[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2858":3,"related-2858":99},{"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":30,"secondary_topics":35,"classification":36,"search_phrases":84,"slug":87,"view_count":64,"doi":8,"paper":88,"created_at":98},2858,"农业视觉感知综述:基于4D混沌和Mamba网络的新颖隐私保护框架——Frontiers in Plant Science 9月17日","https:\u002F\u002Fwww.ebiotrade.com\u002Fnewsf\u002F2026-9\u002F20260917000338095.htm","基于冬小麦-夏玉米双季种植系统的长期定位田间试验,氮肥后效对土壤-作物协调及微生物功能的调控机制尚不明确。试验设置四个处理:CK(小麦季和玉米季均不施氮)、W1M0(仅在冬小麦季施氮)、W0M1(仅在夏玉米季施氮)、W1M1(小麦季和玉米季均施氮)。与不施氮对照(CK)相比,W1M0和W0M1分别使平均年产量提高45.7%和42.2%,而W1M1提高58.6%。PLS-SEM揭示,前茬小麦季土壤氮含量解释了后茬玉米土壤理化性质97.5%的方差。",null,"Frontiers in Plant Science \u002F 生物通","2026-09-17T00:00:00Z","论文",10,false,78,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":20,"comment":21},18,20,17,13,1,"该文提出基于4D混沌与Mamba网络的农业视觉感知隐私保护框架，方法新颖且属农业人工智能前沿交叉方向，信源为核心期刊，时效性强，具备进入每日精选的价值。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","农业遥感","作物表型","隐私保护",{"code":31,"slug":32,"name":33,"path":34,"parent_code":8},"A","field-crops","大田作物","\u002Ftopic\u002Ffield-crops",[],{"status":37,"locked":13,"version":38,"method":39,"evidence":40},"partial","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":45,"reason":83},[42,50,56,62,68,73,78],{"code":43,"score":44,"supported":45,"title":46,"abstract":47,"tags":49},"A2",3,true,[],[48],"小麦",[],{"code":51,"score":44,"supported":45,"title":52,"abstract":53,"tags":55},"A3",[],[54],"玉米",[],{"code":57,"score":44,"supported":45,"title":58,"abstract":59,"tags":61},"H2",[],[60],"土壤",[],{"code":63,"score":64,"supported":13,"title":65,"abstract":66,"tags":67},"I3",2,[],[],[28,27],{"code":69,"score":20,"supported":13,"title":70,"abstract":71,"tags":72},"I1",[],[],[25],{"code":74,"score":20,"supported":13,"title":75,"abstract":76,"tags":77},"I2",[],[],[26],{"code":79,"score":20,"supported":13,"title":80,"abstract":81,"tags":82},"I6",[],[],[29],"一级领域明确，二级方向需要细分",[85,86],"农业人工智能 作物表型 农业遥感 智慧农业","农业人工智能 作物表型","农业人工智能作物表型农业遥感智慧农业-2858",{"doi":8,"openalex_id":8,"authors":89,"venue":8,"cited_by_count":90,"oa_url":8,"card":91,"direction":95,"ingested_from":97},[],0,{"tldr":92,"method":93,"finding":94,"direction":95,"opportunity":96},"通过长期定位试验研究氮肥后效对冬小麦-夏玉米轮作系统土壤-作物协调及微生物功能的调控机制。","长期定位田间试验，设置四种施氮处理，结合PLS-SEM分析。","双季施氮年产量提高58.6%，前茬小麦季土壤氮解释后茬玉米土壤理化性质97.5%的方差。","农业绿色发展与碳","可探究氮肥后效对土壤微生物功能及碳氮循环的长期影响，优化轮作施氮策略。","agent","2026-09-18T00:03:31.115969Z",{"total":100,"page":20,"page_size":100,"items":101},6,[102,240,319,397,447,511],{"id":103,"title":104,"url":105,"summary":106,"summary_zh":107,"content":8,"source_name":108,"source_url":105,"published_at":109,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":110,"score_detail":111,"sources":116,"tags":118,"primary_topic":122,"secondary_topics":123,"classification":124,"search_phrases":176,"slug":179,"view_count":90,"doi":180,"paper":181,"created_at":239},5314,"A data‐driven image extraction and analysis pipeline for plant phenotyping in controlled environments","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fppj2.70116","Abstract Advances in automation, imaging, and artificial intelligence have enabled large‐scale plant phenotyping, but image analysis remains a critical bottleneck for crop improvement and biological discovery. We developed an integrated multispectral phenotyping framework using imagery from the Texas A&M AgriLife Automated Precision Phenotyping Greenhouse and expanded plant growth and phenotyping (PGP v2) data across maize ( Zea mays L.), cotton ( Gossypium hirsutum ), rice ( Oryza sativa ), and sorghum ( Sorghum bicolor L.). The pipeline integrates pseudo‐red‐green‐blue composite image generation, plant detection and segmentation, image stitching, vegetation‐index analysis, texture analysis, morphological trait extraction, and temporal comparison of image‐derived features to quantify changes in plant structure, spectral reflectance, and texture over time. Among the evaluated segmentation approaches, segment anything model (SAM) v3 provided the highest and most consistent accuracy across diverse crop structures, although it required greater computational time than classical methods. Segment anything model for long sequences (SAM2Long)maintained plant‐instance associations across vertically stacked frames, while scale‐invariant feature transform–based stitching reconstructed plant mosaics when individual plants extended beyond a single field of view. For each plant and imaging date, the pipeline generated an 863‐dimensional feature vector spanning vegetation indices, spectral statistics, texture descriptors, and morphological traits. The framework was evaluated through two case studies: treatment‐level temporal analysis of mutagenized sorghum lines and cold‐stress phenotyping of maize using a separate imaging system. In both studies, the extracted features supported statistical and multivariate analyses of phenotypic variation and enabled separation of plants based on treatment‐ or stress‐related responses. The combined dataset and workflow provide structured, automated, and well‐documented phenotypic analysis across multiple crops, experimental settings, and imaging systems for controlled‐environment plant science and crop improvement.","摘要　自动化、成像和人工智能的进步使得大规模植物表型分析成为可能，但图像分析仍然是作物改良和生物学发现的关键瓶颈。我们利用德克萨斯农工大学农业生命科学自动化精准表型温室（Texas A&M AgriLife Automated Precision Phenotyping Greenhouse）的图像，开发了一个集成多光谱表型分析框架，并扩展了玉米（Zea mays L.）、棉花（Gossypium hirsutum）、水稻（Oryza sativa）和高粱（Sorghum bicolor L.）的植物生长与表型分析（plant growth and phenotyping，PGP v2）数据。该流程整合了伪红绿蓝合成图像生成、植物检测与分割、图像拼接、植被指数分析、纹理分析、形态性状提取以及图像衍生特征的时间比较，以量化植物结构、光谱反射率和纹理随时间的变化。在评估的分割方法中，segment anything model（SAM）v3在不同作物结构下提供了最高且最一致的准确性，尽管其所需计算时间多于经典方法。面向长序列的segment anything model（SAM2Long）在垂直堆叠帧之间维持了植物实例关联，而基于尺度不变特征变换（scale-invariant feature transform）的拼接在单株植物超出单一视野时重建了植物拼接图。对于每株植物和每个成像日期，该流程生成了一个863维特征向量，涵盖植被指数、光谱统计量、纹理描述符和形态性状。该框架通过两个案例研究进行了评估：诱变高粱品系的处理水平时间分析，以及使用独立成像系统对玉米进行的冷胁迫表型分析。在这两项研究中，提取的特征支持了表型变异的统计分析和多变量分析，并能够根据处理或胁迫相关响应区分植物。合并的数据集和工作流程为受控环境植物科学和作物改良提供了跨多种作物、实验设置和成像系统的结构化、自动化且记录完善的表型分析。","The Plant Phenome Journal","2026-10-18T00:00:00Z",81,{"impact":16,"substance":112,"depth":16,"authority":113,"freshness":114,"relevant":20,"comment":115},22,14,9,"该研究提出一套面向多作物的自动化多光谱表型分析流程，方法新颖、数据规模可观，对智慧育种与受控环境植物科学研究具有较高参考价值。",[117],{"name":108,"url":105},[25,26,119,120,121],"图像分割","表型组学","多光谱成像",{"code":31,"slug":32,"name":33,"path":34,"parent_code":8},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":125},{"candidates":126,"agricultural_evidence":45,"reason":83},[127,134,139,146,153,160,166,172],{"code":128,"score":100,"supported":45,"title":129,"abstract":130,"tags":133},"A1",[],[131,132],"水稻","rice",[],{"code":51,"score":100,"supported":45,"title":135,"abstract":136,"tags":138},[],[54,137],"maize",[],{"code":140,"score":100,"supported":45,"title":141,"abstract":142,"tags":145},"A5",[],[143,144],"高粱","sorghum",[],{"code":147,"score":100,"supported":45,"title":148,"abstract":149,"tags":152},"A6",[],[150,151],"棉花","cotton",[],{"code":154,"score":100,"supported":45,"title":155,"abstract":156,"tags":159},"B7",[],[157,158],"温室","greenhouse",[],{"code":74,"score":161,"supported":45,"title":162,"abstract":163,"tags":165},5,[],[164],"artificial intelligence",[26,119],{"code":63,"score":167,"supported":45,"title":168,"abstract":169,"tags":171},4,[],[170],"multispectral",[121],{"code":69,"score":20,"supported":13,"title":173,"abstract":174,"tags":175},[],[],[25],[177,178],"Texas A&M 自动化表型温室","玉米 高粱 多光谱表型","TexasAM自动化表型温室-5314","10.1002\u002Fppj2.70116",{"doi":180,"openalex_id":182,"authors":183,"venue":108,"cited_by_count":90,"oa_url":105,"card":232,"direction":236,"ingested_from":238},"W7222893982",[184,186,189,192,195,197,199,202,205,208,211,214,217,220,223,226,228,230],{"name":185,"orcid":8},"Fahimeh Orvati Nia",{"name":187,"orcid":188},"Joshua Peeples","https:\u002F\u002Forcid.org\u002F0000-0001-7861-7789",{"name":190,"orcid":191},"Seth C. Murray","https:\u002F\u002Forcid.org\u002F0000-0002-2960-8226",{"name":193,"orcid":194},"Andrew J. McFarland","https:\u002F\u002Forcid.org\u002F0009-0000-3516-8274",{"name":196,"orcid":8},"Troy Vann",{"name":198,"orcid":8},"Shima Salehi",{"name":200,"orcid":201},"Robert G. Hardin","https:\u002F\u002Forcid.org\u002F0000-0002-0714-8281",{"name":203,"orcid":204},"David D. Baltensperger","https:\u002F\u002Forcid.org\u002F0000-0003-4511-5680",{"name":206,"orcid":207},"Amir M. H. Ibrahim","https:\u002F\u002Forcid.org\u002F0000-0002-0584-753X",{"name":209,"orcid":210},"J. Alex Thomasson","https:\u002F\u002Forcid.org\u002F0000-0002-5557-105X",{"name":212,"orcid":213},"Henry Y. Fadamiro","https:\u002F\u002Forcid.org\u002F0000-0002-4530-9680",{"name":215,"orcid":216},"Nithya K. Subramanian","https:\u002F\u002Forcid.org\u002F0000-0002-1659-7396",{"name":218,"orcid":219},"Suresh D. Pillai","https:\u002F\u002Forcid.org\u002F0000-0002-9766-8765",{"name":221,"orcid":222},"Rebecca Roston","https:\u002F\u002Forcid.org\u002F0000-0002-3063-5002",{"name":224,"orcid":225},"Joslin Ishimwe","https:\u002F\u002Forcid.org\u002F0009-0003-6999-7718",{"name":227,"orcid":8},"Diptadeep Basak",{"name":229,"orcid":8},"Nazar Oladepo",{"name":231,"orcid":8},"Uday Santhosh Raju Vysyaraju",{"tldr":233,"method":234,"finding":235,"direction":236,"opportunity":237},"构建多光谱图像提取分析流程，实现多作物表型自动化量化。","用温室多光谱图像，集成SAM v3分割、SIFT拼接与863维特征提取。","SAM v3分割最准，特征可区分高粱诱变与玉米冷胁迫响应。","农业遥感与作物表型","可探索轻量化分割模型与跨成像系统迁移，降低计算成本并拓展田间表型。","openalex","2026-10-19T23:30:17.276726Z",{"id":241,"title":242,"url":243,"summary":244,"summary_zh":245,"content":8,"source_name":246,"source_url":243,"published_at":247,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":248,"score_detail":249,"sources":253,"tags":255,"primary_topic":259,"secondary_topics":260,"classification":261,"search_phrases":294,"slug":297,"view_count":90,"doi":298,"paper":299,"created_at":318},4901,"Feature-level fusion of Sentinel-1 SAR and Sentinel-2 optical imagery for crop-type mapping in humid tropical mountainous terrain","https:\u002F\u002Fdoi.org\u002F10.64960\u002Feasr.2026.263460","Accurate crop-type mapping in humid tropical mountains is challenged by persistent cloud cover, rugged topography, and fragmented smallholder parcels. This study evaluates a feature-level fusion workflow that integrates Sentinel-2 optical indices and Sentinel-1 SAR backscatter for crop-type mapping in Candipuro District, Lumajang, East Java, Indonesia. Sentinel-2 surface reflectance and Sentinel-1 IW data acquired in June–July 2023 were harmonised in Google Earth Engine to a common 10 m pixel grid, so that all comparison maps were evaluated on the same spatial support. The optical component comprised NDVI, NDBI, and NDWI, whereas the radar component used the VH\u002FVV polarisation ratio. A DEM was used only to characterise the mountainous setting and to assist terrain interpretation, and was not included as a predictor in the classifier. The stacked feature image was classified using a Random Forest model trained with 101 field-survey ground control points representing eight land-cover\u002Fcrop-related classes. Accuracy was assessed using 393 stratified random validation points. The fused-image classification achieved an overall accuracy of 93% and a kappa coefficient of 0.90. The fusion workflow yielded richer thematic differentiation than the optical-only comparison scenarios, particularly for water bodies, sugarcane, and shrubland. However, class-level results reveal substantial uncertainty for corn fields and moderate confusion in built-up and water classes. Therefore, the present workflow should be interpreted as a site-specific, single-date proof of concept rather than a fully transferable operational solution. The results indicate that Sentinel-1\u002FSentinel-2 feature fusion is promising for crop-type mapping in cloud-prone mountainous landscapes, while future work should incorporate multi-temporal phenology, richer vegetation indices, SAR texture features, uncertainty mapping, and broader field sampling.","在湿润的热带山区，准确的作物类型制图面临持续云覆盖、崎岖地形和破碎的小农户地块等挑战。本研究评估了一种特征级融合工作流，该工作流整合了Sentinel-2光学指数与Sentinel-1 SAR后向散射数据，用于印度尼西亚东爪哇省卢马姜县坎迪普罗区的作物类型制图。2023年6月至7月获取的Sentinel-2地表反射率和Sentinel-1 IW数据在Google Earth Engine中统一至共同的10 m像元网格，以确保所有对比制图均在相同的空间支撑上进行评估。光学组分包括NDVI、NDBI和NDWI，雷达组分则使用VH\u002FVV极化比值。DEM仅用于表征山区环境并辅助地形解译，未作为预测变量纳入分类器。堆叠特征影像采用随机森林模型进行分类，该模型以101个野外调查地面控制点进行训练，代表八个土地覆盖\u002F作物相关类别。精度评估使用393个分层随机验证点。融合影像分类的总体精度达到93%，Kappa系数为0.90。与仅光学对比方案相比，融合工作流产生了更丰富的专题区分能力，尤其在水体、甘蔗和灌木地方面。然而，类别层面的结果揭示了玉米田存在较大不确定性，建成区和水体类别存在中等程度的混淆。因此，本工作流应被解读为特定站点的单日期概念验证，而非完全可迁移的业务化方案。结果表明，Sentinel-1\u002FSentinel-2特征融合在多云山区景观的作物类型制图中具有前景，未来工作应纳入多时相物候、更丰富的植被指数、SAR纹理特征、不确定性制图以及更广泛的野外采样。","Engineering and Applied Science Research","2026-10-12T00:00:00Z",66,{"impact":250,"substance":17,"depth":18,"authority":251,"freshness":114,"relevant":20,"comment":252},8,12,"方法扎实、精度可观的遥感作物制图概念验证研究，但属单点单时相案例，公共影响有限，适合作为技术参考而非每日精选头条。",[254],{"name":246,"url":243},[25,26,256,257,258],"遥感","作物识别","哨兵卫星",{"code":31,"slug":32,"name":33,"path":34,"parent_code":8},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":262},{"candidates":263,"agricultural_evidence":45,"reason":83},[264,269,275,282,286,290],{"code":51,"score":100,"supported":45,"title":265,"abstract":266,"tags":268},[],[54,267],"corn",[],{"code":147,"score":100,"supported":45,"title":270,"abstract":271,"tags":274},[],[272,273],"甘蔗","sugarcane",[],{"code":276,"score":100,"supported":45,"title":277,"abstract":278,"tags":281},"G2",[],[279,280],"小农户","smallholder",[],{"code":69,"score":20,"supported":13,"title":283,"abstract":284,"tags":285},[],[],[25],{"code":74,"score":20,"supported":13,"title":287,"abstract":288,"tags":289},[],[],[26],{"code":63,"score":20,"supported":13,"title":291,"abstract":292,"tags":293},[],[],[256],[295,296],"Sentinel-1 Sentinel-2 作物分类","印尼 东爪哇 作物制图","Sentinel-1Sentinel-2作物分类-4901","10.64960\u002Feasr.2026.263460",{"doi":298,"openalex_id":300,"authors":301,"venue":246,"cited_by_count":90,"oa_url":312,"card":313,"direction":236,"ingested_from":238},"W7221544367",[302,305,308,310],{"name":303,"orcid":304},"Indarto Indarto","https:\u002F\u002Forcid.org\u002F0000-0001-6319-6731",{"name":306,"orcid":307},"Gunawan Gunawan","https:\u002F\u002Forcid.org\u002F0000-0001-7914-3669",{"name":309,"orcid":8},"Mahrus Irsyam",{"name":311,"orcid":8},"Fahmi Arif Kurnanto","https:\u002F\u002Fph01.tci-thaijo.org\u002Findex.php\u002Feasr\u002Farticle\u002Fdownload\u002F263460\u002F176575",{"tldr":314,"method":315,"finding":316,"direction":236,"opportunity":317},"融合Sentinel-1 SAR与Sentinel-2光学特征，在印尼热带山地实现93%精度的作物类","Google Earth Engine中10米格网特征级融合NDVI\u002FNDBI\u002F","融合影像总体精度93%、kappa 0.90，优于仅光学方案，但玉米和建成区仍存在明显混淆。","可引入多时相物候、SAR纹理与不确定性制图，提升热带多云山区小农户破碎地块的作物识别与可迁移性。","2026-10-14T23:30:28.943594Z",{"id":320,"title":321,"url":322,"summary":323,"summary_zh":324,"content":8,"source_name":325,"source_url":322,"published_at":326,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":327,"score_detail":328,"sources":330,"tags":332,"primary_topic":336,"secondary_topics":337,"classification":338,"search_phrases":373,"slug":376,"view_count":90,"doi":377,"paper":378,"created_at":396},4234,"Opportunity Cost of Precision Conservation","https:\u002F\u002Fdoi.org\u002F10.3368\u002Fle.103.2.110525-0095r1","Abstract Conservation practices provide public environmental benefits, but the associated private costs are chiefly borne by farmers. Precision agriculture technologies can help reduce farmer private costs by identifying low-yielding areas, thereby minimizing foregone revenue. This study estimates the opportunity cost of such precision conservation on 29 commercial fields in Michigan, USA, using fine-scale yield maps collected between 2020 and 2024. We employ spatial regression models and Monte Carlo simulations to account for spatial heterogeneity and price variability. Results show that under a corn-soybean crop rotation, precision conservation improves profitability in 22 of 29 fields, indicating potential for adoption without government subsidies.","摘要 保护性耕作实践能带来公共环境效益，但相关的私人成本主要由农民承担。精准农业技术有助于通过识别低产区域来降低农民的私人成本，从而最大限度地减少放弃的收入。本研究利用2020年至2024年间收集的精细尺度产量图，估算了美国密歇根州29块商业农田上此类精准保护性耕作的机会成本。我们采用空间回归模型和蒙特卡洛模拟来处理空间异质性和价格波动。结果表明，在玉米-大豆轮作下，精准保护性耕作提高了29块农田中22块的盈利能力，表明无需政府补贴也具备采用潜力。","Land Economics","2026-10-02T00:00:00Z",80,{"impact":16,"substance":112,"depth":16,"authority":113,"freshness":250,"relevant":20,"comment":329},"基于2020-2024年29块商业田块精细产量图，量化精准保护性耕作的机会成本，结论显示多数田块无需补贴即可盈利，对智慧农业落地与农业绿色政策有参考价值。",[331],{"name":325,"url":322},[25,27,333,334,335],"精准农业","保护性耕作","产量地图",{"code":31,"slug":32,"name":33,"path":34,"parent_code":8},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":339},{"candidates":340,"agricultural_evidence":45,"reason":83},[341,346,350,357,364,369],{"code":69,"score":250,"supported":45,"title":342,"abstract":343,"tags":345},[],[333,344],"precision agriculture",[25,333],{"code":51,"score":100,"supported":45,"title":347,"abstract":348,"tags":349},[],[54,267],[],{"code":351,"score":100,"supported":45,"title":352,"abstract":353,"tags":356},"A4",[],[354,355],"大豆","soybean",[],{"code":358,"score":100,"supported":45,"title":359,"abstract":360,"tags":363},"A7",[],[361,362],"轮作","crop rotation",[],{"code":365,"score":167,"supported":45,"title":366,"abstract":367,"tags":368},"H8",[],[334],[334],{"code":63,"score":20,"supported":13,"title":370,"abstract":371,"tags":372},[],[],[27],[374,375],"密歇根 精准保护性耕作 机会成本","精准农业 产量地图 玉米大豆轮作","密歇根精准保护性耕作机会成本-4234","10.3368\u002Fle.103.2.110525-0095r1",{"doi":377,"openalex_id":379,"authors":380,"venue":325,"cited_by_count":90,"oa_url":390,"card":391,"direction":236,"ingested_from":238},"W7215722779",[381,384,387],{"name":382,"orcid":383},"Seo Woo Lee","https:\u002F\u002Forcid.org\u002F0009-0000-4165-9520",{"name":385,"orcid":386},"Scott M. Swinton","https:\u002F\u002Forcid.org\u002F0000-0002-3751-1811",{"name":388,"orcid":389},"Bruno Basso","https:\u002F\u002Forcid.org\u002F0000-0003-2090-4616","https:\u002F\u002Fle.uwpress.org\u002Fcontent\u002Fwple\u002Fearly\u002F2026\u002F09\u002F24\u002Fle.103.2.110525-0095R1.full.pdf",{"tldr":392,"method":393,"finding":394,"direction":95,"opportunity":395},"基于密歇根29块田的精细产量图，估算精准保护的机会成本并评估其经济可行性。","2020-2024年精细产量图，空间回归与蒙特卡洛模拟。","玉米-大豆轮作下，29块田中22块精准保护可提高利润，无需政府补贴。","可拓展至其他作物与区域，探究精准保护对农户收益与环境效益的协同机制。","2026-10-05T23:30:26.394346Z",{"id":398,"title":399,"url":400,"summary":401,"summary_zh":8,"content":8,"source_name":402,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":403,"sources":405,"tags":407,"primary_topic":409,"secondary_topics":410,"classification":411,"search_phrases":434,"slug":437,"view_count":100,"doi":8,"paper":438,"created_at":446},3324,"Diag-STFN：全球收获前作物产量预测的诊断时空多模态融合网络——覆盖38国玉米29国小麦（Ecological Informatics 2026）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37354974?&&labelLang=hun","《Ecological Informatics》2026年第96期：Zhuang等提出Diag-STFN——一种诊断时空多模态融合网络，用于全球收获前作物产量预测。该网络基于数据集特征选择模型结构，以确定是否需要时间趋势耦合和空间模块激活。在三种前置期（早、中、晚季）下，基于覆盖38国玉米和29国小麦的CY-Bench基准数据集进行评估。结果表明，所提方法在所有前置期均实现了两种作物的最低汇总NRMSE，并在MAPE和KGE等补充指标上保持领先。消融研究表明诊断模块选择提供了主要的性能提升；方差分解显示性能差异在国家之间大于模型之间。","《Ecological Informatics》96 (2026) 103860",{"impact":16,"substance":112,"depth":16,"authority":113,"freshness":100,"relevant":20,"comment":404},"方法新颖、覆盖38国玉米与29国小麦的全球收获前产量预测研究，学术价值突出但产业落地尚早，适合作为前沿技术资讯收录。",[406],{"name":402,"url":400},[25,26,408,48,54,256],"产量预测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":8},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":412},{"candidates":413,"agricultural_evidence":45,"reason":83},[414,418,422,426,430],{"code":43,"score":251,"supported":45,"title":415,"abstract":416,"tags":417},[48],[48],[48],{"code":51,"score":251,"supported":45,"title":419,"abstract":420,"tags":421},[54],[54],[54],{"code":63,"score":64,"supported":13,"title":423,"abstract":424,"tags":425},[],[],[408,256],{"code":69,"score":20,"supported":13,"title":427,"abstract":428,"tags":429},[],[],[25],{"code":74,"score":20,"supported":13,"title":431,"abstract":432,"tags":433},[],[],[26],[435,436],"Diag-STFN 作物产量预测","CY-Bench 玉米 小麦","Diag-STFN作物产量预测-3324",{"doi":8,"openalex_id":8,"authors":439,"venue":8,"cited_by_count":90,"oa_url":8,"card":440,"direction":444,"ingested_from":97},[],{"tldr":441,"method":442,"finding":443,"direction":444,"opportunity":445},"提出诊断式时空多模态融合网络Diag-STFN，实现全球收获前玉米小麦产量预测。","基于CY-Bench基准，按数据特征诊断选择时间趋势与空间模块，覆盖38国玉米2","各前置期均取得最低NRMSE，诊断模块选择贡献最大，国家间差异大于模型间差异。","农业人工智能与决策模型","可探索自适应诊断机制迁移至其他作物，并针对国家间差异开展区域化建模与不确定性量化。","2026-09-24T00:04:02.684732Z",{"id":448,"title":449,"url":450,"summary":451,"summary_zh":8,"content":8,"source_name":452,"source_url":450,"published_at":453,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":454,"score_detail":455,"sources":458,"tags":460,"primary_topic":461,"secondary_topics":462,"classification":463,"search_phrases":485,"slug":488,"view_count":90,"doi":489,"paper":490,"created_at":510},1598,"Physiology-Informed Hyperspectral Retrieval of Leaf Vcmax across Wheat and Maize","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102541","Physiology-Informed Hyperspectral Retrieval of Leaf Vcmax across Wheat and Maize。Smart Agricultural Technology","Smart Agricultural Technology","2026-09-01T00:00:00Z",57,{"impact":251,"substance":456,"depth":113,"authority":251,"freshness":167,"relevant":20,"comment":457},15,"利用高光谱反演小麦玉米叶片Vcmax，方法新颖，对作物模型有参考价值，但影响范围有限。",[459],{"name":452,"url":450},[25,256,28],{"code":31,"slug":32,"name":33,"path":34,"parent_code":8},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":464},{"candidates":465,"agricultural_evidence":45,"reason":83},[466,471,477,481],{"code":63,"score":19,"supported":45,"title":467,"abstract":469,"tags":470},[468],"hyperspectral",[468],[28,256],{"code":43,"score":472,"supported":45,"title":473,"abstract":475,"tags":476},11,[474],"wheat",[474],[],{"code":51,"score":472,"supported":45,"title":478,"abstract":479,"tags":480},[137],[137],[],{"code":69,"score":20,"supported":13,"title":482,"abstract":483,"tags":484},[],[],[25],[486,487],"作物表型 智慧农业 遥感","作物表型 智慧农业","作物表型智慧农业遥感-1598","10.1016\u002Fj.atech.2026.102541",{"doi":489,"openalex_id":491,"authors":492,"venue":452,"cited_by_count":90,"oa_url":450,"card":8,"direction":8,"ingested_from":238},"W7207681448",[493,496,498,500,502,505,508],{"name":494,"orcid":495},"Jingcheng Zhang","https:\u002F\u002Forcid.org\u002F0000-0001-5167-4003",{"name":497,"orcid":8},"Shuai Yang",{"name":499,"orcid":8},"Ying Yuan",{"name":501,"orcid":8},"Qingyuan Zhang",{"name":503,"orcid":504},"Yuncai Hu","https:\u002F\u002Forcid.org\u002F0000-0002-4578-6217",{"name":506,"orcid":507},"Ittai Herrmann","https:\u002F\u002Forcid.org\u002F0000-0003-1136-1883",{"name":509,"orcid":8},"Kang Yu","2026-09-04T23:30:04.509903Z",{"id":512,"title":513,"url":514,"summary":515,"summary_zh":8,"content":8,"source_name":516,"source_url":8,"published_at":517,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":518,"score_detail":519,"sources":521,"tags":523,"primary_topic":525,"secondary_topics":526,"classification":527,"search_phrases":550,"slug":553,"view_count":161,"doi":8,"paper":554,"created_at":561},1371,"Diag-STFN：用于全球收获前作物产量预测的诊断时空多模态融合网络","https:\u002F\u002Flinkinghub.elsevier.com\u002Fretrieve\u002Fpii\u002FS1574954126002669","针对全球 38 国玉米和 29 国小麦在早、中、晚三个收获前时段的产量预测，提出 Diag-STFN 诊断时空多模态融合网络；根据数据集特征自动选择时空趋势耦合与空间模块激活；在 CY-Bench 基准下，玉米和小麦所有时段均取得最低池化 NRMSE，在 MAPE 和 KGE 上亦保持领先；消融研究表明诊断模块选择是性能提升的首要因素，融合策略是次要因素；方差分解显示国别间差异大于模型间差异。","Ecological Informatics · Elsevier · 2026-08-31","2026-08-30T16:00:00Z",75,{"impact":16,"substance":112,"depth":16,"authority":113,"freshness":44,"relevant":20,"comment":520},"全球尺度的作物产量预测研究，方法新颖且数据规模大，对农业信息化有参考价值。",[522],{"name":516,"url":514},[25,26,408,524,256],"深度学习",{"code":31,"slug":32,"name":33,"path":34,"parent_code":8},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":528},{"candidates":529,"agricultural_evidence":45,"reason":83},[530,534,538,542,546],{"code":43,"score":44,"supported":45,"title":531,"abstract":532,"tags":533},[],[48],[],{"code":51,"score":44,"supported":45,"title":535,"abstract":536,"tags":537},[],[54],[],{"code":74,"score":64,"supported":13,"title":539,"abstract":540,"tags":541},[],[],[26,524],{"code":63,"score":64,"supported":13,"title":543,"abstract":544,"tags":545},[],[],[408,256],{"code":69,"score":20,"supported":13,"title":547,"abstract":548,"tags":549},[],[],[25],[551,552],"农业人工智能 产量预测 智慧农业 深度学习","农业人工智能 产量预测","农业人工智能产量预测智慧农业深度学习-1371",{"doi":8,"openalex_id":8,"authors":555,"venue":8,"cited_by_count":90,"oa_url":8,"card":556,"direction":444,"ingested_from":97},[],{"tldr":557,"method":558,"finding":559,"direction":444,"opportunity":560},"提出Diag-STFN网络，用于全球收获前玉米和小麦产量预测，在CY-Bench基准上取得最优性能。","诊断时空多模态融合网络，自动选择时空趋势耦合与空间模块激活，基于CY-Bench","Diag-STFN在玉米和小麦所有时段均取得最低NRMSE，诊断模块选择是性能提升首要因素。","国别间差异大于模型间差异，可探索区域自适应或跨域迁移的产量预测模型，以提升全球适用性。","2026-09-02T00:05:07.231943Z"]