区分的高活力种子的识别。超参数通过Optuna框架结合贝叶斯优化在验证集上自动优化,ResNet50被选为最优架构。在测试集上对高活力种子识别的精确率达到74.39%,召回率达到54.46%。温室出苗实验进一步验证了SeedFocusNet筛选出的种子在同一品种内不同储藏时长下均表现出更高的出苗率。",null,"《Smart Agricultural Technology》：Early-stage screening of maize seed vigor from static RGB images: A deep learning approach with Focal Loss and automated hyperparameter tuning\n\n**编辑推荐：**\n\n种子活力（Seed vigor）是种子质量与发芽潜力的关键指标，其早期预测对于培育优质种子和提高玉米产量具有重要意义。在各种成像模态中，RGB成像因其简便性和低成本而受到广泛关注。然而，由于外部视觉特征与内部生理状态之间的相关性较弱，从单个萌发前RGB图像预测\n\n种子活力（Seed vigor）是种子质量与发芽潜力的关键指标，其早期预测对于培育优质种子和提高玉米产量具有重要意义。在各种成像模态中，RGB成像因其简便性和低成本而受到广泛关注。然而，由于外部视觉特征与内部生理状态之间的相关性较弱，从单个萌发前RGB图像预测种子活力仍然是一个重大挑战。为解决这一问题，研究人员提出了SeedFocusNet，一种集成浅层特征提取模块与基于Focal Loss的分类骨干网络的深度学习模型，旨在增强对难以区分的高活力种子的识别。超参数通过Optuna框架结合贝叶斯优化（Bayesian optimization）在验证集上自动优化。在比较多个骨干网络后，ResNet50被选为最优架构。在验证集上最大化S（评分函数）的操作点下，该模型在测试集上对高活力种子识别的精确率（precision）达到74.39%，召回率（recall）达到54.46%。温室出苗实验进一步验证了SeedFocusNet筛选出的种子在同一品种内不同储藏时长下均表现出更高的出苗率。这些结果表明，基于RGB图像的深度学习方法在受控实验室条件下具有种子活力筛选的应用潜力，为未来扩展到实际种植场景提供了基础。\n\n论文解读文章\n\n研究背景、问题与目的\n\n种子活力是种子科学中的基本指标，反映种子快速、均匀发芽并产生健壮幼苗的潜力，与产量潜力和籽粒品质密切相关。传统活力检测方法如四唑染色（tetrazolium staining）具有破坏性，且需要3-7天的高强度人工操作，成为大规模播前筛选的关键瓶颈。虽然X射线计算机断层扫描（CT）和高光谱成像等非破坏性方法可实现高精度活力分类（>95%），但这些技术通常需要专用仪器和实验装置，限制了其在常规或高通量应用中的实用性。相比之下，RGB成像具有易获取、成本低的优势，然而种子活力是内部生理性状，RGB图像捕捉的外部视觉特征（如颜色、表面纹理或形状的细微变化）与内部活力相关性较弱，导致基于RGB特征的预测仍具挑战性。现有研究显示，卷积神经网络（CNN）和视觉变换器（ViT）在此任务上结果均不可靠。因此，本研究从实际应用角度重新定义目标：不追求高总体分类准确率，而是聚焦于可靠识别高活力种子，并通过自定义评分函数平衡精确率与召回率，以实现实用筛选场景下的合理权衡。\n\n本研究旨在探索使用RGB图像进行玉米种子活力分级的潜力。具体目标包括：（1）构建带有活力标签的萌发前玉米种子图像数据集；（2）开发并优化用于高活力种子识别的深度学习模型，通过自动超参数调优；（3）系统评估和比较不同骨干架构的活力分类性能；（4）通过温室出苗试验验证模型预测效果。\n\n主要关键技术方法\n\n研究人员从湖南省种质资源库（Hunan Provincial Germplasm Bank of Crop Resources）获取了955粒在4°C下储藏3年的玉米种子（Zea mays L.）。关键方法包括：（1）图像预处理：将RGB图像转换至HSV色彩空间，仅对亮度通道进行直方图均衡化，再通过Otsu阈值分割、形态学开运算和最大连通分量提取，获得无背景的种子图像；（2）感兴趣区域（ROI）提取：利用凸包和旋转卡壳算法定位种脐端和合点端，通过阈值分割检测种脐区域，并生成种子损伤程度特征图，最终将原始图像与四个ROI（各224×224像素）沿通道维度拼接为15通道表示；（3）浅层特征融合网络：设计两层卷积网络（3×3核和1×1核）将15通道压缩为3通道特征图，增强特征表达；（4）分类骨干网络：采用ResNet50，结合Focal Loss（FL）函数，并通过Optuna框架结合贝叶斯优化自动调优超参数（α t、γ和学习率lr），以自定义评分函数S（S=TP×(Precision-p h)β）指导优化方向，平衡精确率与预测数量。\n\n研究结果\n\n3.1 种子发芽分析\n\n通过标准发芽实验，955粒种子中530粒（55.5%）被划分为高活力种子，425粒（44.5%）为低活力种子。发芽过程中，高活力种子在第3天平均重量（0.83 g）显著高于低活力种子（0.69 g），重量增长率（SE）在两组间分布差异明显。而静态数据（初始重量和掩膜面积）在活力组间高度重叠，基于12种形态特征和初始权重的分类（逻辑回归61.2%、随机森林58.6%、XGBoost 51.3%）准确率低，表明这些特征不可靠。\n\n3.2 SeedFocusNet性能\n\n3.2.1 超参数调优\n\n手动网格扫描发现，当Focal Loss的调节因子γ=2.5、α t=0.5时精确率最高（74.32%），α t 过高（0.9）导致精确率下降。Optuna自动调优在α t 0.62–0.74、γ 1.5–2.6、lr 0.0001–0.001范围内搜索，实现了精确率与预测数量的平衡。\n\n3.2.2 分类骨干网络基准测试\n\n在500次Optuna优化后，ResNet50在评分函数S=6.362时表现最佳，测试集精确率74.4%、召回率54.5%、TP=61。InceptionV3精确率最高（84.2%），但召回率低（28.6%）；ResNet18召回率最高（67.0%），但精确率较低（71.4%）。ResNet50在精确率和召回率间取得最佳平衡。\n\n3.2.3 消融研究与基线比较\n\n去掉ROI和浅层融合模块后，精确率降至72.97%，召回率降至48.21%；仅去掉浅层网络时召回率降至47.32%；仅去掉ROI时精确率降至71.08%。与优化后的交叉熵基线（精确率67.53%，召回率46.43%）相比，SeedFocusNet在精确率上相对提升10.2%，召回率提升17.3%。\n\n3.2.4 温室出苗验证\n\n对同一品种不同储藏时长（1年、2年、3年）的种子，SeedFocusNet筛选组出苗率分别达78.0%、76.0%、68.0%，而对照组分别为60.0%、54.0%、48.0%，绝对提升幅度为18.0–22.0个百分点，表明模型能有效识别具有更高出苗潜力的种子。\n\n讨论与结论\n\n本研究的局限性包括：数据集仅包含单一品种和单一老化历史，模型泛化性需验证；所有图像在受控实验室条件下采集，未评估现场环境下的鲁棒性；性能指标基于单次数据划分，未通过交叉验证量化稳定性；未系统研究模型学习的视觉特征。未来工作应通过多品种数据集收集、批次间验证、重复数据划分、外部测试和可解释性分析来解决这些限制。\n\n研究结论：本研究利用RGB图像预测冷储老化玉米种子活力。为满足实际筛选需求，研究人员将目标重新定义为最大化高活力种子的准确识别，开发了SeedFocusNet深度学习框架，集成浅层特征提取网络与深度分类骨干，结合Focal Loss和Optuna贝叶斯优化，以自定义评分函数平衡精确率与召回率。在验证集最大化S的操作点下，模型对高活力种子识别的精确率为74.4%，召回率为54.5%。温室出苗验证显示，筛选种子在不同储藏时长下出苗率绝对提升18.0–22.0个百分点。当优先考虑精确率时，模型可达到85.3%精确率（召回率25.9%），显示出对误报容忍度不同场景的灵活性。本研究结果表明，基于RGB的深度学习结合自动超参数调优，可为受控实验室条件下的种子活力筛选提供低成本、易获取的选项，并为后续田间验证奠定基础。","Smart Agricultural Technology 2026-08-21","2026-08-21T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":13,"relevant":21,"comment":22},15,22,18,12,1,"论文提出SeedFocusNet深度学习模型，结合Focal Loss和自动超参数调优，在玉米种子活力早期筛选上取得进展，方法新颖，数据详实，对智慧农业种子检测有参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"深度学习","玉米种子活力","Focal Loss","SeedFocusNet","智能农业技术",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":45,"locked":14,"version":46,"method":47,"evidence":48},"classified","2026-10-22.2","rules",{"candidates":49,"agricultural_evidence":52},[50,57,62],{"code":39,"score":51,"supported":52,"title":53,"abstract":55,"tags":56},17,true,[26,54],"deep learning",[],[26],{"code":32,"score":58,"supported":52,"title":59,"abstract":60,"tags":61},16,[34,33],[],[],{"code":63,"score":64,"supported":52,"title":65,"abstract":66,"tags":68},"B7",3,[],[67],"温室",[],[70,71],"智能农业技术 玉米种子活力 深度学习 SeedFocusNet","智能农业技术 玉米种子活力","智能农业技术玉米种子活力深度学习SeedFocusNet-795",5,"2026-08-21T00:05:57.711678Z",{"total":76,"page":21,"page_size":76,"items":77},6,[78,170,227,310,386,448],{"id":79,"title":80,"url":81,"summary":82,"summary_zh":83,"content":8,"source_name":84,"source_url":81,"published_at":85,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":86,"score_detail":87,"sources":91,"tags":93,"primary_topic":98,"secondary_topics":99,"classification":101,"search_phrases":127,"slug":130,"view_count":21,"doi":131,"paper":132,"created_at":169},5164,"Lightweight Hybrid CNN-Transformer Network for Robust Maize Leaf Disease Detection and Edge Deployment","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.50","Early and accurate detection of maize leaf diseases is essential for improving crop productivity and supporting precision agriculture.However, deep learning models trained on controlled leaf-image datasets often experience performance degradation under real-world agricultural conditions because of illumination variation, background clutter, occlusion, leaf orientation, and imaging noise.To address these challenges, this study develops a lightweight deep learning framework for robust maize leaf disease classification and edge-oriented deployment.The framework employs MobileNetV3-Small for efficient extraction of disease-discriminative visual features and investigates lightweight feature-learning strategies for improving classification under challenging field conditions.Experiments were conducted using PlantVillage-Maize and Field-Maize datasets comprising 6,188 images from four categories: Maize Leaf Blight (MLB), Common Rust, Healthy, and Leaf Spot.The image-only MobileNetV3-Small model achieved 97.8% accuracy and a 97.4% F1-score on the controlled PlantVillage-Maize dataset, while its performance decreased to 86.1% accuracy and an 83.9% F1-score on Field-Maize, highlighting the domain gap between controlled and real-field imagery.Robustness was further evaluated under Gaussian noise, illumination variation, and partial occlusion, together with computational-efficiency and edge-deployment analyses.The findings demonstrate the importance of lightweight and robust visual feature learning for practical maize disease diagnosis under real-world agricultural imaging conditions.","早期准确检测玉米叶片病害对于提高作物生产力和支持精准农业至关重要。然而，在受控叶片图像数据集上训练的深度学习模型，在真实农业条件下往往会出现性能下降，原因包括光照变化、背景杂乱、遮挡、叶片朝向以及成像噪声。为应对这些挑战，本研究开发了一个轻量级深度学习框架，用于稳健的玉米叶片病害分类和面向边缘的部署。该框架采用MobileNetV3-Small高效提取具有病害判别力的视觉特征，并研究轻量级特征学习策略，以提升在复杂田间条件下的分类性能。实验使用PlantVillage-Maize和Field-Maize数据集进行，共包含来自四个类别的6，188张图像：玉米大斑病（Maize Leaf Blight，MLB）、普通锈病（Common Rust）、健康（Healthy）和叶斑病（Leaf Spot）。仅使用图像的MobileNetV3-Small模型在受控的PlantVillage-Maize数据集上达到了97.8%的准确率和97.4%的F1分数，而在Field-Maize上的性能下降至86.1%的准确率和83.9%的F1分数，凸显了受控图像与真实田间图像之间的域差距。研究进一步在高斯噪声、光照变化和部分遮挡条件下评估了稳健性，并进行了计算效率和边缘部署分析。研究结果表明，轻量级且稳健的视觉特征学习对于真实农业成像条件下的实际玉米病害诊断具有重要意义。","International journal of intelligent engineering and systems","2026-10-16T00:00:00Z",69,{"impact":20,"substance":88,"depth":58,"authority":20,"freshness":89,"relevant":21,"comment":90},20,9,"该研究提出轻量级玉米叶病检测框架，并揭示受控数据集与田间数据之间的性能差距，方法扎实、结论有参考价值，但属细分技术论文，公共影响有限。",[92],{"name":84,"url":81},[94,95,96,26,97],"智慧农业","农业人工智能","边缘计算","玉米病害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[100],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":102},{"candidates":103,"agricultural_evidence":52},[104,109,114,122],{"code":32,"score":105,"supported":52,"title":106,"abstract":107,"tags":108},14,[33],[34,33],[],{"code":39,"score":110,"supported":52,"title":111,"abstract":112,"tags":113},8,[],[26,54],[95,26],{"code":115,"score":116,"supported":52,"title":117,"abstract":118,"tags":121},"I1",7,[],[119,120],"精准农业","precision agriculture",[94],{"code":123,"score":21,"supported":14,"title":124,"abstract":125,"tags":126},"I5",[],[],[96],[128,129],"MobileNetV3 玉米叶部病害","玉米叶片病害 边缘部署","MobileNetV3玉米叶部病害-5164","10.22266\u002Fijies2026.1130.50",{"doi":131,"openalex_id":133,"authors":134,"venue":84,"cited_by_count":160,"oa_url":81,"card":161,"direction":167,"ingested_from":168},"W7222602850",[135,138,141,143,145,148,150,152,155,157],{"name":136,"orcid":137},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":139,"orcid":140},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":142,"orcid":8},"Bhavani K",{"name":144,"orcid":8},"Sailee N. Panchbhai",{"name":146,"orcid":147},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":149,"orcid":8},"Manoj Kumar S B",{"name":151,"orcid":8},"Dharamvir",{"name":153,"orcid":154},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":156,"orcid":8},"Rani Chhagan Dalvi",{"name":158,"orcid":159},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",0,{"tldr":162,"method":163,"finding":164,"direction":165,"opportunity":166},"构建轻量MobileNetV3-Small框架实现玉米叶片病害分类并评估边缘部署。","MobileNetV3-Small，PlantVillage-Maize与Fie","受控数据准确率97.8%，田间降至86.1%，揭示明显域差距。","农业人工智能与决策模型","可研究跨域自适应与田间鲁棒特征学习，缩小受控与真实场景性能差距。","农业遥感与作物表型","openalex","2026-10-17T23:30:28.248539Z",{"id":171,"title":172,"url":173,"summary":174,"summary_zh":175,"content":8,"source_name":176,"source_url":173,"published_at":177,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":178,"score_detail":179,"sources":181,"tags":183,"primary_topic":186,"secondary_topics":187,"classification":189,"search_phrases":207,"slug":210,"view_count":160,"doi":211,"paper":212,"created_at":226},4759,"Machine Learning-based Prediction of SVI Parameter in Maize: A Comparative Study and Feature Importance Analysis","https:\u002F\u002Fdoi.org\u002F10.24925\u002Fturjaf.v14i10.2870-2879.9043","Background: Accurate estimation of seedling vigor indices (SVI) is critical for monitoring plant health and predicting yields in precision agriculture. This study comparatively evaluates the performance of different machine learning algorithms in estimating the SVI parameter. Methods: Germination data were collected from 39 maize genotypes under three different salinity conditions (0 mM, 100 mM, and 200 mM NaCl), including the parameters Gmax, MGT, GI, SL, RL, SdL, SMR, RMR, and SVI. The dataset was preprocessed through normalization to the [0–1] range. The SVI parameter was estimated using four different machine learning methods: Random Forest, CatBoost, LightGBM, and Support Vector Regression (SVR). To evaluate the performance of the models, both 10-fold cross-validation and 80%–20% hold-out validation techniques were employed. The model performance was examined using RMSE, MSE, MAE, and R² metrics. Results: The findings show that all models have a high explanatory power in the training dataset. Specifically, the CatBoost model showed the highest success in the training phase (R²=0.9962), whereas the SVR model achieved the highest generalization performance on the test dataset (R²=0.9712, RMSE=0.0582). Feature importance analysis results revealed that the 'App' parameter had the highest impact on the target variable in most models, but different structural interactions were prominent in the LightGBM model. The results demonstrate that machine learning techniques provide high accuracy in SVI estimation and that the tendency towards overfitting is limited. Conclusions: In conclusion, this study confirms that machine learning techniques are powerful and reliable tools for estimating spectral indices in precision agriculture applications. The integration of SVR and ensemble-based models into agricultural decision support systems is expected to significantly contribute to optimizing resource use and improving yield predictions.","背景：准确估计幼苗活力指数（SVI）对于精准农业中监测植物健康和预测产量至关重要。本研究比较评估了不同机器学习算法在估计SVI参数方面的性能。方法：从39个玉米基因型在三种不同盐度条件（0 mM、100 mM和200 mM NaCl）下收集发芽数据，包括Gmax、MGT、GI、SL、RL、SdL、SMR、RMR和SVI等参数。数据集通过归一化至[0–1]范围进行预处理。采用四种不同的机器学习方法估计SVI参数：随机森林、CatBoost、LightGBM和支持向量回归（SVR）。为评估模型性能，采用了10折交叉验证和80%–20%留出验证技术。使用RMSE、MSE、MAE和R²指标检验模型性能。结果：研究结果表明，所有模型在训练数据集中均具有较高的解释力。具体而言，CatBoost模型在训练阶段表现出最高的成功率（R²=0.9962），而SVR模型在测试数据集上取得了最高的泛化性能（R²=0.9712，RMSE=0.0582）。特征重要性分析结果显示，在大多数模型中，“App”参数对目标变量的影响最大，但在LightGBM模型中不同的结构交互作用更为突出。结果表明，机器学习技术在SVI估计中提供了高精度，且过拟合倾向有限。结论：总之，本研究证实机器学习技术是精准农业应用中估计光谱指数的强大而可靠的工具。将SVR和基于集成的模型整合到农业决策支持系统中，预计将显著有助于优化资源利用和改善产量预测。","Turkish Journal of Agriculture - Food Science and Technology","2026-10-11T00:00:00Z",63,{"impact":110,"substance":19,"depth":58,"authority":20,"freshness":89,"relevant":21,"comment":180},"方法对比扎实、结论可靠，但属细分领域论文，产业影响有限，适合主题聚合而非头条精选。",[182],{"name":176,"url":173},[94,95,184,34,185],"机器学习","耐盐育种",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[188],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":190},{"candidates":191,"agricultural_evidence":52},[192,199,203],{"code":39,"score":193,"supported":52,"title":194,"abstract":196,"tags":198},19,[195],"machine learning",[184,195,197],"decision support",[95,184],{"code":32,"score":17,"supported":52,"title":200,"abstract":201,"tags":202},[33],[34,33],[34],{"code":115,"score":116,"supported":52,"title":204,"abstract":205,"tags":206},[],[119,120],[94],[208,209],"玉米 SVI 机器学习","玉米 耐盐 幼苗活力指数","玉米SVI机器学习-4759","10.24925\u002Fturjaf.v14i10.2870-2879.9043",{"doi":211,"openalex_id":213,"authors":214,"venue":176,"cited_by_count":160,"oa_url":173,"card":221,"direction":165,"ingested_from":168},"W7221462188",[215,218],{"name":216,"orcid":217},"Mustafa Turan Arslan","https:\u002F\u002Forcid.org\u002F0000-0001-5498-6571",{"name":219,"orcid":220},"Gülay Zülkadir","https:\u002F\u002Forcid.org\u002F0000-0003-3488-4011",{"tldr":222,"method":223,"finding":224,"direction":165,"opportunity":225},"用四种机器学习模型基于39个玉米基因型盐胁迫发芽数据预测幼苗活力指数SVI。","39个玉米基因型在三种盐浓度下的发芽数据，归一化后用RF、CatBoost、Li","SVR泛化最优（R²=0.9712），CatBoost训练拟合最高；App参数对SVI影响最大。","可扩展到多作物多胁迫环境，结合光谱或图像表型数据提升SVI预测的田间适用性。","2026-10-12T23:30:44.762497Z",{"id":228,"title":229,"url":230,"summary":231,"summary_zh":232,"content":8,"source_name":233,"source_url":230,"published_at":234,"category":12,"cover_url":8,"hotness":13,"is_selected":52,"score":235,"score_detail":236,"sources":238,"tags":240,"primary_topic":242,"secondary_topics":243,"classification":245,"search_phrases":272,"slug":275,"view_count":73,"doi":276,"paper":277,"created_at":309},3842,"Raspberry Pi Lightweight Deep Learning Models Deployed for Corn Growth Stage Classification Using PhenoCam Images","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193337","Identifying crop growth stages is essential for comprehensive assessment that facilitates timely and precise agronomic management. However, conventional field-based manual scouting is labor-intensive, time-consuming, and lacks scalability. Digital field images with advanced models deployed on portable edge-computing devices offer an alternative solution for real-time crop monitoring and decision support. Therefore, in this study, the standard 8 corn growth stages were defined as 8 classes based on distinct visual canopy appearance patterns observed in PhenoCam (near-surface [proximal] remote sensing network camera) imagery collected from 10 PhenoCam sites. These classes do not correspond directly to standard agronomic vegetation and reproductive growth stages. For modeling, four lightweight deep learning (DL) models, ELiteCrop0, ELiteCrop1, ELiteCrop4, and MobNetCropV2, were developed and evaluated across five image vertical clipping levels (0–40%) using a supercomputer (NDSU CCAST). The optimized model was subsequently deployed on a single-board Raspberry Pi 5 computer for edge inference. Model training accounted for the majority of the total CPU time, exceeding 97%, while the testing times ranged from 0.01–0.12 min, enabling real-time applications. Among the models, ELiteCrop0 achieved the most balanced performance with a confusion-matrix diagonal ratio (CMDR) of 0.93, followed by ELiteCrop1 (CMDR = 0.92). Overall, model performance decreased with increasing vertical clipping; therefore, a moderate image clipping (0–10%) was recommended for improved computational efficiency. Analysis with a supercomputer produced an intrasite (same training sites) accuracy of 0.90–0.93 (Raspberry Pi: 0.78–0.81) and an intersite (unseen test sites) accuracy of 0.48–0.50 (Raspberry Pi: 0.41–0.43), indicating challenges with model generalization. Raspberry Pi processed ≈ 1000 images\u002Fmin at 68 °C, with a PhenoCam:Raspberry Pi processing ratio of 1:2500 at 50% capacity over an 8 h day. Overall, this study presents a scalable and cost-effective solution for real-time corn growth stage monitoring in precision agriculture, which could be extended to other crops.","识别作物生长阶段对于全面评估、促进及时精准的农艺管理至关重要。然而，传统的田间人工巡查劳动强度大、耗时且缺乏可扩展性。部署在便携式边缘计算设备上的数字田间图像与先进模型为实时作物监测和决策支持提供了替代方案。因此，本研究基于从10个PhenoCam（近地面[近端]遥感网络相机）站点采集的影像中观察到的不同冠层视觉外观模式，将标准的8个玉米生长阶段定义为8个类别。这些类别并不直接对应于标准的农艺营养生长和生殖生长阶段。在建模方面，开发了四种轻量级深度学习（DL）模型——ELiteCrop0、ELiteCrop1、ELiteCrop4和MobNetCropV2，并利用超级计算机（NDSU CCAST）在五种图像垂直裁剪水平（0–40%）下进行了评估。随后，优化后的模型被部署到单板Raspberry Pi 5计算机上进行边缘推理。模型训练占总CPU时间的大部分，超过97%，而测试时间为0.01–0.12分钟，支持实时应用。在各模型中，ELiteCrop0实现了最均衡的性能，混淆矩阵对角线比率（CMDR）为0.93，其次是ELiteCrop1（CMDR = 0.92）。总体而言，模型性能随垂直裁剪比例的增加而下降；因此，建议采用适度的图像裁剪（0–10%）以提高计算效率。使用超级计算机的分析得出站内（相同训练站点）准确率为0.90–0.93（Raspberry Pi：0.78–0.81），站间（未见测试站点）准确率为0.48–0.50（Raspberry Pi：0.41–0.43），表明模型泛化面临挑战。Raspberry Pi在68 °C下处理约1000张图像\u002F分钟，在8小时工作日50%容量下，PhenoCam与Raspberry Pi的处理比为1:2500。总体而言，本研究为精准农业中的实时玉米生长阶段监测提供了一种可扩展且经济高效的解决方案，并可扩展至其他作物。","Remote Sensing","2026-09-29T00:00:00Z",81,{"impact":19,"substance":18,"depth":19,"authority":105,"freshness":89,"relevant":21,"comment":237},"该研究将轻量深度学习模型部署于树莓派实现玉米生育期实时识别，方法新颖、数据扎实，对精准农业边缘监测有参考价值。",[239],{"name":233,"url":230},[94,95,96,34,241],"遥感",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[244],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":246},{"candidates":247,"agricultural_evidence":52},[248,252,257,261,267],{"code":39,"score":19,"supported":52,"title":249,"abstract":250,"tags":251},[54],[26,54,197],[95],{"code":32,"score":17,"supported":52,"title":253,"abstract":255,"tags":256},[254],"corn",[34,254],[34],{"code":115,"score":116,"supported":52,"title":258,"abstract":259,"tags":260},[],[119,120],[94],{"code":262,"score":116,"supported":52,"title":263,"abstract":264,"tags":266},"I3",[],[241,265],"remote sensing",[241],{"code":123,"score":268,"supported":52,"title":269,"abstract":270,"tags":271},4,[],[96],[96],[273,274],"Raspberry Pi 玉米 生长阶段","PhenoCam 玉米 深度学习","RaspberryPi玉米生长阶段-3842","10.3390\u002Frs18193337",{"doi":276,"openalex_id":278,"authors":279,"venue":233,"cited_by_count":160,"oa_url":230,"card":304,"direction":167,"ingested_from":168},"W7214787420",[280,283,286,289,292,295,298,301],{"name":281,"orcid":282},"Anne Joice","https:\u002F\u002Forcid.org\u002F0000-0001-7499-9222",{"name":284,"orcid":285},"Humeera Tazeen","https:\u002F\u002Forcid.org\u002F0000-0003-2411-0725",{"name":287,"orcid":288},"Talha Tufaique","https:\u002F\u002Forcid.org\u002F0000-0002-4490-5341",{"name":290,"orcid":291},"Mathala Juliet Gupta","https:\u002F\u002Forcid.org\u002F0000-0002-3886-2429",{"name":293,"orcid":294},"Cannayen Igathinathane","https:\u002F\u002Forcid.org\u002F0000-0001-8884-7959",{"name":296,"orcid":297},"Nitin Rai","https:\u002F\u002Forcid.org\u002F0000-0002-9350-9601",{"name":299,"orcid":300},"Craig W. Whippo","https:\u002F\u002Forcid.org\u002F0000-0002-7626-6919",{"name":302,"orcid":303},"David Walter Archer","https:\u002F\u002Forcid.org\u002F0000-0002-4816-7040",{"tldr":305,"method":306,"finding":307,"direction":167,"opportunity":308},"用PhenoCam图像训练轻量深度学习模型，在树莓派上实时分类玉米8个生长阶段。","基于10个PhenoCam站点图像，开发4种轻量DL模型，在树莓派5上边缘推理。","ELiteCrop0表现最佳（CMDR=0.93），站点内精度0.90-0.93，但站点间泛化差（0","站点间泛化差是主要瓶颈，可研究跨站点迁移学习或域适应以提升模型鲁棒性。","2026-09-30T23:30:29.168194Z",{"id":311,"title":312,"url":313,"summary":314,"summary_zh":8,"content":315,"source_name":316,"source_url":8,"published_at":317,"category":318,"cover_url":8,"hotness":13,"is_selected":14,"score":319,"score_detail":320,"sources":322,"tags":324,"primary_topic":330,"secondary_topics":336,"classification":339,"search_phrases":380,"slug":383,"view_count":384,"doi":8,"paper":8,"created_at":385},3396,"从吃到用——中国农科院第八届农科开放日现场直击：彩色胡萝卜、丙醇二酸黄瓜、甜糯同粒玉米、转运机器人、动物疾病风险大模型","https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml","9月19日中国农科院36个研究所的560多项最新科研成果集中亮相：彩色胡萝卜、橘红心白菜、特色彩椒等全新果蔬品种轮番展示；富含丙醇二酸的晶莹剔透黄瓜能阻止糖类转化为脂肪；低豆腥味、高异黄酮、适合榨汁的大豆及'甜糯同粒'玉米；农业转运机器人能扛100公斤以上作物在丘陵山区跑、具备原地掉头能力；正在研发的全球动物疾病风险大模型将对动物疫病实现实时预报预警。","[首页](https:\u002F\u002Fwww.cctv.cn\u002F)\n\n[时政](javascript:;)\n\n[新闻](https:\u002F\u002Fnews.cctv.cn\u002F)\n\n[评论](https:\u002F\u002Fopinion.cctv.cn\u002F)\n\n[视频](https:\u002F\u002Fv.cctv.cn\u002F)\n\n[财经](https:\u002F\u002Ffinance.cctv.cn\u002Findex.shtml)\n\n[体育](https:\u002F\u002Fsports.cctv.cn\u002F)\n\n[教育](https:\u002F\u002Fedu.cctv.cn\u002F)\n\n[熊猫](https:\u002F\u002Fwww.ipanda.cn\u002F)\n\n[直播中国](https:\u002F\u002Flivechina.cctv.cn\u002F)\n\n[4K](https:\u002F\u002Ftv.cctv.cn\u002F4K\u002Findex.shtml)\n\n[CCTV.直播](https:\u002F\u002Ftv.cctv.cn\u002Findex.shtml)\n\n[中](https:\u002F\u002Fwww.cctv.cn\u002Findex.shtml)\n\n[](https:\u002F\u002Faigc.cctv.cn\u002Findex.shtml \"AIGC\")\n\n[](javascript:; \"盲人用户进入后，若无读屏软件可通过Ctrl+Alt+V开启声音获取语音提示\")\n\n[](javascript:void(0);)\n\n*   [人民领袖习近平](https:\u002F\u002Fnews.cctv.cn\u002Frmlx\u002Findex.shtml)\n*   [联播+](https:\u002F\u002Fnews.cctv.cn\u002Flbj\u002Findex.shtml)\n*   [中国领导人](https:\u002F\u002Fleaders.cctv.cn\u002F)\n*   [央视快评](https:\u002F\u002Fnews.cctv.cn\u002Fyskp\u002Findex.shtml)\n*   [习式妙语](https:\u002F\u002Fv.cctv.cn\u002Fshizheng\u002Fxsmy\u002Findex.shtml)\n*   [热解读](https:\u002F\u002Fnews.cctv.cn\u002Frjd\u002F)\n*   [天天学习](https:\u002F\u002Fnews.cctv.cn\u002Ftiantianxuexi\u002Findex.shtml)\n\n*   [直播](https:\u002F\u002Ftv.cctv.cn\u002Flive\u002Findex.shtml)\n*   [片库](https:\u002F\u002Ftv.cctv.cn\u002Fyxg\u002Findex.shtml)\n*   [栏目大全](https:\u002F\u002Ftv.cctv.cn\u002Flm\u002Findex.shtml)\n*   [节目单](https:\u002F\u002Ftv.cctv.cn\u002Fepg\u002Findex.shtml)\n*   [听音](https:\u002F\u002Ftv.cctv.cn\u002Fty\u002Fm\u002Findex.shtml)\n*   [微视频](https:\u002F\u002Ftv.cctv.cn\u002Fwsp\u002Fm\u002Findex.shtml)\n*   [主持人](https:\u002F\u002Ftv.cctv.cn\u002Fzhuchiren\u002Findex.shtml)\n*   [下载央视影音](https:\u002F\u002Fapp.cctv.cn\u002Findex.shtml#page5)\n\n*   [海外频道](https:\u002F\u002Fglobal.cctv.cn\u002F)\n*   [iPanda](https:\u002F\u002Fen.ipanda.com\u002F)\n*   [English](https:\u002F\u002Fenglish.cctv.cn\u002F)\n*   [Монгол](https:\u002F\u002Fmn.cctv.cn\u002F)\n*   [![Image 5](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652856235095_854.png)![Image 6](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652856239393_131.png)](https:\u002F\u002Fmongol.cctv.cn\u002F)\n*   [![Image 7](https:\u002F\u002Fp3.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691224953149_874.png)![Image 8](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691224956116_551.png)](http:\u002F\u002Fwww.tibetcnr.com\u002F)\n*   [![Image 9](https:\u002F\u002Fp3.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691224981945_575.png)![Image 10](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691224983459_899.png)](http:\u002F\u002Fwww.uycnr.com\u002F)\n*   [![Image 11](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691225001997_335.png)![Image 12](https:\u002F\u002Fp3.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691225003416_711.png)](http:\u002F\u002Fwww.kazakcnr.com\u002F)\n*   [![Image 13](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691225018456_630.png)![Image 14](https:\u002F\u002Fp1.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2023\u002F8\u002F5\u002F1691225020349_640.png)](http:\u002F\u002Fwww.krcnr.cn\u002F)\n\n*   [地方](https:\u002F\u002Flocal.cctv.cn\u002Findex.shtml)\n*   [乡村振兴](https:\u002F\u002Fxczx.cctv.cn\u002Findex.shtml)\n*   [生态](https:\u002F\u002Feco.cctv.cn\u002F)\n*   [一带一路](https:\u002F\u002Fydyl.cctv.cn\u002F)\n*   [央博](https:\u002F\u002Fyangbo.cctv.cn\u002F)\n*   [文化](https:\u002F\u002Fwww.cctv.cn\u002Fculture\u002Findex.shtml)\n*   [旅游](https:\u002F\u002Fculture-travel.cctv.cn\u002F)\n*   [科普](https:\u002F\u002Fkepu.cctv.cn\u002F)\n*   [健康](https:\u002F\u002Fjiankang.cctv.cn\u002F)\n*   [乐龄](https:\u002F\u002Flaoling.cctv.cn\u002Findex.shtml)\n*   [阅读](https:\u002F\u002Fbook.cctv.cn\u002F)\n*   [艺术](https:\u002F\u002Farts.cctv.cn\u002F)\n*   [数智](https:\u002F\u002F5gai.cctv.cn\u002F)\n*   [5G](https:\u002F\u002F5g.cctv.cn\u002F)\n*   [产业+](https:\u002F\u002Fbusiness.cctv.cn\u002F)\n*   [央央好物](https:\u002F\u002Fwww.cctvmall.com\u002F)\n\n网页\n\n[网页](javascript:void(0))[视频](javascript:void(0))\n\n[热搜榜](https:\u002F\u002Ftv.cctv.cn\u002Ftop\u002F)\n\n- [x]下次自动登录[忘记密码](http:\u002F\u002Freg.cntv.cn\u002FforgetPassword\u002FfindPassword.jsp)\n\n[登录](javascript:void(0);)[立即注册](http:\u002F\u002Freg.cctv.cn\u002Fregist.html?from=http:\u002F\u002Fwww.cctv.cn)\n\n使用合作网站账号登录[![Image 15: 微信](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Ftemplet\u002Fcommon\u002FDEPA1381197220279381\u002Fcooper_wx_141230.png)](javascript:;)[![Image 16: QQ](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Ftemplet\u002Fcommon\u002FDEPA1381197220279381\u002Fcooper_qq_10886_140506.png)](javascript:;)[![Image 17: 新浪网](https:\u002F\u002Fp1.img.cntv.cn\u002FphotoAlbum\u002Ftemplet\u002Fcommon\u002FDEPA1441519391707376\u002Fcooper_wb_13730_151019.png)](javascript:;)[![Image 18: 支付宝](https:\u002F\u002Fp1.img.cntv.cn\u002FphotoAlbum\u002Ftemplet\u002Fcommon\u002FDEPA1456645307521846\u002Fzfb_14686_160513.png)](javascript:;)\n\n![Image 19](https:\u002F\u002Fp1.img.cntv.cn\u002FphotoAlbum\u002Ftemplet\u002Fcommon\u002FDEPA1652643499621200\u002FmapLogo.png)\n\n[总台春晚](https:\u002F\u002Fchunwan.cctv.cn\u002F)[网络春晚](https:\u002F\u002Fwlchunwan.cctv.com\u002F)[共产党员网](https:\u002F\u002Fwww.12371.cn\u002F)[秧纪录](http:\u002F\u002Fjishi.cntv.cn\u002Fspecial\u002Fzgjlyx\u002Findex.shtml)[纪录片网](http:\u002F\u002Fwww.docuchina.cn\u002F)[国家大剧院](http:\u002F\u002Fncpa-classic.cntv.cn\u002Findex.shtml)[大型活动](https:\u002F\u002Fgongyi.cctv.cn\u002Fevents\u002F)\n\n[新闻](https:\u002F\u002Fnews.cctv.cn\u002F)[国内](https:\u002F\u002Fnews.cctv.cn\u002Fchina\u002F)[国际](https:\u002F\u002Fnews.cctv.cn\u002Fworld\u002F)[评论](https:\u002F\u002Fopinion.cctv.cn\u002F)[经济](https:\u002F\u002Fjingji.cctv.cn\u002F)[军事](https:\u002F\u002Fmilitary.cctv.cn\u002Findex.shtml)[科技](https:\u002F\u002Fnews.cctv.cn\u002Ftech\u002Findex.shtml)[法治](https:\u002F\u002Fnews.cctv.cn\u002Flaw\u002F)[文娱](https:\u002F\u002Fnews.cctv.cn\u002Fent\u002F)[人物](https:\u002F\u002Fpeople.cctv.cn\u002F)[公益](https:\u002F\u002Fgongyi.cctv.cn\u002F)[图片](https:\u002F\u002Fphoto.cctv.cn\u002F)\n\n[人民领袖习近平](https:\u002F\u002Fnews.cctv.cn\u002Frmlx\u002Findex.shtml)[联播+](https:\u002F\u002Fnews.cctv.cn\u002Flbj\u002Findex.shtml)[热解读](https:\u002F\u002Fnews.cctv.cn\u002Frjd\u002F)[天天学习](https:\u002F\u002Fnews.cctv.cn\u002Ftiantianxuexi\u002Findex.shtml)[习式妙语](https:\u002F\u002Fv.cctv.cn\u002Fshizheng\u002Fxsmy\u002Findex.shtml)[央视快评](https:\u002F\u002Fnews.cctv.cn\u002Fyskp\u002Findex.shtml)[央视网评](https:\u002F\u002Fopinion.cctv.cn\u002Fyswp\u002Findex.shtml)[光华锐评](https:\u002F\u002Fghrp.cctv.cn\u002Findex.shtml)[锋面](https:\u002F\u002Fnews.cctv.cn\u002Ffengmian\u002Findex.shtml)\n\n[视频](https:\u002F\u002Fv.cctv.cn\u002F)[小央视频](https:\u002F\u002Fv.cctv.cn\u002Fxysp\u002Findex.shtml)[小央直播](https:\u002F\u002Fv.cctv.cn\u002Fzhangbo\u002Findex.shtml)[直播中国](https:\u002F\u002Flivechina.cctv.cn\u002F)[熊猫频道](https:\u002F\u002Fwww.ipanda.cn\u002F)[VR\u002FAR](https:\u002F\u002Fv.cctv.cn\u002FVR\u002Findex.shtml)[4K专区](https:\u002F\u002Ftv.cctv.cn\u002F4K\u002Findex.shtml)[全景新闻](http:\u002F\u002Fnews.cctv.cn\u002Fyuanchuang\u002FVR\u002Findex.shtml)\n\n[现场](https:\u002F\u002Fv.cctv.cn\u002Fzixun\u002Fxc\u002Findex.shtml)[前线](https:\u002F\u002Fv.cctv.cn\u002Fzixun\u002Fqx\u002Findex.shtml)[比划](https:\u002F\u002Fv.cctv.cn\u002Freping\u002Fbh\u002Findex.shtml)[快看](https:\u002F\u002Fnews.cctv.cn\u002Fkuaikan\u002Findex.shtml)[蓝海中国](https:\u002F\u002Fv.cctv.cn\u002Fjishi\u002Flhzglhzg\u002Findex.shtml)[新兵请入列](https:\u002F\u002Fv.cctv.cn\u002Fjishi\u002Fjsxbqrl\u002Findex.shtml)[人生第一次](https:\u002F\u002Fv.cctv.cn\u002Fjishi\u002Frsdyc\u002Findex.shtml)[人生第二次](https:\u002F\u002Fv.cctv.cn\u002Fjishi\u002Fjsrsdec\u002F)\n\n[体育](https:\u002F\u002Fsports.cctv.cn\u002F)[直播](https:\u002F\u002Ftv.cctv.cn\u002Flive\u002Fcctv5\u002F)[竞猜](https:\u002F\u002Fcbs.sports.cctv.cn\u002F)[2026年亚运会](https:\u002F\u002Fyayun.cctv.cn\u002F2026\u002Findex.shtml)[2026年世界杯](https:\u002F\u002Fworldcup.cctv.cn\u002F2026\u002Findex.shtml)[2026年冬奥会](https:\u002F\u002Fsports.cctv.cn\u002FMilano2026\u002F)[CBA](https:\u002F\u002Fsports.cctv.cn\u002Fcba\u002F)[NBA](https:\u002F\u002Fsports.cctv.cn\u002Fnba\u002F)[中超](https:\u002F\u002Fsports.cctv.cn\u002Fcsl\u002F)[国足](https:\u002F\u002Fsports.cctv.cn\u002Ffootball\u002Fchina\u002F)[国际足球](https:\u002F\u002Fsports.cctv.cn\u002Ffootball\u002Finternational\u002Findex.shtml)[网球](https:\u002F\u002Fsports.cctv.cn\u002Ftennis\u002F)[综合体育](https:\u002F\u002Fsports.cctv.cn\u002Fzong\u002Findex.shtml)\n\n[VIP会员](https:\u002F\u002Fvip.sports.cctv.cn\u002F)[CCTV奥林匹克频道](https:\u002F\u002Fsports.cctv.cn\u002Folympicportal\u002Findex.shtml)[生活体育大会](https:\u002F\u002Fsports.cctv.cn\u002Fspecial\u002Fclsc\u002Findex.shtml)[体育江湖](https:\u002F\u002Fsports.cctv.cn\u002Fspecial\u002FJianghu\u002Findex.shtml)[文化体育](https:\u002F\u002Fsports.cctv.cn\u002Fwlty\u002Findex.shtml)[冰雪道路](https:\u002F\u002Fsports.cctv.cn\u002Fspecial\u002Ffootprintsinthesnow\u002Findex.shtml)[足球道路](http:\u002F\u002Fworldcup.cctv.cn\u002F2018\u002Flm\u002Ffootballroadmap\u002F)\n\n[财经](https:\u002F\u002Ffinance.cctv.cn\u002Findex.shtml)[教育](https:\u002F\u002Fedu.cctv.cn\u002F)[乡村振兴](https:\u002F\u002Fxczx.cctv.cn\u002Findex.shtml)[生态环境](https:\u002F\u002Feco.cctv.cn\u002F)[一带一路](http:\u002F\u002Fydyl.cctv.cn\u002F)[央博](https:\u002F\u002Fyangbo.cctv.cn\u002F)[非遗](https:\u002F\u002Fchina-feiyi.cctv.cn\u002F)[文化](https:\u002F\u002Fwww.cctv.cn\u002Fculture\u002Findex.shtml)[旅游](https:\u002F\u002Fculture-travel.cctv.cn\u002F)[科普](https:\u002F\u002Fkepu.cctv.cn\u002F)[健康](https:\u002F\u002Fjiankang.cctv.cn\u002F)[乐龄](https:\u002F\u002Flaoling.cctv.cn\u002Findex.shtml)[阅读](https:\u002F\u002Fbook.cctv.cn\u002F)[艺术](https:\u002F\u002Farts.cctv.cn\u002Findex.shtml)[汽车](https:\u002F\u002Fauto.cctv.cn\u002F)[数智](https:\u002F\u002F5gai.cctv.cn\u002F)[5G](https:\u002F\u002F5g.cctv.cn\u002F)[产业+](https:\u002F\u002Fbusiness.cctv.cn\u002F)\n\n[大国智造](https:\u002F\u002Fjingji.cctv.cn\u002Fspecial\u002Fdgzz\u002Fhome\u002Findex.shtml)[大国展会](https:\u002F\u002Fv.cctv.cn\u002Flive_zb\u002FLIVE3386.html?pageid=3386&tag=MicroLiveType)[大国保险](https:\u002F\u002Ffinance.cctv.cn\u002Fspecial\u002Fdaguobaoxian\u002Fhome\u002Findex.shtml)[云顶对话](https:\u002F\u002Ffinance.cctv.cn\u002Fspecial\u002Fyunding\u002Findex.shtml)[云起](https:\u002F\u002Flocal.cctv.cn\u002Fzt\u002Fyunqi\u002F)[超级工厂](https:\u002F\u002Fbusiness.cctv.cn\u002Fspecial\u002Fcjgc\u002Findex.html)[智敬中国](https:\u002F\u002F5gai.cctv.cn\u002FZJZG\u002Findex.shtml)[全民健康](https:\u002F\u002Fedu.cctv.cn\u002F2022\u002F08\u002F24\u002FVIDA9GgWzG2ywQ4nu0h078fv220824.shtml)[颜选攻略](https:\u002F\u002Fedu.cctv.cn\u002F2021\u002F06\u002F01\u002FVIDAEeKQjpGs6E8CrdT0uPf9210601.shtml)[海洋](https:\u002F\u002Focean.cctv.cn\u002F)[时尚](https:\u002F\u002Fstyle.cctv.cn\u002F)[天气](http:\u002F\u002Fweather.cctv.cn\u002Findex.shtml)[才艺](https:\u002F\u002Fcaiyi.cctv.cn\u002Fcy\u002F1\u002Findex.shtml)[网展](https:\u002F\u002Fwangzhan.cctv.cn\u002F)[央央好物](https:\u002F\u002Fwww.cctvmall.com\u002F)\n\n[![Image 20](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857455273_78.png)](https:\u002F\u002Flocal.cctv.cn\u002Findex.shtml)[![Image 21](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857468382_741.png)](https:\u002F\u002Fsh.cctv.cn\u002F)[![Image 22](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857487408_417.png)](http:\u002F\u002Fdbzx.cctv.cn\u002Findex.shtml)\n\n[CCTV.节目官网](https:\u002F\u002Ftv.cctv.cn\u002F)[直播](https:\u002F\u002Ftv.cctv.cn\u002Flive\u002Findex.shtml)[节目单](https:\u002F\u002Ftv.cctv.cn\u002Fepg\u002Findex.shtml)[栏目](https:\u002F\u002Ftv.cctv.cn\u002Flm\u002F)[片库](https:\u002F\u002Ftv.cctv.cn\u002Fyxg\u002F)[热播榜](https:\u002F\u002Ftv.cctv.cn\u002Ftop\u002F)[总台企业白名单](https:\u002F\u002Ftv.cctv.cn\u002Fspecial\u002Fqybmd\u002Findex.shtml)\n\n*   [![Image 23](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857919170_116.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv1\u002F)\n*   [![Image 24](https:\u002F\u002Fp3.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857908565_283.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv2\u002F)\n*   [![Image 25](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857899758_226.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv3\u002F)\n*   [![Image 26](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857890508_970.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv4asia\u002F)\n*   [![Image 27](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857880669_439.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv5\u002F)\n*   [![Image 28](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857870022_568.png)](http:\u002F\u002Ftv.cctv.cn\u002Fcctv5plus\u002F)\n*   [![Image 29](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857866003_622.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv6\u002F)\n*   [![Image 30](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857849889_559.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv7\u002F)\n*   [![Image 31](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857845477_430.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv8\u002F)\n*   [![Image 32](https:\u002F\u002Fp4.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857796382_346.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv9\u002F)\n*   [![Image 33](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857791503_238.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv10\u002F)\n*   [![Image 34](https:\u002F\u002Fp3.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857775917_66.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv11\u002F)\n*   [![Image 35](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857764456_492.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv12\u002F)\n*   [![Image 36](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857760604_164.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv13\u002F)\n*   [![Image 37](https:\u002F\u002Fp5.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857722814_387.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv14\u002F)\n*   [![Image 38](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857703226_327.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv15\u002F)\n*   [![Image 39](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857684625_15.png)](http:\u002F\u002Ftv.cctv.cn\u002Fcctv16\u002F)\n*   [![Image 40](https:\u002F\u002Fp3.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F18\u002F1652857654002_764.png)](https:\u002F\u002Ftv.cctv.cn\u002Fcctv17\u002F)\n\n*   [![Image 41](https:\u002F\u002Fp2.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F5\u002F23\u002F1653307509334_306.png)](https:\u002F\u002Fnews.cctv.cn\u002Fspecial\u002Fzhgqsh\u002Ftgdzh\u002Findex.shtml)\n*   [![Image 42](https:\u002F\u002Fp3.img.cntv.cn\u002FphotoAlbum\u002Fpage\u002Fperformance\u002Fimg\u002F2022\u002F7\u002F1\u002F1656653912700_622.png)](https:\u002F\u002Ftvtech.cctv.cn\u002F)\n\n短信登录 账号登录\n\n +86 | \n手机号\n\n手机号格式错误\n\n图形验证码\n\n[![Image 43](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)](javascript:;)\n\n图形验证码错误\n\n短信验证码\n\n_获取验证码_\n\n短信验证码错误\n\n验证码已发送，可能会有延后请耐心等待\n\n[登 录](javascript:;)\n\n请阅读并勾选下列协议\n\n同意[《央视网用户服务协议》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002Ffuwuxieyi\u002Findex.shtml)[《央视网隐私政策》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FPAGE1381887126760260\u002Findex.shtml)[《儿童隐私保护指引》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002F20200605\u002Findex.shtml)\n\n免费注册\n\n手机号\u002F邮箱\n\n输入格式有误，请使用邮箱或手机号码登录 \n\n密码长度为 8-16 个字符\n\n图形验证码\n\n[![Image 44](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)](javascript:;)\n\n图形验证码错误\n\n记住我\n\n[忘记密码](https:\u002F\u002Fuser.cctv.cn\u002FfindPassword\u002Findex.shtml)\n\n[登 录](javascript:;)\n\n请阅读并勾选下列协议\n\n同意[《央视网用户服务协议》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002Ffuwuxieyi\u002Findex.shtml)[《央视网隐私政策》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FPAGE1381887126760260\u002Findex.shtml)[《儿童隐私保护指引》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002F20200605\u002Findex.shtml)\n\n免费注册\n\n[](javascript:;)[](javascript:;)[](javascript:;)[](javascript:;)\n\n#### 打开 央视影音手机客户端\n\n#### 扫描二维码登录\n\n二维码已失效\n\n点击刷新\n\n扫码成功\n\n请在手机上确认 [登录]\n\n登录即代表同意[《央视网用户服务协议》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002Ffuwuxieyi\u002Findex.shtml)[《央视网隐私政策》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FPAGE1381887126760260\u002Findex.shtml)[《儿童隐私保护指引》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002F20200605\u002Findex.shtml)\n\n[下载央视影音客户端](https:\u002F\u002Fapp.cctv.cn\u002F)\n\n手机注册 邮箱注册\n\n +86 | \n手机号\n\n手机号格式错误\n\n图形验证码\n\n[![Image 45](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)](javascript:;)\n\n图形验证码错误\n\n短信验证码\n\n_获取验证码_\n\n短信验证码错误\n\n验证码已发送，可能会有延后请耐心等待\n\n密码与确认密码不一致\n\n请再次输入密码\n\n[注 册](javascript:;)\n\n请阅读并勾选下列协议\n\n同意[《央视网用户服务协议》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002Ffuwuxieyi\u002Findex.shtml)[《央视网隐私政策》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FPAGE1381887126760260\u002Findex.shtml)[《儿童隐私保护指引》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002F20200605\u002Findex.shtml)\n\n返回登录\n\n邮箱\n\n邮箱格式错误\n\n图形验证码\n\n[![Image 46](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)](javascript:;)\n\n图形验证码错误\n\n密码与确认密码不一致\n\n请再次输入密码\n\n[注 册](javascript:;)\n\n请阅读并勾选下列协议\n\n同意[《央视网用户服务协议》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002Ffuwuxieyi\u002Findex.shtml)[《央视网隐私政策》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FPAGE1381887126760260\u002Findex.shtml)[《儿童隐私保护指引》](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002F20200605\u002Findex.shtml)\n\n返回登录\n\n扫码成功\n\n请绑定手机号\n\n +86 | \n手机号\n\n手机号格式错误\n\n图形验证码\n\n[![Image 47](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)](javascript:;)\n\n图形验证码错误\n\n短信验证码\n\n_获取验证码_\n\n短信验证码错误\n\n验证码已发送，可能会有延后请耐心等待\n\n[提 交](javascript:;)\n温馨提示：若您的手机号已在央视网注册，绑定后， 仅保留手机账号内的信息。\n\n验证邮件发送成功  \n立即[进入邮箱查看](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)\n\n24h同一个用户请求邮件验证码超过10次\n\n邮箱验证码\n\n已发送,可能会有延后请耐心等待\n\n[确定](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)\n\n安全验证\n\n图形验证码\n\n[![Image 48](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)](javascript:;)\n\n图形验证码错误\n\n确 定\n\n您的密码存在安全风险，请 [立即修改](https:\u002F\u002Fuser.cctv.cn\u002FfindPassword\u002Findex.shtml)\n\n激活成功\n\n3s 后自动跳转到登录页\n\n返回登录\n\n信息已提交  \n请点击邮箱中的链接激活账号\n\n立即访问邮箱\n\n系统维护中，请稍后再试\n\n请完成安全验证\n\n![Image 49](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)\n\n向右滑动完成验证\n\n![Image 50](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)\n\n[](http:\u002F\u002Fm.cctv.cn\u002F)\n\n[新闻](http:\u002F\u002Fnews.cctv.cn\u002F)\n\n[](http:\u002F\u002Fm.cctv.cn\u002Fquanzhannav2019\u002Findex.shtml)\n\n[](https:\u002F\u002Fsearch.cctv.cn\u002Fm\u002F)\n\n[新闻频道](https:\u002F\u002Fnews.cctv.cn\u002F)[>](javascript:void(0);)[中国新闻](https:\u002F\u002Fnews.cctv.cn\u002Fzgxwyc\u002F)\n\n# 从吃到用 实验室与餐桌距离被看得见、尝得到、用得上的“新鲜事”拉近\n\n来源：央视网 | 2026年09月20日 13:58:17\n\n央视网 | 2026年09月20日 13:58:17\n\n###### 原标题：\n\n正在加载\n\n[Video 3](https:\u002F\u002Fdh5.cntv.cdn20.com\u002Fasp\u002Fh5e\u002Fhls\u002Fmain\u002F0303000a\u002F3\u002Fdefault\u002F8d26c0f8c36e4e1e8ed02d6406007686\u002Fmain.m3u8?maxbr=2048&contentid=15120519184043)\n\n静音(m)全屏(f)\n\nADCountdown Time | 广告\n\n![Image 51](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)关闭广告\n\n![Image 52](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)\n\n尊贵的用户，已为您跳过广告\n\n0:00\n\n正在加载 视频播放器。\n\n播放(p)播放视频\n\n播放(p)\n\n当前时间 0:00\n\n\u002F\n\n时长 2:12\n\n媒体流类型 直播\n\n高清\n\n画质\n\n*   超清\n*   高清, 选择\n*   标清\n*   流畅\n\n静音(m)\n\n全屏(f)\n\n加载完成: 0%\n\n-\n\n88:88\n\n[](javascript:void(0);)\n\n*   core:undefined.undefined\n*   wrap:3.8.2.260723\n\n画中画\n\n**央视网消息：**9月19日，中国农业科学院36个研究所的560多项最新科研成果集中面向社会公众亮相，把农业实验室里的“新鲜事”带到公众眼前。\n\n![Image 53](https:\u002F\u002Fp3.img.cntv.cn\u002Fphotoworkspace\u002Fcontentimg\u002F2026\u002F09\u002F20\u002F2026092013212476326.png)\n\n在果蔬成果展区，最受欢迎的不是常见的香甜水果，而是一杯胡萝卜汁。  \n  \n 科研人员通过调节不同品种胡萝卜的收获时间和栽培模式，培育出口感更甜更细腻的品种以及减糖版胡萝卜。  \n  \n 中国农业科学院蔬菜花卉研究所大宗蔬菜产业技术体系岗位专家庄飞云介绍，胡萝卜口感整体受环境影响特别大，通过调节里面的一些组分，很多让人不愉快的组分把它尽量减少到很低，当然它的营养还能保持原有的营养。\n\n![Image 54](https:\u002F\u002Fp5.img.cntv.cn\u002Fphotoworkspace\u002Fcontentimg\u002F2026\u002F09\u002F20\u002F2026092013213274797.png)\n\n另一边的展区里，这种晶莹剔透的黄瓜不仅口感脆嫩，还富含一种能有效阻止糖类转化为脂肪的功能小分子——“丙醇二酸”。吃根黄瓜还能顺带帮着管理体重。  \n  \n 作物展区里，作物科学研究所带来了新的攻关成果。低豆腥味、高异黄酮、适合榨汁的大豆，还有一款新研发的“甜糯同粒”玉米。\n\n![Image 55](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)\n\n中国农业科学院作物科学研究所育种专家肖永贵介绍，原来的玉米要么是甜，要么是糯，要么就是7粒糯1粒甜，要么3粒糯1粒甜，把甜和糯放到一个粒里按照不同比例调配口感会更好。  \n  \n 机械展区，各种新型农用机器人集体亮相。这台农业转运机器人不仅能扛100公斤以上的作物在丘陵山区跑，还会“凌波微步”。\n\n![Image 56](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F20\u002FARTIkUEnHV7gFcVPFEweSMwS260920.shtml)\n\n农业农村部南京农业机械化研究所助理研究员宫庆硕介绍，可以进行左右横移，在狭窄的田间环境中可以实现快速换行，也可以实现原地掉头能力。  \n  \n 正在研发的全球动物疾病风险大模型，未来将对动物疫病实现实时预报预警，相当于给全球畜牧业装上一张“天气图”，让餐桌上的肉蛋奶更安全。从吃到用，实验室与餐桌的距离正在被这些“看得见、尝得到、用得上”的成果不断拉近。\n\n编辑：杨书杰 责任编辑：刘亮\n\n*   [从吃到用](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E4%BB%8E%E5%90%83%E5%88%B0%E7%94%A8)\n*   [实验室](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E5%AE%9E%E9%AA%8C%E5%AE%A4)\n*   [餐桌](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E9%A4%90%E6%A1%8C)\n\n点击收起全文\n\n[返回央视网首页](http:\u002F\u002Fwww.cctv.cn\u002F)[返回新闻频道](http:\u002F\u002Fnews.cctv.cn\u002F)[_望海热线_](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FjianjiePAGEQezAEWqHSGGmjjQL6s0V231214\u002Findex.shtml)\n\n[返回顶部](javascript:;)\n\n[](http:\u002F\u002Fwww.cctv.cn\u002F)\n\n[望海热线](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FjianjiePAGEQezAEWqHSGGmjjQL6s0V231214\u002Findex.shtml)\n\n_xinwenxiansuo@staff.cntv.cn_\n\n[](https:\u002F\u002Fwww.cctv.cn\u002Fspecial\u002Fguanyunew\u002FjianjiePAGEQezAEWqHSGGmjjQL6s0V231214\u002Findex.shtml)\n\n最新推荐\n\n*   [![Image 57](https:\u002F\u002Fp1.img.cntv.cn\u002Fphotoworkspace\u002F2026\u002F09\u002F25\u002F2026092508003423212.jpg)](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTI6HUnyOfkLrkJK5Q68fz1260925.shtml) [习近平和彭丽媛出席特朗普总统夫妇举行的欢迎宴会](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTI6HUnyOfkLrkJK5Q68fz1260925.shtml) [当地时间9月24日晚，国家主席习近平和夫人彭丽媛出席美国总统特朗普和夫人梅拉尼娅在白宫举行的欢迎宴会。](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTI6HUnyOfkLrkJK5Q68fz1260925.shtml) 2026-09-25 00:00[习近平](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E4%B9%A0%E8%BF%91%E5%B9%B3)[特朗普](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E7%89%B9%E6%9C%97%E6%99%AE)[彭丽媛](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E5%BD%AD%E4%B8%BD%E5%AA%9B)   \n*   [![Image 58](https:\u002F\u002Fp3.img.cntv.cn\u002Fphotoworkspace\u002F2026\u002F09\u002F25\u002F2026092507551410751.jpg)](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIj0L0EwC5sCqKsSsTKVV1260925.shtml) [彭丽媛同美国总统特朗普夫人梅拉尼娅参观国立亚洲艺术博物馆](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIj0L0EwC5sCqKsSsTKVV1260925.shtml) [当地时间9月24日中午，国家主席习近平夫人彭丽媛在华盛顿同美国总统特朗普夫人梅拉尼娅参观国立亚洲艺术博物馆。](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIj0L0EwC5sCqKsSsTKVV1260925.shtml) 2026-09-24 23:59[彭丽媛](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E5%BD%AD%E4%B8%BD%E5%AA%9B)[梅拉尼娅](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E6%A2%85%E6%8B%89%E5%B0%BC%E5%A8%85)   \n*   [![Image 59](https:\u002F\u002Fp4.img.cntv.cn\u002Fphotoworkspace\u002F2026\u002F09\u002F25\u002F2026092507395662013.jpg)](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIJzgdypivBYzCg2YdvUAE260925.shtml) [大国外交进行时丨特朗普总统夫妇在白宫热情迎接习近平主席夫妇](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIJzgdypivBYzCg2YdvUAE260925.shtml) [当地时间9月24日晚，国家主席习近平和夫人彭丽媛在白宫出席美国总统特朗普和夫人梅拉尼娅举行的欢迎宴会。](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIJzgdypivBYzCg2YdvUAE260925.shtml) 2026-09-24 23:42[大国外交进行时](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E5%A4%A7%E5%9B%BD%E5%A4%96%E4%BA%A4%E8%BF%9B%E8%A1%8C%E6%97%B6)   \n*   [![Image 60](https:\u002F\u002Fp1.img.cntv.cn\u002Fphotoworkspace\u002F2026\u002F09\u002F25\u002F2026092507401440491.jpg)](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIQKqznf9idYWS6iNTtQnG260925.shtml) [大国外交进行时丨习近平主席夫妇抵达白宫出席欢迎宴会](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIQKqznf9idYWS6iNTtQnG260925.shtml) [当地时间9月24日晚，国家主席习近平和夫人彭丽媛乘车抵达白宫，出席美国总统特朗普和夫人梅拉尼娅举行的欢迎宴会。](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIQKqznf9idYWS6iNTtQnG260925.shtml) 2026-09-24 23:41[大国外交进行时丨习近平主席夫妇抵达白宫出席欢迎宴会](https:\u002F\u002Fsearch.cctv.cn\u002Fsearch.php?qtext=%E5%A4%A7%E5%9B%BD%E5%A4%96%E4%BA%A4%E8%BF%9B%E8%A1%8C%E6%97%B6%E4%B8%A8%E4%B9%A0%E8%BF%91%E5%B9%B3%E4%B8%BB%E5%B8%AD%E5%A4%AB%E5%A6%87%E6%8A%B5%E8%BE%BE%E7%99%BD%E5%AE%AB%E5%87%BA%E5%B8%AD%E6%AC%A2%E8%BF%8E%E5%AE%B4%E4%BC%9A)   \n*   [![Image 61](https:\u002F\u002Fp4.img.cntv.cn\u002Fphotoworkspace\u002F2026\u002F09\u002F25\u002F2026092507245664866.jpg)](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIrkOg3GKxtFuslY0DqNVz260925.shtml) [大国外交进行时丨白宫：礼兵和军乐团就位 迎候习近平主席](https:\u002F\u002Fnews.cctv.cn\u002F2026\u002F09\u002F25\u002FARTIrkOg3GKxtFuslY0DqNVz260925.shtml) [当地时间9月2","央视网 2026-09-20","2026-09-20T00:00:00Z","报道",65,{"impact":19,"substance":17,"depth":20,"authority":17,"freshness":73,"relevant":21,"comment":321},"央媒对中国农科院开放日的综合报道，集中展示彩色胡萝卜、丙醇二酸黄瓜、甜糯同粒玉米及转运机器人、动物疾病风险大模型等成果，信息量足但属活动报道，时效已过一周，可作主题聚合素材。",[323],{"name":316,"url":313},[325,326,327,328,329],"农业机器人","种业振兴","动物疫病防控","农业科技","功能型农产品",{"code":331,"slug":332,"name":333,"path":334,"parent_code":335},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[337,338],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":340},{"candidates":341,"agricultural_evidence":52},[342,348,353,358,364,370,375],{"code":331,"score":18,"supported":52,"title":343,"abstract":346,"tags":347},[344,345],"黄瓜","萝卜",[344,345],[],{"code":32,"score":349,"supported":52,"title":350,"abstract":351,"tags":352},11,[34],[34],[],{"code":39,"score":349,"supported":52,"title":354,"abstract":356,"tags":357},[355],"大模型",[355],[],{"code":359,"score":268,"supported":52,"title":360,"abstract":361,"tags":363},"C5",[],[362],"动物疫病",[327],{"code":365,"score":64,"supported":52,"title":366,"abstract":367,"tags":369},"A4",[],[368],"大豆",[],{"code":371,"score":21,"supported":14,"title":372,"abstract":373,"tags":374},"F1",[],[],[326],{"code":376,"score":21,"supported":14,"title":377,"abstract":378,"tags":379},"F6",[],[],[325],[381,382],"中国农科院 农科开放日","彩色胡萝卜 丙醇二酸黄瓜","中国农科院农科开放日-3396",2,"2026-09-25T00:09:29.650043Z",{"id":387,"title":388,"url":389,"summary":390,"summary_zh":8,"content":8,"source_name":391,"source_url":389,"published_at":392,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":86,"score_detail":393,"sources":396,"tags":398,"primary_topic":401,"secondary_topics":402,"classification":408,"search_phrases":433,"slug":436,"view_count":268,"doi":437,"paper":438,"created_at":447},3152,"An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23311932.2026.2725400","An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania。Cogent Food & Agriculture","Cogent Food & Agriculture","2026-09-22T00:00:00Z",{"impact":20,"substance":19,"depth":58,"authority":394,"freshness":13,"relevant":21,"comment":395},13,"论文提出物联网与机器学习融合的玉米产量预测框架，方法有新意但属区域性应用研究，影响力有限，时效性强。",[397],{"name":391,"url":389},[94,95,399,400,34],"产量预测","物联网",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[403,404],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":123,"slug":405,"name":406,"path":407,"parent_code":43},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":45,"locked":14,"version":46,"method":47,"evidence":409},{"candidates":410,"agricultural_evidence":52},[411,415,420,424,429],{"code":32,"score":20,"supported":52,"title":412,"abstract":413,"tags":414},[33],[33],[34],{"code":115,"score":20,"supported":52,"title":416,"abstract":418,"tags":419},[417],"smart agriculture",[417],[94],{"code":39,"score":20,"supported":52,"title":421,"abstract":422,"tags":423},[195],[195],[95],{"code":123,"score":20,"supported":52,"title":425,"abstract":427,"tags":428},[426],"IoT",[426],[400],{"code":262,"score":21,"supported":14,"title":430,"abstract":431,"tags":432},[],[],[399],[434,435],"坦桑尼亚 玉米 产量预测","物联网 机器学习 智慧农业","坦桑尼亚玉米产量预测-3152","10.1080\u002F23311932.2026.2725400",{"doi":437,"openalex_id":439,"authors":440,"venue":391,"cited_by_count":160,"oa_url":389,"card":8,"direction":446,"ingested_from":168},"W7213978365",[441,444],{"name":442,"orcid":443},"Alcardo Alex Barakabitze","https:\u002F\u002Forcid.org\u002F0000-0001-8960-8415",{"name":445,"orcid":8},"Yasinta Nzogera","智慧农业 \u002F 农业物联网","2026-09-22T23:30:10.178097Z",{"id":449,"title":450,"url":451,"summary":452,"summary_zh":8,"content":453,"source_name":454,"source_url":8,"published_at":455,"category":318,"cover_url":8,"hotness":13,"is_selected":14,"score":456,"score_detail":457,"sources":460,"tags":462,"primary_topic":467,"secondary_topics":472,"classification":475,"search_phrases":516,"slug":519,"view_count":110,"doi":8,"paper":8,"created_at":520},3100,"秋实满田 智赋丰年——中国移动(成都)产业研究院\"谷丰登\"农业大模型赋能山西大同玉米单产提升试点亩产 2481 斤较非试点增产 15.5%","https:\u002F\u002Fiot.youth.cn\u002Fyw\u002F202609\u002Ft20260921_16881000.htm","9-21 中国青年网物联网频道报道中国移动(成都)产业研究院秋收赋能：以\"九天大模型\"为底座自主研发\"谷丰登\"农业大模型、构建覆盖土壤分析\u002F品种优选\u002F精准水肥药方案\u002F产量预估全生命周期服务体系；联合中储粮打造行业首个储粮场景大模型\"稷元\"已落地 3 个中央储备粮库，粮食储存损失降至 0.2% 以下、化学药剂年使用量减少 1-2 次；牵头制定《农业大模型高质量数据集》《农业种植大模型应用测评规范》两项团体标准。山西大同玉米单产提升标杆项目依托空天地一体化监测+北斗高精定位+农业大模型实现玉米耕种管收全流程无人化作业，试点田亩产 2481 斤较非试点增产 15.5%，被农业农村部评为\"全国智慧农业建设典型案例\"。","九月的田野，稻菽飘香，又是一年丰收时。\n\n随着“十五五”规划的全面实施，农业农村现代化建设蹄疾步稳。传统“看天吃饭”的农业生产模式正在被改写，数字技术驱动下，丰收迎来科技赋能、全链提质、数智增效的全新发展阶段。\n\n当前正值金秋丰收的关键时期，中国移动（成都）产业研究院（以下简称“成研院”）充分发挥科技引领作用，贯通智慧种养、智能储粮、数字治理、产销对接全业务链路，推动数字技术与农业生产融合走深走实，为国家粮食安全与乡村全面振兴注入强劲数字动能。\n\n**科技强农：打造从田间到粮仓的“智慧大脑”**\n\n成研院聚焦AI育种创新、种植生产管理与粮食仓储等关键环节，以中国移动“九天大模型”为底座，自主研发谷丰登农业大模型，构建起全周期、智能化的农业生产服务体系，打造扎根田野的“身边的农业知识专家”。\n\n“藏粮于技”的关键，在于让技术真正下沉到田间地头。成研院打造国内首个种植综合农业大模型，覆盖土壤分析、品种优选、精准水肥药方案、产量预估等全生命周期服务，实现“信息随手握、种养全程导、在线有人帮”。在山西大同玉米单产提升标杆项目中，成研院构建“良田、良种、良机、良法”融合体系，依托空天地一体化监测、北斗高精定位与农业大模型三大核心能力，实现玉米耕、种、管、收全流程无人化作业。当年秋收，试点田亩产达2481斤，较非试点区域增产15.5％，被农业农村部评为“全国智慧农业建设典型案例”。\n\n丰产更要保收，储粮减损是守住丰收成果、保障粮食安全的关键一环。成研院联合中储粮打造行业首个储粮场景大模型“稷元”，内置二十余万条储粮知识单元及千余本专业文献，结合智能语音助手“粮小助”，实时采集、动态监测各类粮情核心指标，智能预判粮情变化趋势，提前预警仓储虫害风险，自动生成仓储调控最优方案，同时采用一体化集成设计，适配粮库现有系统，实现核心业务在库内闭环处理，严守粮食仓储信息安全底线。目前，“稷元”大模型已在中储粮三个中央储备粮库落地，粮食储存损失降至0.2%以下，化学药剂年使用量减少1—2次，大幅提升粮食仓储安全水平，守住丰收成果、筑牢储粮安全防线。\n\n此外，成研院牵头制定《农业大模型高质量数据集》《农业种植大模型应用测评规范》两项团体标准，填补行业规范空白，为大模型规范化、规模化应用筑牢基础。\n\n![Image 1](https:\u002F\u002Fiot.youth.cn\u002Fyw\u002F202609\u002FW020260921554681104915.png)\n\n![Image 2](https:\u002F\u002Fiot.youth.cn\u002Fyw\u002F202609\u002FW020260921554681314335.png)\n\n**数字惠农：激活基层治理民生温度**\n\n成研院以数字技术创新破解基层治理痛点、赋能民生服务、激活乡村发展动能，推动数字技术真正扎根田野、服务农民。\n\n在传承着焦裕禄精神的河南兰考葡萄架乡，成研院打造的数字乡村平台全面落地应用。平台贯通乡、村两级业务全链条，整合民政、社保、农业等多部门数据资源，实现“一次采集、多方复用”。平台提供20余项高频服务“掌上办”，让“数据多跑路、群众少跑腿”，并依托AI智能预警，推动基层治理高效化、智能化。目前，平台已覆盖全乡20个行政村，累计收录人口数据超3万条，助力基层干部事务性工作量降低60%以上，实现网格管理一屏总览、AI智能安防实时监测、积分激励激活村民参与，打通基层治理“最后一公里”。\n\n在甘肃积石山县团结村，智慧乡村大脑聚焦民族地区灾后重建与乡村振兴，集成灾后重建、乡村振兴、民族团结、服务治理、综合监测五大模块，一屏统揽耕地分布、帮扶进展、集体经济、群众诉求等村庄“家底”，为村委科学决策提供精准支撑。同时，村里为50户重点关爱家庭免费安装一键呼叫终端，直连紧急救助与亲情通话，让乡村治理更有精度与温度。\n\n**产业富农：搭建产销双向联通桥梁**\n\n从培育乡村产业带头人到打通农产品出村进城通道，成研院以数字技术为纽带，一头连着田间地头的生产者，一头连着广阔市场的消费者，让好产品卖出好价钱，让乡村产业真正活起来、强起来。\n\n作为农业农村部“头雁”项目的技术支撑方，成研院为“头雁”人才培育系统提供的全方位信息化支撑。目前，“头雁”平台已覆盖全国31省份，累计服务7万余名乡村产业带头人，为乡村培育“造血种子”。\n\n如果说头雁工程是为乡村培育“造血种子”，那么“陆海优品公共服务平台”就是为乡村产业打通“出村进城、走向世界”的黄金通道。平台开设免费电商、直播、品控等培训，助力800多万农民转型“新农人”，推动中国移动对口帮扶的五省（区）八县、成渝地区双城经济圈特色农产品实现精准产销对接。目前，平台已带动超2000万元消费帮扶、实现3亿元农产品出口额，服务全国超600万用户，以数智力量畅通国内国际双循环。\n\n丰收，不再只是田野里的金黄稻浪，更是数据流中奔涌的智慧动能。当技术真正扎根泥土，当数字红利真正惠及农民，丰收便有了更坚实的支撑，乡村便有了更持久的活力。面向未来，成研院将继续以数智之力深耕沃土，让“藏粮于技”落地生根，让“数字乡村”可感可及，在广袤田野上书写属于新时代的丰收故事。","中国青年网","2026-09-21T00:00:00Z",84,{"impact":458,"substance":18,"depth":58,"authority":394,"freshness":89,"relevant":21,"comment":459},24,"央媒报道的农业大模型落地标杆案例，含亩产2481斤、增产15.5%、储粮损失降至0.2%等硬数据，产业示范价值突出，值得进入每日精选。",[461],{"name":454,"url":451},[463,94,95,464,465,466],"数字乡村","农业大模型","玉米单产提升","粮食仓储",{"code":468,"slug":469,"name":470,"path":471,"parent_code":36},"A8","yield-food-security","单产提升与粮食安全","\u002Ftopic\u002Ffield-crops\u002Fyield-food-security",[473,474],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":45,"locked":14,"version":46,"method":47,"evidence":476},{"candidates":477,"agricultural_evidence":52},[478,483,487,491,495,501,505,511],{"code":468,"score":394,"supported":52,"title":479,"abstract":481,"tags":482},[480],"单产提升",[480],[465,466],{"code":39,"score":394,"supported":52,"title":484,"abstract":485,"tags":486},[355],[355],[95,464],{"code":32,"score":20,"supported":52,"title":488,"abstract":489,"tags":490},[34],[34],[465],{"code":115,"score":268,"supported":52,"title":492,"abstract":493,"tags":494},[],[94],[94],{"code":496,"score":64,"supported":52,"title":497,"abstract":498,"tags":500},"H2",[],[499],"土壤",[],{"code":123,"score":64,"supported":52,"title":502,"abstract":503,"tags":504},[],[400],[],{"code":506,"score":64,"supported":52,"title":507,"abstract":508,"tags":510},"J4",[],[509],"秋收",[],{"code":512,"score":21,"supported":14,"title":513,"abstract":514,"tags":515},"I6",[],[],[463],[517,518],"中国移动 谷丰登 农业大模型","山西大同 玉米 亩产2481斤","中国移动谷丰登农业大模型-3100","2026-09-22T00:05:33.912382Z"]