[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4325":3,"related-4325":100},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":69,"slug":72,"view_count":73,"doi":74,"paper":75,"created_at":99},4325,"Precision agriculture reveals crop-yield footprints associated with distance to natural-seminatural habitats","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104997","Context Modern agricultural expansion has simplified landscapes and reduced natural and semi-natural habitats (NSNH), potentially disrupting ecological processes supporting crop production. Many of these processes are distance-dependent, potentially leaving spatial footprints in crop yield that vary with landscape context. Yet, their influence on crop yields at sub-field scales remains poorly understood. Precision agriculture offers opportunities to address this gap. Objective To evaluate how sunflower distance-to-NSNH - yield relationships vary across landscape contexts within contrasting landscape settings using precision agriculture data. Methods High-resolution yield-monitor data (∼700,000 observations) from 54 yield maps (Pampas, Argentina) were combined with landscape metrics derived from land-cover products, and distance-yield relationships were analysed using mixed-effects models. These relationships were evaluated across gradients of NSNH cover (landscape context) and between zones representing contrasting landscape settings. Results and conclusions Distance-yield relationships were non-linear, varied with landscape context, and differed between landscape settings. In simplified landscapes, yields declined beyond a few hundred meters from NSNH, with steeper declines under higher NSNH cover. In the more complex landscape setting, where NSNH were more abundant and distances to habitat were shorter, yield responses were weak across the observed NSNH gradient. These patterns may reflect distance-mediated ecological processes associated with NSNH, although their observational nature precludes attribution to specific mechanisms. Expanding the dataset across broader landscape gradients would strengthen the mechanistic interpretation of these patterns. Significance Precision agriculture can help identify crop-yield footprints consistent with distance-mediated ecological processes at sub-field scales, improving understanding of landscape-crop interactions and supporting ecologically informed landscape management.","背景 现代农业扩张使景观趋于简化，并减少了自然与半自然生境（NSNH），可能破坏了支撑作物生产的生态过程。其中许多过程具有距离依赖性，可能在作物产量中留下随景观背景而变化的时空印记。然而，这些过程在田块尺度以下对作物产量的影响仍知之甚少。精准农业为解决这一空白提供了机遇。目的 利用精准农业数据，评估在不同景观情境下，向日葵距自然与半自然生境的距离—产量关系如何随景观背景而变化。方法 将来自54幅产量图的高分辨率产量监测数据（约70万条观测值，阿根廷潘帕斯地区）与基于土地覆盖产品衍生的景观指标相结合，并采用混合效应模型分析距离—产量关系。这些关系在自然与半自然生境覆盖度梯度（景观背景）以及代表不同景观情境的区域之间进行了评估。结果与结论 距离—产量关系呈非线性，随景观背景而变化，并在不同景观情境之间存在差异。在简化景观中，产量在距自然与半自然生境数百米之外下降，且在自然与半自然生境覆盖度较高时下降更陡。在更为复杂的景观情境中，自然与半自然生境更为丰富且距生境距离更短，产量响应在所观测的自然与半自然生境梯度上较弱。这些格局可能反映了与自然与半自然生境相关的距离介导生态过程，尽管其观测性质使其无法归因于具体机制。将数据集扩展至更广泛的景观梯度将增强对这些格局的机制性解释。意义 精准农业有助于识别与田块尺度以下距离介导生态过程相一致的作物产量印记，增进对景观—作物相互作用的理解，并支持基于生态学信息的景观管理。",null,"Agricultural Systems","2026-10-06T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,14,9,1,"基于70万条产量监测数据揭示田块尺度产量与自然栖息地距离的非线性关系，方法新颖、数据规模大，对生态化农田管理有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","精准农业","遥感","作物产量","农业生态",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"A4","soybean-oilseeds","大豆与油料","\u002Ftopic\u002Ffield-crops\u002Fsoybean-oilseeds","A",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,52,58,64],{"code":46,"score":17,"supported":47,"title":48,"abstract":50,"tags":51},"I1",true,[49],"precision agriculture",[28,49],[27,28],{"code":33,"score":53,"supported":47,"title":54,"abstract":55,"tags":57},3,[],[56],"向日葵",[],{"code":59,"score":60,"supported":14,"title":61,"abstract":62,"tags":63},"I3",2,[],[],[30,29],{"code":65,"score":22,"supported":14,"title":66,"abstract":67,"tags":68},"H6",[],[],[31],[70,71],"潘帕斯 向日葵 产量 自然栖息地","精准农业 产量监测 景观","潘帕斯向日葵产量自然栖息地-4325",0,"10.1016\u002Fj.agsy.2026.104997",{"doi":74,"openalex_id":76,"authors":77,"venue":10,"cited_by_count":73,"oa_url":6,"card":92,"direction":96,"ingested_from":98},"W7220681058",[78,81,84,87,89],{"name":79,"orcid":80},"Facundo José Oddi","https:\u002F\u002Forcid.org\u002F0000-0003-4478-978X",{"name":82,"orcid":83},"Matías G. Goldenberg","https:\u002F\u002Forcid.org\u002F0000-0002-9498-2951",{"name":85,"orcid":86},"Paula Zermoglio","https:\u002F\u002Forcid.org\u002F0000-0002-6056-5084",{"name":88,"orcid":9},"Tomás González",{"name":90,"orcid":91},"Lucas A. Garibaldi","https:\u002F\u002Forcid.org\u002F0000-0003-0725-4049",{"tldr":93,"method":94,"finding":95,"direction":96,"opportunity":97},"利用精准农业产量数据揭示向日葵产量随距自然半自然生境距离变化的非线性关系。","54幅产量图约70万条监测数据，结合土地覆盖景观指标与混合效应模型。","简化景观中产量随距生境距离增加而下降，复杂景观中响应微弱。","农业遥感与作物表型","可扩展至多作物多区域，结合机制模型量化生境距离对产量的因果贡献。","openalex","2026-10-07T23:30:03.865642Z",{"total":101,"page":22,"page_size":101,"items":102},6,[103,199,281,345,396,457],{"id":104,"title":105,"url":106,"summary":107,"summary_zh":108,"content":9,"source_name":109,"source_url":106,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":110,"score_detail":111,"sources":116,"tags":118,"primary_topic":122,"secondary_topics":123,"classification":130,"search_phrases":154,"slug":157,"view_count":22,"doi":158,"paper":159,"created_at":198},4445,"Soil intrinsic penetration (SIP) index: decoupling environmental noise from mechanical resistance to improve soybean yield prediction","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-75118-7","Soil compaction is a critical global agricultural concern, acting as a severe physical barrier that restricts root system expansion and reduces crop productivity. However, conventional Soil Penetration Resistance (PR) is a transient metric dictated by instantaneous hydraulic states rather than a stable structural property, leading to misleading interpretations in precision agriculture. This study aimed to develop and validate the Moisture-Normalized Soil Intrinsic Penetration (SIP) Index to isolate persistent anthropogenic structural degradation from environmental noise. Data were compiled from five field campaigns (2020–2025) conducted on a Typic Hapludox in Chapadão do Sul, Brazil. Three distinct sensing technologies: electronic (reference); hydraulic; and impact penetrometers, were evaluated across four depth intervals (0.0–0.4 m). The SIP Index was derived using a power-law normalization approach (SIP = PR x SW α x Clay β ), with empirical coefficients optimized via a Differential Evolution algorithm to maximize Spearman correlations with soybean yield. Results consistently identified the 0.10–0.20 m layer as the critical functional compaction barrier (traffic pan) across all sensing systems. While raw PR from continuous-insertion sensors (electronic and hydraulic) showed negligible or counter-intuitive yield correlations (ρ ≈ -0.01 to 0.08), the SIP Index drastically enhanced predictive capacity, reaching ρ = -0.39 for the electronic sensor, representing a substantial shift from the negligible associations observed with raw data, and ρ = -0.41 for the hydraulic system. Impact penetrometers exhibited higher inherent stability against moisture variations, rendering the SIP correction less significant for that device. Ultimately, the SIP framework effectively filters out pedogenic and hydraulic noise, providing a robust anthropogenic signature for delineating management zones and identifying true mechanical constraints to crop performance.","土壤压实是全球农业面临的严峻问题，作为一种严重的物理障碍，限制根系扩展并降低作物生产力。然而，传统的土壤穿透阻力（PR）是一种瞬时指标，受即时水分状态支配，而非稳定的结构属性，这导致在精准农业中产生误导性解读。本研究旨在开发并验证水分归一化土壤固有穿透（SIP）指数，以将持久性人为结构退化与环境噪声分离。数据来源于2020至2025年间在巴西沙帕当杜苏尔一处典型强淋溶老成土上开展的五次田间试验。评估了三种不同的传感技术：电子（参考）、液压和冲击式穿透仪，涵盖四个深度区间（0.0–0.4 m）。SIP指数采用幂律归一化方法（SIP = PR × SW^α × Clay^β）推导，经验系数通过差分进化算法优化，以最大化与大豆产量的Spearman相关性。结果一致表明，在所有传感系统中，0.10–0.20 m土层均为关键功能性压实障碍（机械压实层）。连续插入式传感器（电子和液压）的原始PR与产量相关性可忽略或呈反直觉关系（ρ ≈ -0.01至0.08），而SIP指数大幅提升了预测能力，电子传感器达到ρ = -0.39，相较于原始数据的可忽略关联实现了显著转变，液压系统达到ρ = -0.41。冲击式穿透仪对水分变化表现出更高的固有稳定性，因此SIP校正对该设备意义较小。最终，SIP框架有效滤除了成土和水分噪声，为划定管理分区和识别作物生长的真实机械限制提供了稳健的人为信号。","Scientific Reports",76,{"impact":112,"substance":18,"depth":19,"authority":113,"freshness":114,"relevant":22,"comment":115},15,13,8,"提出水分归一化土壤内在穿透指数，用三种传感技术跨五年田间数据验证，显著提升大豆产量预测能力，方法新颖且对精准农业管理分区有实用价值。",[117],{"name":109,"url":106},[27,28,119,120,121],"土壤传感","土壤压实","大豆产量",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[124],{"code":125,"slug":126,"name":127,"path":128,"parent_code":129},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":40,"locked":14,"version":41,"method":42,"evidence":131},{"candidates":132,"agricultural_evidence":47},[133,139,144,148],{"code":33,"score":20,"supported":47,"title":134,"abstract":136,"tags":138},[135],"soybean",[137,135],"大豆",[],{"code":125,"score":20,"supported":47,"title":140,"abstract":141,"tags":143},[126],[142,126],"土壤",[],{"code":46,"score":114,"supported":47,"title":145,"abstract":146,"tags":147},[],[28,49],[27,28],{"code":149,"score":53,"supported":47,"title":150,"abstract":151,"tags":153},"J3",[],[152],"全球农业",[],[155,156],"土壤穿透阻力 大豆产量","SIP 指数 土壤压实","土壤穿透阻力大豆产量-4445","10.1038\u002Fs41598-026-75118-7",{"doi":158,"openalex_id":160,"authors":161,"venue":109,"cited_by_count":73,"oa_url":190,"card":191,"direction":197,"ingested_from":98},"W7220671604",[162,165,167,170,173,176,179,182,184,187],{"name":163,"orcid":164},"Fábio Henrique Rojo Baio","https:\u002F\u002Forcid.org\u002F0000-0002-9522-0342",{"name":166,"orcid":9},"Job Teixeira de Oliveira",{"name":168,"orcid":169},"Cassiano Garcia Roque","https:\u002F\u002Forcid.org\u002F0000-0001-6872-0424",{"name":171,"orcid":172},"Ricardo Gava","https:\u002F\u002Forcid.org\u002F0000-0001-6268-5728",{"name":174,"orcid":175},"Larissa Pereira Ribeiro Teodoro","https:\u002F\u002Forcid.org\u002F0000-0002-8121-0119",{"name":177,"orcid":178},"Cid Naudi Silva Campos","https:\u002F\u002Forcid.org\u002F0000-0001-6810-885X",{"name":180,"orcid":181},"Rafael Felippe Ratke","https:\u002F\u002Forcid.org\u002F0000-0001-6930-3913",{"name":183,"orcid":9},"Octávio Babosa Plaster",{"name":185,"orcid":186},"Dthenifer Cordeiro Santana","https:\u002F\u002Forcid.org\u002F0000-0001-7611-6040",{"name":188,"orcid":189},"Paulo Eduardo Teodoro","https:\u002F\u002Forcid.org\u002F0000-0002-8236-542X","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-75118-7_reference.pdf",{"tldr":192,"method":193,"finding":194,"direction":195,"opportunity":196},"提出土壤固有穿透指数SIP，剔除水分等环境噪声，提升大豆产量预测精度。","基于2020-2025年巴西五季田间数据，用幂律归一化与差分进化算法优化系数。","0.10-0.20米为关键压实层，SIP使电子与液压传感器产量相关性提升至-0.39和-0.41。","智慧农业 \u002F 农业物联网","可探索SIP指数在不同土壤类型与作物上的普适性，并集成到实时传感与变量作业决策中。","数字乡村与农业信息化","2026-10-08T23:30:38.497161Z",{"id":200,"title":201,"url":202,"summary":203,"summary_zh":204,"content":9,"source_name":205,"source_url":202,"published_at":206,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":207,"score_detail":208,"sources":213,"tags":215,"primary_topic":219,"secondary_topics":220,"classification":227,"search_phrases":246,"slug":249,"view_count":60,"doi":250,"paper":251,"created_at":280},3986,"YOLOv8-MST: a lightweight and efficient real-time detection and counting deep learning algorithm for double-grain peanut seeding","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112481","YOLOv8-MST: a lightweight and efficient real-time detection and counting deep learning algorithm for double-grain peanut seeding。Computers and Electronics in Agriculture","YOLOv8-MST：一种用于双粒花生播种的轻量高效实时检测与计数深度学习算法。《计算机与电子农业》","Computers and Electronics in Agriculture","2026-10-01T00:00:00Z",72,{"impact":209,"substance":210,"depth":211,"authority":20,"freshness":21,"relevant":22,"comment":212},12,20,17,"核心期刊发表的轻量化实时检测计数算法，对花生精量播种智能化有实用价值，但属细分技术进展，影响面有限。",[214],{"name":205,"url":202},[27,216,217,28,218],"农业人工智能","目标检测","花生播种",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[221],{"code":222,"slug":223,"name":224,"path":225,"parent_code":226},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":40,"locked":14,"version":41,"method":42,"evidence":228},{"candidates":229,"agricultural_evidence":47},[230,236,242],{"code":222,"score":17,"supported":47,"title":231,"abstract":233,"tags":235},[232],"deep learning",[234,232],"深度学习",[216,217],{"code":33,"score":20,"supported":47,"title":237,"abstract":239,"tags":241},[238],"peanut",[240,238],"花生",[],{"code":46,"score":60,"supported":14,"title":243,"abstract":244,"tags":245},[],[],[27,28],[247,248],"YOLOv8-MST 花生播种","双粒花生 实时检测计数","YOLOv8-MST花生播种-3986","10.1016\u002Fj.compag.2026.112481",{"doi":250,"openalex_id":252,"authors":253,"venue":205,"cited_by_count":73,"oa_url":9,"card":274,"direction":278,"ingested_from":98},"W7215133023",[254,257,259,261,263,265,267,269,272],{"name":255,"orcid":256},"Baogang Li","https:\u002F\u002Forcid.org\u002F0000-0002-3430-7508",{"name":258,"orcid":9},"Enxi Liu",{"name":260,"orcid":9},"Yijia Chen",{"name":262,"orcid":9},"Zhipeng Feng",{"name":264,"orcid":9},"Yuhuan Li",{"name":266,"orcid":9},"Zunmin Liu",{"name":268,"orcid":9},"Jingchun Tang",{"name":270,"orcid":271},"Jiang Liu","https:\u002F\u002Forcid.org\u002F0000-0001-6746-9987",{"name":273,"orcid":9},"Fazhan Yang",{"tldr":275,"method":276,"finding":277,"direction":278,"opportunity":279},"提出YOLOv8-MST轻量算法，实现双粒花生播种实时检测与计数。","基于YOLOv8改进的轻量深度学习模型，用于花生播种图像检测计数。","YOLOv8-MST在保持高精度的同时实现轻量化实时检测与计数。","农业人工智能与决策模型","可探索轻量模型在多种作物播种质量实时监测中的泛化与边缘部署。","2026-10-02T23:30:03.835851Z",{"id":282,"title":283,"url":284,"summary":285,"summary_zh":286,"content":9,"source_name":205,"source_url":284,"published_at":206,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":207,"score_detail":287,"sources":289,"tags":291,"primary_topic":295,"secondary_topics":296,"classification":297,"search_phrases":314,"slug":317,"view_count":60,"doi":318,"paper":319,"created_at":344},3977,"Development and evaluation of a chain-groove lateral seedling feeding device based on modular stepping misalignment for multi-row transplanting of rapeseed bare-root seedlings","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112468","Development and evaluation of a chain-groove lateral seedling feeding device based on modular stepping misalignment for multi-row transplanting of rapeseed bare-root seedlings。Computers and Electronics in Agriculture","基于模块化步进错位的链槽式侧向投苗装置开发与评估：面向油菜裸根苗多行移栽。Computers and Electronics in Agriculture",{"impact":209,"substance":210,"depth":211,"authority":20,"freshness":21,"relevant":22,"comment":288},"核心期刊论文，提出链槽式模块化错位送苗装置，对多行油菜裸苗移栽机械化有实质方法创新，但属细分领域技术进展，公共影响有限。",[290],{"name":205,"url":284},[27,292,28,293,294],"农业机器人","油菜","移栽机械",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":298},{"candidates":299,"agricultural_evidence":47},[300,305,309],{"code":33,"score":112,"supported":47,"title":301,"abstract":303,"tags":304},[302],"rapeseed",[293,302],[293],{"code":46,"score":60,"supported":14,"title":306,"abstract":307,"tags":308},[],[],[27,28],{"code":310,"score":22,"supported":14,"title":311,"abstract":312,"tags":313},"F6",[],[],[292],[315,316],"油菜裸苗移栽 链槽式送苗装置","Computers and Electronics in Agriculture 移栽","油菜裸苗移栽链槽式送苗装置-3977","10.1016\u002Fj.compag.2026.112468",{"doi":318,"openalex_id":320,"authors":321,"venue":205,"cited_by_count":73,"oa_url":9,"card":339,"direction":195,"ingested_from":98},"W7215105622",[322,325,327,329,332,334,336],{"name":323,"orcid":324},"Hua Yuan","https:\u002F\u002Forcid.org\u002F0000-0001-7594-8718",{"name":326,"orcid":9},"Qingxi Liao",{"name":328,"orcid":9},"Zhengyu Liu",{"name":330,"orcid":331},"Zhe Liu","https:\u002F\u002Forcid.org\u002F0000-0003-2653-0408",{"name":333,"orcid":9},"Lin Li",{"name":335,"orcid":9},"Yitao Liao",{"name":337,"orcid":338},"Wenli Xiao","https:\u002F\u002Forcid.org\u002F0000-0002-8443-8987",{"tldr":340,"method":341,"finding":342,"direction":195,"opportunity":343},"研发并评估链槽式侧向供苗装置，实现油菜裸根苗多行移栽的模块化步进错位供苗。","设计链槽侧向供苗机构，采用模块化步进错位方案，并进行样机试验评估。","该装置能实现多行裸根苗有序错位供苗，提升移栽效率与供苗质量。","可结合视觉检测与伺服控制，研究供苗状态实时监测与自适应错位调节，提升多行移栽智能化水平。","2026-10-02T23:30:02.682513Z",{"id":346,"title":347,"url":348,"summary":349,"summary_zh":9,"content":9,"source_name":350,"source_url":9,"published_at":351,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":352,"sources":354,"tags":356,"primary_topic":359,"secondary_topics":360,"classification":361,"search_phrases":383,"slug":386,"view_count":60,"doi":9,"paper":387,"created_at":395},3600,"Development of an Adaptive Sprayer Control System for UAV-Based Spot Spraying in Soybean（基于植被覆盖率的自适应无人机大豆点喷控制系统研发）","https:\u002F\u002Fwww.ebiotrade.com\u002Fnewsf\u002F2026-9\u002F20260924002257098.htm","本研究开发了一套集成无人机的自适应喷雾控制系统，将冠层感知与基于阈值的点喷技术相连接。研究人员利用大豆单独覆盖度作为局部杂草斑块检测的基准基线，室内与田间估算结果的R²值分别为0.91和0.69。在播种后24天，采用25%的阈值可将潜在误喷激活率限制在4.8%。室内测试中，自动喷雾执行准确率达到97.3%。研究指出杂草可导致大豆超过30%的产量损失，全球年经济损失达330亿美元。无人机喷洒避免了与土壤的直接接触，减少了土壤压实和作物损伤的风险，提高了关键除草窗口期的操作灵活性。","Smart Agricultural Technology 7.1 2026-09-24","2026-09-24T00:00:00Z",{"impact":19,"substance":18,"depth":19,"authority":113,"freshness":114,"relevant":22,"comment":353},"该研究提出基于冠层覆盖度的无人机自适应点喷控制方法，数据详实、结论可靠，对精准植保技术研发具有参考价值，值得进入每日精选。",[355],{"name":350,"url":348},[27,28,137,357,358],"无人机植保","杂草管理",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":362},{"candidates":363,"agricultural_evidence":47},[364,368,375,379],{"code":33,"score":210,"supported":47,"title":365,"abstract":366,"tags":367},[137,135],[137],[137],{"code":369,"score":370,"supported":47,"title":371,"abstract":372,"tags":374},"F4",4,[],[373],"除草",[357],{"code":125,"score":53,"supported":47,"title":376,"abstract":377,"tags":378},[],[142],[],{"code":46,"score":60,"supported":14,"title":380,"abstract":381,"tags":382},[],[],[27,28],[384,385],"无人机 大豆 点喷","自适应喷雾 大豆 杂草","无人机大豆点喷-3600",{"doi":9,"openalex_id":9,"authors":388,"venue":9,"cited_by_count":73,"oa_url":9,"card":389,"direction":195,"ingested_from":394},[],{"tldr":390,"method":391,"finding":392,"direction":195,"opportunity":393},"研发基于冠层覆盖率的无人机自适应点喷系统，实现大豆田间精准除草。","用无人机冠层感知与阈值点喷控制，室内外估算覆盖度R²为0.91和0.69。","25%阈值下误喷激活率仅4.8%，室内自动喷雾执行准确率达97.3%。","可探索多作物、多生育期自适应阈值与杂草识别模型融合，提升田间鲁棒性。","agent","2026-09-27T00:05:18.158668Z",{"id":397,"title":398,"url":399,"summary":400,"summary_zh":401,"content":9,"source_name":402,"source_url":399,"published_at":351,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":403,"score_detail":404,"sources":406,"tags":408,"primary_topic":411,"secondary_topics":412,"classification":417,"search_phrases":433,"slug":436,"view_count":53,"doi":437,"paper":438,"created_at":456},3501,"A Dual-Phenological-Characteristic Weighting Method to Reconcile Time Discrepancies in Soybean Phenology Estimation from MODIS NDVI Time Series","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193300","Accurate large-scale monitoring of crop phenology is essential for optimizing agricultural management. Remote sensing has been widely used for estimating crop phenological stages, yet time discrepancies often exist between remotely sensed phenological metrics and ground-observed growth stages. Moreover, phenological parameters derived from different characterization models exhibit varying degrees of deviation from field observations. The primary goal of this study was to develop a novel method that fully exploits the deviation patterns of diverse phenological parameters to enhance the accuracy of soybean phenology retrieval. To this end, we extracted 11 phenological parameters for six key growth stages—emerged, blooming, pod-setting, turning yellow, dropping leaf, and harvest—of soybean across 16 U.S. states using MODIS NDVI (normalized difference vegetation index) time-series data from 2000 to 2020, employing GU-, curvature-, and derivative-based phenological modeling methods. The study design centered on proposing a dual-phenological-characteristic weighting (DPCW) method that leverages the deviation features of different phenological parameters relative to ground-observed growth stages, generating composite phenological characteristics by pairing two distinct parameters. The key innovation of this paper is the use of dual-feature weighting to improve the correspondence between satellite-derived phenometrics and field observations, offering an alternative to conventional phenological estimation. The results demonstrated that the optimal DPCW-based combinations for the six growth stages were SOS (start of season) and GREEN, SOS and POS (peak of season), MATURITY and POS, EOS (end of season) and SENES (senescence), RD (recession date) and DD (downturn date), and EOS and DORM (dormancy), respectively. The coefficient of determination (R2) between the retrieved transition dates and ground observations exceeded 0.65 for most stages, with the emerged stage improving to 0.47 from 0.052 and 0.357 of the unadjusted and offset-adjusted benchmarks. The average root mean square error (RMSE) was less than 5 days in most cases, representing a reduction of over 40%, with the most substantial improvement at the turning yellow stage, where RMSE dropped from 12.8 days to 2.8 days. A strength of this study lies in its multi-state, multi-decade validation, demonstrating the robustness and temporal consistency of the DPCW method within the major U.S. soybean-growing region. However, a limitation is that the method’s performance may vary with different satellite sensors or crop types, warranting further investigation. The proposed approach is expected to enhance the accuracy of remote sensing-based crop phenology monitoring and offers an effective alternative for calibrating remotely sensed phenological parameters.","准确的大尺度作物物候监测对于优化农业管理至关重要。遥感已被广泛用于估算作物物候阶段，但遥感物候指标与地面观测生育阶段之间常存在时间差异。此外，不同特征化模型衍生的物候参数与田间观测之间存在不同程度的偏差。本研究的主要目标是开发一种新方法，充分利用多种物候参数的偏差模式，以提高大豆物候反演精度。为此，我们利用2000—2020年MODIS NDVI（归一化差异植被指数）时间序列数据，采用基于GU、曲率和导数的方法提取了美国16个州大豆六个关键生育阶段——出苗、开花、结荚、黄化、落叶和收获——的11个物候参数。研究设计的核心是提出一种双物候特征加权（dual-phenological-characteristic weighting，DPCW）方法，该方法利用不同物候参数相对于地面观测生育阶段的偏差特征，通过配对两个不同参数生成复合物候特征。本文的关键创新在于利用双特征加权提高卫星衍生物候指标与田间观测之间的对应关系，为传统物候估算提供了一种替代方案。结果表明，六个生育阶段基于DPCW的最优组合分别为SOS（生长季开始）与GREEN、SOS与POS（生长季峰值）、MATURITY与POS、EOS（生长季结束）与SENES（衰老）、RD（衰退日期）与DD（下降日期）以及EOS与DORM（休眠）。反演得到的转换日期与地面观测之间的决定系数（R²）在大多数阶段超过0.65，其中出苗阶段从基准的0.052和偏移调整后的0.357提高至0.47。大多数情况下平均均方根误差（RMSE）小于5天，降幅超过40%，其中黄化阶段改善最为显著，RMSE从12.8天降至2.8天。本研究的一个优势在于其多州、多年代际验证，证明了DPCW方法在美国主要大豆种植区内的稳健性和时间一致性。","Remote Sensing",81,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":405},"提出双物候特征加权方法，用MODIS NDVI长时序数据校正大豆物候遥感估算偏差，方法新颖、验证扎实，对农情遥感监测有参考价值。",[407],{"name":402,"url":399},[27,137,409,29,410],"农情监测","作物表型",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[413],{"code":59,"slug":414,"name":415,"path":416,"parent_code":226},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":418},{"candidates":419,"agricultural_evidence":47},[420,424,429],{"code":33,"score":112,"supported":47,"title":421,"abstract":422,"tags":423},[135],[137,135],[137],{"code":59,"score":21,"supported":47,"title":425,"abstract":426,"tags":428},[],[29,427],"remote sensing",[410,409,29],{"code":46,"score":22,"supported":14,"title":430,"abstract":431,"tags":432},[],[],[27],[434,435],"MODIS NDVI 大豆 物候","美国大豆 遥感 物候监测","MODISNDVI大豆物候-3501","10.3390\u002Frs18193300",{"doi":437,"openalex_id":439,"authors":440,"venue":402,"cited_by_count":73,"oa_url":399,"card":451,"direction":96,"ingested_from":98},"W7214203102",[441,443,446,449],{"name":442,"orcid":9},"Qiuxiang Yi",{"name":444,"orcid":445},"Siting Chen","https:\u002F\u002Forcid.org\u002F0000-0003-3468-9320",{"name":447,"orcid":448},"Fumin Wang","https:\u002F\u002Forcid.org\u002F0000-0002-5078-358X",{"name":450,"orcid":9},"Qinyan Zhu",{"tldr":452,"method":453,"finding":454,"direction":96,"opportunity":455},"提出双物候特征加权法，校正MODIS NDVI大豆物候估计与地面观测的时间偏差。","用MODIS NDVI 2000-2020数据，结合GU、曲率、导数三类物候模型","多数生育期R²超0.65，RMSE多小于5天，降幅超40%，转黄期RMSE从12.8天降至2.8天。","可将该加权校正思路迁移到其他作物与多源遥感数据，并探索自适应权重与深度学习融合的物候反演。","2026-09-25T23:30:31.075499Z",{"id":458,"title":459,"url":460,"summary":461,"summary_zh":462,"content":9,"source_name":402,"source_url":460,"published_at":463,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":464,"score_detail":465,"sources":467,"tags":469,"primary_topic":472,"secondary_topics":473,"classification":476,"search_phrases":498,"slug":501,"view_count":370,"doi":502,"paper":503,"created_at":535},2320,"Genotype-Aware Prediction of Soybean Seed Composition from Multimodal UAV Imagery of the Standing Crop","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183121","Geospatial artificial intelligence (GeoAI) integrates multimodal remote sensing with deep learning to model complex agricultural systems at scale. Within this framework, accurate and non-destructive prediction of seed composition from in-season standing crops is essential for breeding and precision agriculture. This study developed an end-to-end convolutional neural network (CNN) framework to estimate eight seed traits (protein, oil, sucrose, fiber, starch, ash, complex and simple carbohydrates) from UAV-based multisensor imagery and associated genotype and phenological metadata. A total of 372 soybean samples were collected over two growing seasons (2020–2021) from two fields in Missouri, with UAV flights capturing multispectral (MSI), thermal (THR), and LiDAR (LDR) data at four time points spanning vegetative to reproductive growth stages. CNN models were trained in single- and multi-date configurations, incorporating genotype (GEN) and days after sowing (DAS) as additional features. The highest accuracy was achieved for sucrose (R2 = 0.80), followed by simple carbohydrate (R2 = 0.70) and starch (R2 = 0.55), with notable gains from GEN and DAS. Multi-date models incorporating earlier acquisitions often matched or outperformed later or all-date combinations. Among modalities, MSI provided the most robust estimates, with limited added value from LDR or THR. Unlike feature-based pipelines prone to multicollinearity, this image-to-trait approach enables automated, scalable prediction of soybean seed composition for in-season, field-level assessment.","地理空间人工智能（GeoAI）将多模态遥感与深度学习相结合，以在大尺度上对复杂农业系统进行建模。在该框架下，对当季未收获作物进行准确且无损的种子成分预测，对于育种和精准农业至关重要。本研究开发了一种端到端的卷积神经网络（CNN）框架，利用基于无人机（UAV）的多传感器影像以及相关的基因型和物候元数据，估算八种种子性状（蛋白质、油分、蔗糖、纤维、淀粉、灰分、复杂碳水化合物和简单碳水化合物）。研究在2020—2021两个生长季内，从密苏里州两块田地共采集372份大豆样本，无人机飞行在从营养生长期到生殖生长期的四个时间点获取了多光谱（MSI）、热红外（THR）和激光雷达（LDR）数据。CNN模型以单日期和多日期配置进行训练，并将基因型（GEN）和播种后天数（DAS）作为附加特征纳入。蔗糖的估算精度最高（R² = 0.80），其次为简单碳水化合物（R² = 0.70）和淀粉（R² = 0.55），且GEN和DAS的加入带来了显著提升。纳入早期采集数据的多日期模型往往与后期或全日期组合的表现相当，甚至更优。在各模态中，MSI提供了最稳健的估算结果，而LDR或THR的附加价值有限。与易受多重共线性影响的特征工程流程不同，这种从图像到性状的方法能够实现大豆种子成分的自动化、可扩展预测，用于当季田块尺度的评估。","2026-09-11T00:00:00Z",80,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":114,"relevant":22,"comment":466},"基于多模态无人机影像与基因型信息的大豆籽粒成分无损预测研究，方法新颖、数据扎实，对智慧育种与精准农业有参考价值。",[468],{"name":402,"url":460},[27,470,216,29,471],"无人机","大豆育种",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[474,475],{"code":222,"slug":223,"name":224,"path":225,"parent_code":226},{"code":59,"slug":414,"name":415,"path":416,"parent_code":226},{"status":40,"locked":14,"version":41,"method":42,"evidence":477},{"candidates":478,"agricultural_evidence":47},[479,483,488,493],{"code":33,"score":112,"supported":47,"title":480,"abstract":481,"tags":482},[135],[137,135],[471],{"code":222,"score":13,"supported":47,"title":484,"abstract":485,"tags":487},[],[234,232,486],"artificial intelligence",[216],{"code":59,"score":13,"supported":47,"title":489,"abstract":490,"tags":492},[],[29,427,491],"multispectral",[29],{"code":46,"score":494,"supported":47,"title":495,"abstract":496,"tags":497},7,[],[28,49],[27],[499,500],"农业人工智能 大豆育种 智慧农业 无人机","农业人工智能 大豆育种","农业人工智能大豆育种智慧农业无人机-2320","10.3390\u002Frs18183121",{"doi":502,"openalex_id":504,"authors":505,"venue":402,"cited_by_count":73,"oa_url":460,"card":530,"direction":96,"ingested_from":98},"W7212223520",[506,509,512,515,518,520,522,525,528],{"name":507,"orcid":508},"Vasit Sagan","https:\u002F\u002Forcid.org\u002F0000-0003-4375-2096",{"name":510,"orcid":511},"Kristen Rhodes","https:\u002F\u002Forcid.org\u002F0000-0002-8469-5043",{"name":513,"orcid":514},"Sourav Bhadra","https:\u002F\u002Forcid.org\u002F0000-0002-5832-4695",{"name":516,"orcid":517},"Haireti Alifu","https:\u002F\u002Forcid.org\u002F0000-0002-7369-6657",{"name":519,"orcid":9},"Aviskar Giri",{"name":521,"orcid":9},"Ashutosh Pawar",{"name":523,"orcid":524},"Bishal Roy","https:\u002F\u002Forcid.org\u002F0000-0001-9912-5505",{"name":526,"orcid":527},"Supria Sarkar","https:\u002F\u002Forcid.org\u002F0000-0001-9467-5786",{"name":529,"orcid":9},"Felix Fritschi",{"tldr":531,"method":532,"finding":533,"direction":96,"opportunity":534},"用无人机多模态影像与基因型数据训练CNN，预测大豆八种种子成分。","372份大豆样本，多光谱\u002F热红外\u002FLiDAR影像加基因型与播后天数，端到端CNN","蔗糖预测最优(R²=0.80)，基因型与播期提升精度，多光谱最稳健。","可探索基因型-表型-环境交互建模，并迁移至其他作物与多时相早期预测。","2026-09-13T23:30:22.776177Z"]