[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-965":3,"related-965":64},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":33,"secondary_topics":39,"classification":40,"search_phrases":58,"slug":61,"view_count":62,"doi":8,"paper":8,"created_at":63},965,"云南农科院发布3项农业科研成果 为澜湄区域农业产业提供「云南技术方案」","https:\u002F\u002Fwww.lmcchina.org\u002Flmhzdt\u002F202608\u002Ft20260825_12010002.html","近日云南省农业科学院质量标准与检测技术研究所受邀参加云南省商务厅联合南亚东南亚七国驻昆明总领事馆主办的「共享大市场•出口中国」系列活动，发布3项核心农业科研成果：一、葡萄产业绿色发展及标准化体系构建——搭建起科学完善的葡萄产业标准体系，提升果品质量安全水平；二、中国猕猴桃品质评价技术体系——为澜湄区域各类特色果蔬品质评定提供标准化参考依据；三、花卉智能检测技术及颜色图像分析系统——打破传统花卉育种与检测对人工肉眼主观判定的依赖，实现花卉颜色的定量、定性精准分析。三项科研成果精准对接产业需求与跨境贸易痛点，为澜湄区域农业产业协同发展筑牢技术根基。",null,"澜沧江-湄公河合作 2026-08-25","2026-08-25T08:20:00Z","报道",10,false,65,{"impact":16,"substance":17,"depth":18,"authority":12,"freshness":19,"relevant":20,"comment":21},18,16,12,9,1,"省级农科院发布三项农业科研成果，涉及葡萄、猕猴桃、花卉检测技术，对澜湄区域农业合作有实质推动，但影响范围限于区域，深度一般。",[23],{"name":9,"url":6},[25,26,27,28,29,30,31,32],"猕猴桃","标准化","花卉","云南省农科院","葡萄","澜湄","智能检测","品质评价",{"code":34,"slug":35,"name":36,"path":37,"parent_code":38},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":41,"locked":13,"version":42,"method":43,"evidence":44},"classified","2026-10-22.2","rules",{"candidates":45,"agricultural_evidence":48},[46,52],{"code":34,"score":47,"supported":48,"title":49,"abstract":50,"tags":51},8,true,[],[29,25],[25,29],{"code":53,"score":54,"supported":48,"title":55,"abstract":56,"tags":57},"B4",4,[],[27],[27],[59,60],"云南省农科院 品质评价 智能检测 标准化","云南省农科院 品质评价","云南省农科院品质评价智能检测标准化-965",2,"2026-08-26T00:09:31.281710Z",{"total":65,"page":20,"page_size":65,"items":66},6,[67,111,172,217,280,343],{"id":68,"title":69,"url":70,"summary":71,"summary_zh":8,"content":72,"source_name":73,"source_url":8,"published_at":74,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":75,"sources":79,"tags":81,"primary_topic":86,"secondary_topics":87,"classification":88,"search_phrases":105,"slug":108,"view_count":109,"doi":8,"paper":8,"created_at":110},5516,"上海农科院葡萄团队赴银川参加第47届世界葡萄与葡萄酒大会","https:\u002F\u002Fwww.saas.sh.cn\u002Fhzjl\u002Fgjhz\u002Fcontent_57128","10月12日至16日第47届世界葡萄与葡萄酒大会在银川举办，智慧农业研究中心葡萄团队负责人奚晓军研究员作专题报告，阐明疏穗与环剥处理对果实糖、花青素及脱落酸积累的源库调控机制。团队还观摩酿酒葡萄AI综合作业机器人成果展示，与研发单位围绕葡萄智慧装备与果园智能化管理深入交流。","2026年10月12-16日，第47届世界葡萄与葡萄酒大会在银川举办，智慧农业研究中心葡萄团队负责人奚晓军研究员一行赴会交流。团队围绕“提升葡萄种植生产韧性与可持续发展能力”主题，向全球同行展示最新科研成果。\n\n会上，奚晓军作“Changes in sugar, anthocyanin and ABA accumulation in response to cluster thinning and girdling in ‘Jumeigui’grape”专题报告。报告围绕葡萄疏穗与环剥处理开展研究，阐明源库比对果实糖、花青素及脱落酸积累的调控机制，为葡萄优质栽培技术提供理论支撑，报告内容引发国内外园艺专家广泛研讨。参会期间，团队前往银川国际会展中心观摩酿酒葡萄 AI 综合作业机器人成果展示，详细了解该装备在葡萄园智能作业方面的技术特点与应用前景，并与研发单位围绕葡萄智慧装备研发、果园智能化管理等方向开展深入交流。\n\n本次参会是葡萄团队持续推进科研国际化、对标国际前沿开展研究的重要实践。","上海市农业科学院 2026-10-19","2026-10-19T00:00:00Z",{"impact":17,"substance":76,"depth":77,"authority":77,"freshness":65,"relevant":20,"comment":78},17,13,"国际学术会议交流并涉及葡萄AI作业机器人观摩，有实质科研内容与行业参考价值，但属团队参会动态，影响面有限。",[80],{"name":73,"url":70},[82,83,29,84,85],"智慧农业","智能农机","栽培技术","国际交流",{"code":34,"slug":35,"name":36,"path":37,"parent_code":38},[],{"status":41,"locked":13,"version":42,"method":43,"evidence":89},{"candidates":90,"agricultural_evidence":48},[91,95,100],{"code":34,"score":18,"supported":48,"title":92,"abstract":93,"tags":94},[29],[29],[29],{"code":96,"score":54,"supported":48,"title":97,"abstract":98,"tags":99},"I1",[],[82],[82],{"code":101,"score":20,"supported":13,"title":102,"abstract":103,"tags":104},"F5",[],[],[83],[106,107],"上海农科院 葡萄 银川","世界葡萄与葡萄酒大会 奚晓军","上海农科院葡萄银川-5516",0,"2026-10-22T00:07:04.061911Z",{"id":112,"title":113,"url":114,"summary":115,"summary_zh":8,"content":8,"source_name":116,"source_url":8,"published_at":117,"category":118,"cover_url":8,"hotness":119,"is_selected":13,"score":120,"score_detail":121,"sources":125,"tags":130,"primary_topic":135,"secondary_topics":136,"classification":137,"search_phrases":154,"slug":157,"view_count":20,"doi":158,"paper":159,"created_at":171},4407,"From Downstream Demand to Upstream Innovation: How a Digital Platform Coordinates Agri-Food Value Chain Upgrading—The Case of Taotian Digital Agriculture","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1972526\u002Ffull","曹帆基于对中国淘天集团即食猕猴桃项目的深度案例研究,通过对访谈、田野观察、企业内部文件、政府材料与公开来源的分析,揭示数字平台通过将消费者需求转化为清晰产品目标,并在生产、加工、储存、物流、销售各环节进行技术与组织协调的「需求—创新」机制;案例显示平台主导升级的持久性与包容性可能取决于稳定经济回报、可触达本地服务、可管理合规成本、风险分担安排与平台治理。","Frontiers in Sustainable Food Systems 2026-10-02 接受","2026-10-02T00:00:00Z","论文",25,78,{"impact":16,"substance":122,"depth":16,"authority":123,"freshness":65,"relevant":20,"comment":124},22,14,"核心期刊案例研究，揭示数字平台驱动农产品价值链升级的机制，对农业数字化转型有参考价值。",[126,127],{"name":116,"url":114},{"name":128,"url":129},"Frontiers in Sustainable Food Systems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1972526",[131,25,132,133,134],"数字农业","农业数字化","数字平台","农产品价值链",{"code":34,"slug":35,"name":36,"path":37,"parent_code":38},[],{"status":41,"locked":13,"version":42,"method":43,"evidence":138},{"candidates":139,"agricultural_evidence":48},[140,145,149],{"code":96,"score":12,"supported":48,"title":141,"abstract":143,"tags":144},[142],"digital agriculture",[],[132,131],{"code":34,"score":54,"supported":48,"title":146,"abstract":147,"tags":148},[],[25],[25],{"code":150,"score":20,"supported":13,"title":151,"abstract":152,"tags":153},"I",[],[],[132],[155,156],"淘天集团 猕猴桃 数字平台","数字农业 价值链 案例研究","淘天集团猕猴桃数字平台-4407","10.3389\u002Ffsufs.2026.1972526\u002Ffull",{"doi":158,"openalex_id":160,"authors":161,"venue":128,"cited_by_count":109,"oa_url":129,"card":164,"direction":168,"ingested_from":170},"W7221535736",[162],{"name":163,"orcid":8},"Fan Cao",{"tldr":165,"method":166,"finding":167,"direction":168,"opportunity":169},"基于淘天即食猕猴桃案例，揭示数字平台以需求驱动农业食品价值链升级的机制。","深度案例研究，分析访谈、田野观察、企业文件与政府材料。","平台将消费需求转为产品目标并协调全链，升级持续性取决于回报、服务、合规、风险分担与治理。","数字乡村与农业信息化","可量化平台治理与风险分担机制对农户包容性升级的影响，并比较不同品类与平台的差异。","openalex","2026-10-08T00:07:47.273966Z",{"id":173,"title":174,"url":175,"summary":176,"summary_zh":8,"content":177,"source_name":178,"source_url":8,"published_at":179,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":180,"score_detail":181,"sources":184,"tags":186,"primary_topic":190,"secondary_topics":191,"classification":198,"search_phrases":212,"slug":215,"view_count":20,"doi":8,"paper":8,"created_at":216},4399,"湖北省农科院武汉江夏国家猕猴桃种质资源圃 100 多份材料陆续进入成熟期","https:\u002F\u002Fchangjiangyun.cjyun.org\u002Fp\u002F4634134.html","湖北省农科院国家柑橘产业技术体系猕猴桃武汉综合试验站,金秋时节武汉江夏国家猕猴桃种质资源圃内 100 多份猕猴桃材料陆续进入成熟期,黄肉、红心、绿肉果实挂满枝头;金魁、金农、金阳等本土优良品种迎来丰收,副研究员罗轩评估今年长势不错、产量有增加。","汉川融媒记者 张彤：湖北的秋天什么颜色最动人？今天，我们来到汉川南河古渡，一起去寻找属于江汉平原的丰收金。\n\n汉川南河古渡，2.4万多亩生态蟹塘进入捕捞季。依托襄河活水，当地运用微孔增氧、水质调控等技术，河蟹养殖告别“靠天收”，转向生态提质。\n\n蟹肥时节，丰收滋味从塘头端上餐桌。9月30日，公安县举办陆逊湖大闸蟹丰收季厨艺大赛，以美食擦亮农产品牌。\n\n参赛厨师 莫利龙：陆逊湖大闸蟹，水质优、生长环境好、肉质紧实鲜甜、蟹黄饱满，是我们公安最具代表性的本土优质食材。","长江云 2026-10-04","2026-10-04T00:00:00Z",32,{"impact":47,"substance":65,"depth":182,"authority":47,"freshness":182,"relevant":20,"comment":183},5,"标题指向猕猴桃种质资源，但正文实为大闸蟹丰收报道，内容与标题严重不符，信息增量有限，不建议进入每日精选。",[185],{"name":178,"url":175},[187,25,188,189],"种业振兴","湖北省农科院","种质资源圃",{"code":34,"slug":35,"name":36,"path":37,"parent_code":38},[192],{"code":193,"slug":194,"name":195,"path":196,"parent_code":197},"F1","seed-industry","种业与品种管理","\u002Ftopic\u002Finputs-equipment\u002Fseed-industry","F",{"status":41,"locked":13,"version":42,"method":43,"evidence":199},{"candidates":200,"agricultural_evidence":48},[201,207],{"code":34,"score":202,"supported":48,"title":203,"abstract":204,"tags":206},15,[25],[205,25],"柑橘",[25],{"code":193,"score":18,"supported":48,"title":208,"abstract":210,"tags":211},[209],"种质资源",[209],[187],[213,214],"湖北农科院 猕猴桃 种质资源圃","武汉江夏 猕猴桃 成熟期","湖北农科院猕猴桃种质资源圃-4399","2026-10-08T00:06:56.841965Z",{"id":218,"title":219,"url":220,"summary":221,"summary_zh":222,"content":8,"source_name":223,"source_url":220,"published_at":224,"category":118,"cover_url":8,"hotness":12,"is_selected":13,"score":225,"score_detail":226,"sources":230,"tags":232,"primary_topic":236,"secondary_topics":237,"classification":238,"search_phrases":256,"slug":259,"view_count":247,"doi":260,"paper":261,"created_at":279},3255,"Grape yield estimation using on-the-fly MIMO millimeter-wave radar at operational field speed: A variety-dependent proof of concept","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112395","Accurate pre-harvest grape yield estimation is a critical challenge in precision viticulture, yet current optical approaches (RGB cameras, LiDAR) are fundamentally limited by foliage occlusion and sensitivity to ambient lighting conditions. This paper presents a ground-based grape yield estimation system using a dual 77 GHz Multiple-Input Multiple-Output (MIMO) Frequency-Modulated Continuous-Wave (FM-CW) radar mounted on a rover operating at an average speed of 1.0 m\u002Fs (3.7 km\u002Fh), matching practical vineyard tractor speeds. Unlike prior radar-based studies conducted in static or slow-moving setups, the proposed pipeline achieves continuous 3D reconstruction of vinerows through digital beamforming in the elevation plane, combined with an IMU-fused Kalman filter for point cloud stabilization on irregular terrain. An experimental campaign was conducted on 136 km of scanned vinerows across seven grape varieties and three phenological growth stages (BBCH 75–89) in a commercial vineyard in Gascony, France. Statistical features extracted from 3D radar echo level images are used to train a Support Vector Regressor (SVR) evaluated in cross-validation. The primary out-of-sample result is a cross-validation Mean Absolute Error (CV MAE) of 31.2% on the full multi-variety dataset without any defoliation, achieved against certified wine-vat bulk weights as the ground truth reference. This figure should be contextualized against the ∼ 24–25% discrepancy observed between portable field weighing plates and vat-certified weights across the same dataset, and against manual pre-harvest estimation errors routinely exceeding 30% in viticultural practice. A sensitivity analysis over physical parameters reveals that grape variety is the dominant −and limiting- source of performance heterogeneity: CV MAE ranges from 7% for Tannat to 69% for Baco, demonstrating that a single global model is insufficient for multi-variety deployment and that variety-specific calibration is a necessary condition for operational use. These results are best understood as an architectural proof of concept: the primary contribution is the demonstration that MIMO digital beamforming removes the speed bottleneck of prior mechanically-scanned radar systems, enabling gapless 3D vinerow reconstruction at practical field speeds. The yield estimation results provide a first quantitative characterization of the system’s sensing capability and its variety-dependent limitations and establish a baseline for future variety-specific model development.","准确的采前葡萄产量估测是精准葡萄栽培中的一项关键挑战，然而当前的光学方法（RGB相机、LiDAR）从根本上受到冠层遮挡和对环境光照条件敏感性的限制。本文提出了一种地基葡萄产量估测系统，采用双77 GHz多输入多输出（MIMO）调频连续波（FM-CW）雷达，搭载于以平均速度1.0 m\u002Fs（3.7 km\u002Fh）行驶的移动平台上，与实际葡萄园拖拉机作业速度相匹配。与先前在静态或慢速移动装置中进行的雷达研究不同，所提出的处理流程通过仰角平面上的数字波束成形实现葡萄行连续三维重建，并结合IMU融合卡尔曼滤波器在不规则地形上实现点云稳定。在法国加斯科尼的一个商业葡萄园中，对七个葡萄品种和三个物候生长期（BBCH 75–89）的136 km扫描葡萄行进行了实验。从三维雷达回波强度图像中提取的统计特征用于训练支持向量回归器（SVR），并通过交叉验证进行评估。主要样本外结果为：在完整多品种数据集上、未进行任何去叶处理的情况下，交叉验证平均绝对误差（CV MAE）为31.2%，以认证酒罐散装重量作为地面真值参考。该数值应结合以下背景加以理解：在同一数据集上，便携式田间称重板与酒罐认证重量之间观察到约24–25%的差异，而葡萄栽培实践中人工采前估测误差通常超过30%。对物理参数的敏感性分析表明，葡萄品种是性能异质性的主要——也是限制性——来源：CV MAE从Tannat的7%到Baco的69%不等，表明单一全局模型不足以支持多品种部署，品种特异性校准是实际应用的必要条件。这些结果最好被理解为一种架构层面的概念验证：主要贡献在于证明了MIMO数字波束成形消除了先前机械扫描雷达系统的速度瓶颈，从而能够在实际田间速度下实现无间隙三维葡萄行重建。产量估测结果首次定量表征了该系统的感知能力及其品种依赖性局限，并为未来","Computers and Electronics in Agriculture","2026-09-23T00:00:00Z",84,{"impact":16,"substance":227,"depth":228,"authority":123,"freshness":12,"relevant":20,"comment":229},23,19,"首次在实用田间车速下用MIMO毫米波雷达实现葡萄产量预估，136公里商业园数据与品种依赖性结论具参考价值。",[231],{"name":223,"url":220},[82,233,29,234,235],"精准农业","产量预估","毫米波雷达",{"code":34,"slug":35,"name":36,"path":37,"parent_code":38},[],{"status":41,"locked":13,"version":42,"method":43,"evidence":239},{"candidates":240,"agricultural_evidence":48},[241,246,252],{"code":34,"score":202,"supported":48,"title":242,"abstract":244,"tags":245},[243],"grape",[29,243],[29],{"code":101,"score":247,"supported":48,"title":248,"abstract":249,"tags":251},3,[],[250],"tractor",[],{"code":96,"score":62,"supported":13,"title":253,"abstract":254,"tags":255},[],[],[82,233],[257,258],"MIMO 毫米波雷达 葡萄 产量预估","葡萄园 雷达 三维重建","MIMO毫米波雷达葡萄产量预估-3255","10.1016\u002Fj.compag.2026.112395",{"doi":260,"openalex_id":262,"authors":263,"venue":223,"cited_by_count":109,"oa_url":220,"card":273,"direction":277,"ingested_from":170},"W7214043753",[264,267,270],{"name":265,"orcid":266},"Etienne Dedic","https:\u002F\u002Forcid.org\u002F0000-0002-1414-019X",{"name":268,"orcid":269},"Dominique Henry","https:\u002F\u002Forcid.org\u002F0000-0002-6016-140X",{"name":271,"orcid":272},"H. Aubert","https:\u002F\u002Forcid.org\u002F0000-0002-6113-0648",{"tldr":274,"method":275,"finding":276,"direction":277,"opportunity":278},"用双77GHz MIMO雷达在1m\u002Fs车速下重建葡萄藤行并估算产量，验证品种依赖性。","双77GHz MIMO FMCW雷达、数字波束成形、IMU卡尔曼滤波、SVR，1","全品种交叉验证MAE为31.2%，但品种间差异大（Tannat 7%至Baco 69%），需按品种校","农业遥感与作物表型","可研究品种自适应建模与迁移学习，解决多品种部署时单一模型失效问题，并融合光学与雷达数据。","2026-09-23T23:30:01.516727Z",{"id":281,"title":282,"url":283,"summary":284,"summary_zh":8,"content":8,"source_name":128,"source_url":8,"published_at":285,"category":118,"cover_url":8,"hotness":12,"is_selected":13,"score":286,"score_detail":287,"sources":289,"tags":291,"primary_topic":295,"secondary_topics":296,"classification":302,"search_phrases":330,"slug":333,"view_count":62,"doi":8,"paper":334,"created_at":342},3245,"Shaanxi Kiwi Farmers Break Free from Yield-Security FoMO（陕西猕猴桃农户摆脱\"产量安全错失恐惧\"）——Frontiers Sustain Food Syst 试错经验可破除数字养分管理技术采纳障碍","https:\u002F\u002Fagritechinsights.com\u002Findex.php\u002F2026\u002F09\u002F19\u002Fshaanxi-kiwi-farmers-break-free-from-yield-security-fomo","Frontiers in Sustainable Food Systems 发表研究：马来西亚博特拉大学Xia Li等学者针对中国陕西省675户猕猴桃种植户开展调研，发现\"产量安全错失恐惧（Yield-Security FoMO）\"——农户对不使用每一种可用工具以最大化产量的焦虑——是数字养分管理技术（土壤检测仪、叶绿素仪、农技咨询App等）采纳的主要障碍。研究发现，虽然感知有用性和相对优势能促进采纳，但产量安全错失恐惧对三种技术的采纳意向均呈持续负面影响。然而，参与结构化\"动手试错\"体验的农户更可能采纳土壤检测仪和叶绿素仪，且该恐惧对决策的影响更小。对农技咨询App影响较小，说明试错体验的效应可能因技术而异。该研究为农技企业和政策制定者提供启示：让农户亲手尝试新技术是弥合怀疑与采纳之间鸿沟的关键。","2026-09-19T00:00:00Z",77,{"impact":17,"substance":122,"depth":16,"authority":77,"freshness":47,"relevant":20,"comment":288},"基于675户调研揭示FoMO阻碍数字养分管理技术采纳、试错体验可缓解，对农技推广有实证参考价值。",[290],{"name":128,"url":283},[82,292,25,293,294],"农户采纳","陕西","数字农业技术",{"code":34,"slug":35,"name":36,"path":37,"parent_code":38},[297],{"code":298,"slug":299,"name":300,"path":301,"parent_code":197},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers",{"status":41,"locked":13,"version":42,"method":43,"evidence":303},{"candidates":304,"agricultural_evidence":48},[305,309,315,321,326],{"code":34,"score":18,"supported":48,"title":306,"abstract":307,"tags":308},[25],[25],[25],{"code":298,"score":310,"supported":48,"title":311,"abstract":313,"tags":314},11,[312],"养分管理",[312],[],{"code":316,"score":247,"supported":48,"title":317,"abstract":318,"tags":320},"H2",[],[319],"土壤",[],{"code":322,"score":20,"supported":13,"title":323,"abstract":324,"tags":325},"G2",[],[],[292],{"code":96,"score":20,"supported":13,"title":327,"abstract":328,"tags":329},[],[],[82],[331,332],"陕西 猕猴桃 数字养分管理","产量安全错失恐惧 农户采纳","陕西猕猴桃数字养分管理-3245",{"doi":8,"openalex_id":8,"authors":335,"venue":8,"cited_by_count":109,"oa_url":8,"card":336,"direction":168,"ingested_from":341},[],{"tldr":337,"method":338,"finding":339,"direction":168,"opportunity":340},"陕西675户猕猴桃种植户调研发现，产量安全错失恐惧阻碍数字养分管理技术采纳，试错体验可缓解。","对陕西675户猕猴桃种植户问卷调查，分析FoMO与三种数字技术采纳意向关系。","产量安全错失恐惧持续负向影响采纳；动手试错体验提升土壤检测仪和叶绿素仪采纳，对App影响小。","可探究不同数字农业技术中试错体验的差异化机制，设计降低农户FoMO的干预策略。","agent","2026-09-23T00:04:33.090863Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":348,"content":8,"source_name":349,"source_url":346,"published_at":350,"category":118,"cover_url":8,"hotness":12,"is_selected":13,"score":351,"score_detail":352,"sources":355,"tags":357,"primary_topic":361,"secondary_topics":362,"classification":368,"search_phrases":399,"slug":402,"view_count":62,"doi":403,"paper":404,"created_at":420},2874,"Laboratory Evaluation of Multispectral Grape Quality Grade Prediction with Compensation for Controlled Illumination Variation","https:\u002F\u002Fdoi.org\u002F10.1088\u002F2631-8695\u002Faea952","Abstract Accurate fruit quality assessment is important for selective harvesting in agricultural robotics, where multispectral sensing provides a non-destructive approach but remains sen- sitive to variability in illumination conditions. This study presents a controlled laboratory evaluation conducted in a dark box under halogen illumination with fixed sensor and sam- ple geometry, in which illumination variation was simulated by adjusting lamp intensity. Prediction models for visually assigned grape quality grades were first established under fixed illumination using an AS7265x multispectral sensor with 18 channels from 410 to 940 nm, covering the visible and part of the near-infrared range. Spectral data were prepro- cessed using standard normal variate transformation, standardization, variable importance in projection feature selection, and mixup interpolation. Three machine learning meth- ods, partial least squares regression, support vector regression, and random forest, were evaluated with nested cross-validation, out-of-fold prediction, and 2000-iteration bootstrap resampling. Support vector regression achieved the best performance, with R² = 0.9084 [95% CI: 0.851–0.945], RMSE = 0.3352, and MAE = 0.2374. To address illumination vari- ability, three compensation methods, direct standardization, extended multiplicative scatter correction, and a polynomial per-band fitting method, were implemented and compared across five lamp intensity levels from 20% to 100% of rated power. The three methods and the uncompensated condition reached similar mean accuracy across the five levels, with the exception of extended multiplicative scatter correction, which was lower at every level. Di- rect standardization reduced the spread of the five predictions obtained for the same berry by about 31% relative to no compensation, and gave the highest grade-level accuracy of the four conditions. These results provide laboratory feasibility evidence that direct standard- ization can improve the consistency of grade prediction across controlled illumination levels, and establish a basis for further validation under natural field illumination toward future robotic harvesting applications.","摘要 准确的水果品质评估对于农业机器人中的选择性采收至关重要，其中多光谱传感提供了一种非破坏性方法，但仍对光照条件的变化较为敏感。本研究提出了一种在暗箱中、卤素灯照明下、传感器与样品几何构型固定的受控实验室评估方法，通过调节灯强度来模拟光照变化。首先在固定光照条件下，使用AS7265x多光谱传感器（具有410至940 nm范围内的18个通道，覆盖可见光及部分近红外波段）建立了视觉 assigned 葡萄品质等级的预测模型。光谱数据采用标准正态变量变换、标准化、投影变量重要性特征选择以及mixup插值进行预处理。采用嵌套交叉验证、折外预测和2000次迭代自助重采样，对偏最小二乘回归、支持向量回归和随机森林三种机器学习方法进行了评估。支持向量回归取得了最佳性能，R² = 0.9084 [95% CI: 0.851–0.945]，RMSE = 0.3352，MAE = 0.2374。为解决光照变化问题，实施了直接标准化、扩展多元散射校正和逐波段多项式拟合三种补偿方法，并在额定功率20%至100%的五个灯强度水平下进行了比较。三种方法及未补偿条件在五个水平下达到了相似的平均准确率，但扩展多元散射校正除外，其在每个水平下均较低。与未补偿相比，直接标准化使同一浆果五次预测结果的离散度降低了约31%，并在四种条件中给出了最高的等级准确率。这些结果为直接标准化能够提高受控光照水平下等级预测的一致性提供了实验室可行性证据，并为未来机器人采收应用中在自然田间光照下进一步验证奠定了基础。","Engineering Research Express","2026-09-17T00:00:00Z",66,{"impact":47,"substance":353,"depth":76,"authority":77,"freshness":47,"relevant":20,"comment":354},20,"实验室条件下多光谱葡萄品质分级与光照补偿研究，方法扎实、结论可靠，但属实验室可行性验证，产业影响有限。",[356],{"name":349,"url":346},[82,358,29,359,360],"农业人工智能","多光谱检测","水果品质分级",{"code":34,"slug":35,"name":36,"path":37,"parent_code":38},[363],{"code":364,"slug":365,"name":366,"path":367,"parent_code":150},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":41,"locked":13,"version":42,"method":43,"evidence":369},{"candidates":370,"agricultural_evidence":48},[371,375,380,388,395],{"code":34,"score":202,"supported":48,"title":372,"abstract":373,"tags":374},[243],[29,243],[29],{"code":364,"score":310,"supported":48,"title":376,"abstract":378,"tags":379},[377],"multispectral",[377],[],{"code":381,"score":382,"supported":48,"title":383,"abstract":384,"tags":387},"I2",7,[],[385,386],"机器学习","machine learning",[358],{"code":389,"score":65,"supported":48,"title":390,"abstract":391,"tags":394},"F6",[],[392,393],"农业机器人","robotic harvesting",[],{"code":96,"score":20,"supported":13,"title":396,"abstract":397,"tags":398},[],[],[82],[400,401],"多光谱 葡萄 品质分级","AS7265x 多光谱传感器","多光谱葡萄品质分级-2874","10.1088\u002F2631-8695\u002Faea952",{"doi":403,"openalex_id":405,"authors":406,"venue":349,"cited_by_count":109,"oa_url":346,"card":414,"direction":419,"ingested_from":170},"W7213509882",[407,409,411],{"name":408,"orcid":8},"Guodong Xiu",{"name":410,"orcid":8},"Sára Strakošová",{"name":412,"orcid":413},"Ikuo Mizuuchi","https:\u002F\u002Forcid.org\u002F0000-0003-4657-2613",{"tldr":415,"method":416,"finding":417,"direction":277,"opportunity":418},"在暗箱中评估多光谱葡萄品质分级预测，并比较三种光照补偿方法。","AS7265x多光谱传感器、SNV与VIP预处理、SVR\u002FRF建模、直接标准化等","SVR预测最佳（R²=0.9084）；直接标准化使同果预测离散度降低约31%。","可延伸至自然田间光照下的验证，并融合机器人采摘的实时多光谱分级系统。","农业人工智能与决策模型","2026-09-18T23:30:52.790038Z"]