[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2841":3,"related-2841":81},{"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":21,"tags":23,"primary_topic":29,"secondary_topics":34,"classification":35,"search_phrases":76,"slug":79,"view_count":61,"doi":8,"paper":8,"created_at":80},2841,"中国农科院资划所多因子监测实现小麦晚霜冻害大范围动态预警登European Journal of Agronomy","https:\u002F\u002Fwww.caas.cn\u002Fxwzx\u002Fmtxw\u002Fbe939456a5354c4da317420bf21577db.htm","近日,中国农业科学院农业资源与农业区划研究所农业遥感团队提出了多因子综合霜冻监测指数,提升小麦晚霜冻害监测精度。黄淮海平原是我国冬小麦核心产区,每年3至4月小麦拔节至抽穗期间频发的晚霜冻害严重威胁粮食安全。该指数综合高精度气象预报和冬小麦生长进程信息,兼顾低温强度、持续时间及不同生育期敏感性,并利用遥感土壤水分数据构建非线性调节系数,精准刻画湿润土壤对低温的缓冲效应,突破了气象站点的空间局限。",null,"中国农业科学院 \u002F 中国科学报","2026-09-17T00:00:00Z","报道",10,true,87,{"impact":16,"substance":16,"depth":17,"authority":18,"freshness":12,"relevant":19,"comment":20},22,18,15,1,"国家级科研团队在核心期刊提出多因子霜冻监测指数，方法新颖、结论可靠，对黄淮海冬小麦防灾减灾有实质价值，值得进入每日精选。",[22],{"name":9,"url":6},[24,25,26,27,28],"智慧农业","农业遥感","粮食安全","小麦","农业气象",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},"A2","wheat","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[],{"status":36,"locked":37,"version":38,"method":39,"evidence":40},"classified",false,"2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":13},[42,47,53,59,66,71],{"code":30,"score":43,"supported":13,"title":44,"abstract":45,"tags":46},12,[27],[27],[27],{"code":48,"score":49,"supported":13,"title":50,"abstract":51,"tags":52},"A8",4,[],[26],[26],{"code":54,"score":49,"supported":13,"title":55,"abstract":56,"tags":58},"I3",[],[57],"遥感",[25],{"code":60,"score":61,"supported":13,"title":62,"abstract":63,"tags":65},"H2",3,[],[64],"土壤",[],{"code":67,"score":19,"supported":37,"title":68,"abstract":69,"tags":70},"H7",[],[],[28],{"code":72,"score":19,"supported":37,"title":73,"abstract":74,"tags":75},"I1",[],[],[24],[77,78],"农业气象 农业遥感 智慧农业 粮食安全","农业气象 农业遥感","农业气象农业遥感智慧农业粮食安全-2841","2026-09-18T00:03:28.607700Z",{"total":82,"page":19,"page_size":82,"items":83},6,[84,149,231,293,342,417],{"id":85,"title":86,"url":87,"summary":88,"summary_zh":89,"content":8,"source_name":90,"source_url":87,"published_at":91,"category":92,"cover_url":8,"hotness":12,"is_selected":37,"score":93,"score_detail":94,"sources":100,"tags":102,"primary_topic":105,"secondary_topics":106,"classification":107,"search_phrases":124,"slug":127,"view_count":61,"doi":128,"paper":129,"created_at":148},4020,"Robust QR Code Detection in Oblique Aerial Images for Agricultural Field Experiments","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193361","Field experiments in precision agriculture require reliable linkage of plant variants to experimental plots, which is difficult in oblique aerial imagery because the drone position does not identify the imaged ground location. We present and evaluate a reproducible workflow for detecting QR reference markers in high-resolution UAV images acquired over a wheat field before crop growth at a 45° viewing angle. The workflow combines manually defined regions of interest, documented preprocessing, a rotation sweep, and independent evaluation of OpenCV and pyzbar decoding backends. QR codes were selected for practical field deployment because their payload can directly encode a plot identifier and can be checked with an ordinary smartphone; the study does not benchmark QR codes against other fiducial-marker families. In 500 field-collected QR-code crops from 20 images, 491 codes (98.2%) were decoded; all nine failures had incomplete code visibility. The observed result is therefore a system-level outcome of both image acquisition and decoding under the tested configuration, rather than a growing-season operational accuracy. The mean processing time was approximately 0.41 s per region of interest on a standard PC. The work demonstrates QR-marker detection under the stated pre-growth conditions and provides a basis for future plot-label reference, calibration, and downstream Fusarium Head Blight phenotyping.","精准农业中的田间试验需要将植物变异可靠地关联到试验小区，而这在倾斜航空影像中较为困难，因为无人机位置并不能标识所成像的地面位置。我们提出并评估了一套可重复的工作流程，用于在作物生长前以45°视角获取的小麦田高分辨率无人机影像中检测QR参考标记。该工作流程结合了人工定义的感兴趣区域、有记录的前处理步骤、旋转扫描，以及对OpenCV和pyzbar解码后端的独立评估。选择QR码用于实际田间部署，是因为其有效载荷可直接编码小区标识符，并可用普通智能手机进行核验；本研究并未将QR码与其他基准标记类型进行基准比较。在来自20幅影像的500个田间采集QR码裁剪区域中，491个码（98.2%）被成功解码；全部9个失败案例均存在码可见性不完整的问题。因此，所观察到的结果是测试配置下图像采集与解码共同作用的系统级结果，而非整个生长季的运行精度。在标准PC上，每个感兴趣区域的平均处理时间约为0.41 s。该工作证明了在上述生长前条件下QR标记检测的可行性，并为未来的小区标签参考、校准以及下游赤霉病（Fusarium Head Blight）表型分析提供了基础。","Remote Sensing","2026-10-01T00:00:00Z","论文",65,{"impact":95,"substance":17,"depth":96,"authority":97,"freshness":98,"relevant":19,"comment":99},8,16,14,9,"该论文提出斜视无人机影像中QR码检测的可复现流程，在500个样本中解码成功率达98.2%，为精准农业田间试验的地块标识提供了实用方案，方法新颖且数据可靠，但属细分技术进展，影响范围有限。",[101],{"name":90,"url":87},[24,103,25,27,104],"无人机","精准农业",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[],{"status":36,"locked":37,"version":38,"method":39,"evidence":108},{"candidates":109,"agricultural_evidence":13},[110,115,120],{"code":72,"score":95,"supported":13,"title":111,"abstract":112,"tags":114},[],[104,113],"precision agriculture",[24,104],{"code":30,"score":116,"supported":13,"title":117,"abstract":118,"tags":119},7,[],[27,31],[27],{"code":54,"score":19,"supported":37,"title":121,"abstract":122,"tags":123},[],[],[25],[125,126],"无人机 斜视影像 QR码 检测","小麦 田间试验 地块标识","无人机斜视影像QR码检测-4020","10.3390\u002Frs18193361",{"doi":128,"openalex_id":130,"authors":131,"venue":90,"cited_by_count":140,"oa_url":87,"card":141,"direction":145,"ingested_from":147},"W7215065180",[132,134,137],{"name":133,"orcid":8},"Gudrun Kinz",{"name":135,"orcid":136},"Hermann Buerstmayr","https:\u002F\u002Forcid.org\u002F0000-0002-0748-2351",{"name":138,"orcid":139},"Peter M. Roth","https:\u002F\u002Forcid.org\u002F0000-0001-9566-1298",0,{"tldr":142,"method":143,"finding":144,"direction":145,"opportunity":146},"提出并评估了在45°斜视无人机图像中检测田间二维码标记的可复现流程，解码成功率达98.2%。","结合手动ROI、预处理、旋转扫描及OpenCV与pyzbar双后端解码，使用50","491\u002F500个二维码成功解码，9个失败均因码可见性不完整，平均处理时间约0.41秒\u002FROI。","农业遥感与作物表型","可探索斜视图像下多类基准标记的鲁棒检测与自动ROI定位，并接入生长季表型分析流程。","openalex","2026-10-02T23:30:19.815764Z",{"id":150,"title":151,"url":152,"summary":153,"summary_zh":154,"content":8,"source_name":155,"source_url":152,"published_at":156,"category":92,"cover_url":8,"hotness":12,"is_selected":37,"score":157,"score_detail":158,"sources":162,"tags":164,"primary_topic":167,"secondary_topics":168,"classification":169,"search_phrases":189,"slug":192,"view_count":193,"doi":194,"paper":195,"created_at":230},2615,"A low-cost RGB image and point cloud integrated scanning system for wheat phenotyping","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112441","A low-cost RGB image and point cloud integrated scanning system for wheat phenotyping。Computers and Electronics in Agriculture","一种用于小麦表型分析的低成本RGB图像与点云集成扫描系统。","Computers and Electronics in Agriculture","2026-09-16T00:00:00Z",79,{"impact":17,"substance":159,"depth":160,"authority":97,"freshness":12,"relevant":19,"comment":161},20,17,"低成本RGB与点云融合的小麦表型扫描系统，方法新颖且面向育种实践，具备细分领域参考价值。",[163],{"name":155,"url":152},[24,25,27,165,166],"表型组学","三维点云",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[],{"status":36,"locked":37,"version":38,"method":39,"evidence":170},{"candidates":171,"agricultural_evidence":13},[172,176,180,185],{"code":30,"score":18,"supported":13,"title":173,"abstract":174,"tags":175},[31],[27,31],[27],{"code":72,"score":19,"supported":37,"title":177,"abstract":178,"tags":179},[],[],[24],{"code":181,"score":19,"supported":37,"title":182,"abstract":183,"tags":184},"I2",[],[],[166],{"code":54,"score":19,"supported":37,"title":186,"abstract":187,"tags":188},[],[],[25],[190,191],"三维点云 农业遥感 智慧农业 表型组学","三维点云 农业遥感","三维点云农业遥感智慧农业表型组学-2615",5,"10.1016\u002Fj.compag.2026.112441",{"doi":194,"openalex_id":196,"authors":197,"venue":155,"cited_by_count":140,"oa_url":8,"card":225,"direction":145,"ingested_from":147},"W7213304555",[198,200,202,204,206,208,210,212,214,216,218,220,222],{"name":199,"orcid":8},"Yan Li",{"name":201,"orcid":8},"Suyi Liu",{"name":203,"orcid":8},"Xuerui Qi",{"name":205,"orcid":8},"Chuanjing Jin",{"name":207,"orcid":8},"Xiangxin Zhuang",{"name":209,"orcid":8},"Zetao Wang",{"name":211,"orcid":8},"Jinyong Li",{"name":213,"orcid":8},"Chengming Zhao",{"name":215,"orcid":8},"Xia Yao",{"name":217,"orcid":8},"Yongchao Tian",{"name":219,"orcid":8},"Yan Zhu",{"name":221,"orcid":8},"Weixing Cao",{"name":223,"orcid":224},"Xiaohu Zhang","https:\u002F\u002Forcid.org\u002F0000-0001-5654-1445",{"tldr":226,"method":227,"finding":228,"direction":145,"opportunity":229},"开发低成本RGB与点云融合扫描系统，用于小麦表型测量。","低成本RGB相机与点云融合扫描系统，采集小麦三维表型数据。","该系统能低成本获取小麦RGB与点云数据，实现表型分析。","可探索低成本多模态表型系统在田间高通量育种和抗逆监测中的应用。","2026-09-16T23:30:01.907231Z",{"id":232,"title":233,"url":234,"summary":235,"summary_zh":8,"content":8,"source_name":236,"source_url":8,"published_at":237,"category":92,"cover_url":8,"hotness":12,"is_selected":37,"score":238,"score_detail":239,"sources":241,"tags":243,"primary_topic":247,"secondary_topics":248,"classification":259,"search_phrases":280,"slug":283,"view_count":19,"doi":8,"paper":284,"created_at":292},5535,"基于无人机多光谱图像与VGG21模型的小麦渍害调控效果识别","https:\u002F\u002Ffinance.sina.cn\u002F2026-10-16\u002Fdetail-inivmprm8363597.d.html","江苏省农科院农业信息研究所联合中国农科院环发所与湖北省农科院粮作所，在小麦拔节至抽穗、抽穗至灌浆两个阶段设置对照、渍水胁迫、硅肥与氨基酸调控试验，用大疆精灵4采集冠层多光谱影像。VGG21模型对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","智慧农业（中英文）2026-10-21","2026-10-21T00:00:00Z",82,{"impact":17,"substance":16,"depth":17,"authority":97,"freshness":12,"relevant":19,"comment":240},"省级科研机构联合攻关，方法新颖、数据扎实，对渍害遥感识别与调控评估有实质参考价值，值得入选。",[242],{"name":236,"url":234},[24,25,244,245,246],"作物表型","无人机多光谱","小麦渍害",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[249,254],{"code":54,"slug":250,"name":251,"path":252,"parent_code":253},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"code":67,"slug":255,"name":256,"path":257,"parent_code":258},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":36,"locked":37,"version":38,"method":39,"evidence":260},{"candidates":261,"agricultural_evidence":13},[262,267,271,276],{"code":30,"score":263,"supported":13,"title":264,"abstract":265,"tags":266},11,[27],[27],[],{"code":54,"score":263,"supported":13,"title":268,"abstract":269,"tags":270},[245],[],[244,25,245],{"code":67,"score":95,"supported":13,"title":272,"abstract":274,"tags":275},[273],"渍害",[],[],{"code":72,"score":19,"supported":37,"title":277,"abstract":278,"tags":279},[],[],[24],[281,282],"江苏省农科院 小麦渍害 多光谱","VGG21 小麦 硅肥调控","江苏省农科院小麦渍害多光谱-5535",{"doi":8,"openalex_id":8,"authors":285,"venue":8,"cited_by_count":140,"oa_url":8,"card":286,"direction":145,"ingested_from":291},[],{"tldr":287,"method":288,"finding":289,"direction":145,"opportunity":290},"用无人机多光谱图像和VGG21模型识别小麦渍害后硅肥与氨基酸调控效果。","大疆精灵4采集冠层多光谱影像，构建VGG21深度学习分类模型。","VGG21对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","可扩展多生育期、多调控组合与轻量化模型，探索渍害胁迫等级与调控效果的同步识别。","agent","2026-10-22T00:07:10.070916Z",{"id":294,"title":295,"url":296,"summary":297,"summary_zh":8,"content":8,"source_name":298,"source_url":8,"published_at":299,"category":92,"cover_url":8,"hotness":12,"is_selected":37,"score":300,"score_detail":301,"sources":304,"tags":306,"primary_topic":307,"secondary_topics":308,"classification":311,"search_phrases":330,"slug":333,"view_count":140,"doi":8,"paper":334,"created_at":341},5296,"雷添杰研究员团队《基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别》","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-10-16\u002Fdoc-inivmprm8363597.shtml","《智慧农业(中英文)》2026年第8卷第4期刊载梁万杰、刘晓君、雷添杰等论文,在小麦拔节—抽穗和抽穗—灌浆两个生长阶段进行对照、渍水胁迫、硅肥调控、氨基酸调控控制试验;利用大疆精灵4多光谱无人机采集小麦冠层多光谱图像建立数据集,基于VGG21模型构建识别模型,发现硅肥调控样本识别性能最好,识别精度最高,具良好鲁棒性和可扩展性,可为小麦渍害综合防控提供理论与技术支持。","智慧农业(中英文)(2026,8(4))","2026-10-16T00:00:00Z",76,{"impact":96,"substance":302,"depth":160,"authority":97,"freshness":95,"relevant":19,"comment":303},21,"核心期刊论文，方法新颖、结论可靠，对小麦渍害防控有实用价值，值得进入每日精选。",[305],{"name":298,"url":296},[24,25,244,245,246],{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[309,310],{"code":67,"slug":255,"name":256,"path":257,"parent_code":258},{"code":54,"slug":250,"name":251,"path":252,"parent_code":253},{"status":36,"locked":37,"version":38,"method":39,"evidence":312},{"candidates":313,"agricultural_evidence":13},[314,318,322,326],{"code":30,"score":263,"supported":13,"title":315,"abstract":316,"tags":317},[27],[27],[],{"code":67,"score":263,"supported":13,"title":319,"abstract":320,"tags":321},[273],[273],[],{"code":54,"score":263,"supported":13,"title":323,"abstract":324,"tags":325},[245],[],[244,25,245],{"code":72,"score":49,"supported":13,"title":327,"abstract":328,"tags":329},[],[24],[24],[331,332],"雷添杰 小麦渍害 无人机多光谱","VGG21 小麦渍害 识别模型","雷添杰小麦渍害无人机多光谱-5296",{"doi":8,"openalex_id":8,"authors":335,"venue":8,"cited_by_count":140,"oa_url":8,"card":336,"direction":145,"ingested_from":291},[],{"tldr":337,"method":338,"finding":339,"direction":145,"opportunity":340},"用无人机多光谱图像和VGG21模型识别小麦渍害调控效果。","大疆精灵4采集冠层多光谱图像，构建VGG21识别模型。","硅肥调控样本识别性能最好、精度最高，模型鲁棒可扩展。","可探索多生育期多光谱特征与不同调控措施的耦合机制，并扩展到其他作物渍害监测。","2026-10-19T00:07:48.071055Z",{"id":343,"title":344,"url":345,"summary":346,"summary_zh":347,"content":8,"source_name":348,"source_url":345,"published_at":349,"category":92,"cover_url":8,"hotness":12,"is_selected":37,"score":350,"score_detail":351,"sources":353,"tags":355,"primary_topic":359,"secondary_topics":360,"classification":361,"search_phrases":390,"slug":393,"view_count":140,"doi":394,"paper":395,"created_at":416},4820,"Integrated strategies for improving lodging resistance in wheat: physiological mechanisms, plant growth regulators and agronomic management","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1925460","Wheat lodging remains a major constraint to sustainable wheat production because it reduces grain yield and quality, increases harvesting losses and lowers production efficiency. The widespread cultivation of high-yielding cultivars, intensive nitrogen fertilization, higher planting densities, expansion of irrigated agriculture, and increasingly frequent extreme weather events have collectively increased lodging susceptibility, making effective management an important priority. Lodging is a complex phenomenon governed by interactions among plant architecture, stem mechanical properties, root anchorage, crop management practices and environmental conditions. Consequently, improving lodging resistance requires an integrated approach that combines physiological understanding with practical agronomic interventions. This review synthesizes recent advances in the structural, physiological, biochemical and agronomic mechanisms underlying lodging resistance in wheat. Particular emphasis is placed on stem biomechanics, basal internode characteristics, cell wall composition, lignin and cellulose deposition, root system architecture, and genetic factors that collectively determine plant stability. The review further examines the influence of major agronomic practices, including nitrogen management, plant population, sowing time, irrigation scheduling and cultivar selection, on lodging risk under diverse production environments. In addition, the physiological responses, field performance, practical applications and limitations of commonly used plant growth regulators, including chlormequat chloride, trinexapac-ethyl, paclobutrazol, uniconazole and ethephon, are critically evaluated in relation to their roles in improving stem strength and reducing lodging. The available evidence indicates that no single strategy provides consistent lodging control across all production systems. Instead, durable improvement in lodging resistance depends on integrating genetic improvement, balanced crop nutrition, optimized agronomic management, and judicious use of plant growth regulators according to local environmental conditions. The review also highlights emerging opportunities offered by precision agriculture, high-throughput phenotyping, advanced spray technologies, and improved understanding of stem biomechanics and root anchorage. Together, these advances provide a framework for developing sustainable, climate-resilient lodging management strategies that enhance wheat productivity, crop stability and resource-use efficiency, while also highlighting key research priorities for future investigation.","小麦倒伏仍是可持续小麦生产的主要制约因素，因为它降低籽粒产量和品质，增加收获损失并降低生产效率。高产栽培品种的广泛种植、集约化氮肥施用、更高的种植密度、灌溉农业的扩张以及日益频繁的极端天气事件，共同增加了倒伏易感性，使有效管理成为重要优先事项。倒伏是一种复杂现象，受植株结构、茎秆力学特性、根系锚定、作物管理措施和环境条件之间相互作用的支配。因此，提高抗倒伏性需要将生理学认识与实际农艺干预相结合的综合方法。本综述综合了小麦抗倒伏性所依据的结构、生理、生化和农艺机制方面的最新进展。特别强调了茎秆生物力学、基部节间特征、细胞壁组成、木质素和纤维素沉积、根系构型以及共同决定植株稳定性的遗传因素。本综述进一步考察了主要农艺措施，包括氮素管理、植株群体、播期、灌溉制度和品种选择，在不同生产环境下对倒伏风险的影响。此外，对常用植物生长调节剂，包括矮壮素(chlormequat chloride)、抗倒酯(trinexapac-ethyl)、多效唑(paclobutrazol)、烯效唑(uniconazole)和乙烯利(ethephon)，在其提高茎秆强度和减少倒伏的作用方面，对其生理响应、田间表现、实际应用和局限性进行了批判性评价。现有证据表明，没有任何单一策略能够在所有生产系统中提供一致的倒伏控制。相反，抗倒伏性的持久改善取决于将遗传改良、平衡作物营养、优化农艺管理以及根据当地环境条件合理使用植物生长调节剂相结合。本综述还强调了精准农业、高通量表型分析、先进喷雾技术以及对茎秆生物力学和根系锚定认识的提高所提供的新兴机遇。总之，这些进展为开发可持续、气候适应型的倒伏管理策略提供了框架，从而提高小麦生产","Frontiers in Plant Science","2026-10-12T00:00:00Z",81,{"impact":17,"substance":16,"depth":17,"authority":97,"freshness":98,"relevant":19,"comment":352},"系统综述小麦抗倒伏的生理机制、生长调节剂与农艺管理，信息增量与专业深度较高，对小麦稳产与智慧化管理有参考价值。",[354],{"name":348,"url":345},[24,27,356,357,358],"抗倒伏","植物生长调节剂","农艺管理",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[],{"status":36,"locked":37,"version":38,"method":39,"evidence":362},{"candidates":363,"agricultural_evidence":13},[364,368,372,379,385],{"code":30,"score":18,"supported":13,"title":365,"abstract":366,"tags":367},[31],[27,31],[27],{"code":72,"score":116,"supported":13,"title":369,"abstract":370,"tags":371},[],[104,113],[24],{"code":373,"score":82,"supported":13,"title":374,"abstract":375,"tags":378},"H3",[],[376,377],"灌溉","irrigation",[],{"code":380,"score":61,"supported":13,"title":381,"abstract":382,"tags":384},"F3",[],[383],"fertilization",[],{"code":67,"score":61,"supported":13,"title":386,"abstract":387,"tags":389},[],[388],"气候适应",[],[391,392],"小麦 抗倒伏 栽培管理","小麦 植物生长调节剂 矮壮素","小麦抗倒伏栽培管理-4820","10.3389\u002Ffpls.2026.1925460",{"doi":394,"openalex_id":396,"authors":397,"venue":348,"cited_by_count":140,"oa_url":409,"card":410,"direction":145,"ingested_from":147},"W7221517218",[398,400,402,404,407],{"name":399,"orcid":8},"Kavita Devi",{"name":401,"orcid":8},"Jasdev Singh Deol",{"name":403,"orcid":8},"Amit Kaul",{"name":405,"orcid":406},"Arun Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-0106-2735",{"name":408,"orcid":8},"Rahul Sharma","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1925460\u002Fpdf",{"tldr":411,"method":412,"finding":413,"direction":414,"opportunity":415},"综述小麦抗倒伏的生理机制、植物生长调节剂与农艺管理，提出综合防控策略。","文献综述，整合茎秆生物力学、细胞壁、根系及农艺与调节剂证据。","单一措施难以稳定控倒，需结合遗传、营养、农艺与调节剂并因地制宜。","农业人工智能与决策模型","可结合高通量表型与精准农业构建抗倒伏智能决策模型，实现因地制宜动态调控。","2026-10-13T23:30:19.035054Z",{"id":418,"title":419,"url":420,"summary":421,"summary_zh":422,"content":8,"source_name":423,"source_url":420,"published_at":424,"category":92,"cover_url":8,"hotness":12,"is_selected":37,"score":350,"score_detail":425,"sources":427,"tags":429,"primary_topic":433,"secondary_topics":434,"classification":440,"search_phrases":467,"slug":470,"view_count":193,"doi":471,"paper":472,"created_at":489},4433,"PROSAIL-DNN-TL: A Hyperspectral Inversion Framework for Winter Wheat Leaf Chlorophyll Content Based on Fine-Tuned Transfer Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16191971","Accurate and efficient estimation of leaf chlorophyll content (LCC) is essential for crop physiological monitoring and precision agriculture. Current remote sensing approaches for LCC estimation mainly rely on machine learning and deep learning methods, which exhibit strong nonlinear modelling capabilities but require sufficient and representative samples. Radiative transfer models (RTMs) can simulate canopy spectral response based on physical mechanisms and generate large-scale datasets, thereby overcoming the limitations of purely data-driven approaches. However, their applications under diverse environmental conditions remain challenging due to uncertainties caused by model parameterization and discrepancies between simulated and observed data. This study proposed a hybrid framework, PROSAIL-DNN-TL, integrating the PROSAIL RTM with full-network fine-tuned transfer learning for winter wheat LCC estimation. First, 85,680 simulated samples generated by PROSAIL were used to pre-train a deep neural network (DNN), and field observations (n = 270) were subsequently used for full-network fine-tuning. A conventional DNN model trained only with field data and machine learning models based on different feature selection strategies were established for comparison. The results showed that: (1) UVE-selected bands were distributed across visible, red-edge, and near-infrared regions; CARS retained more bands in the visible region, whereas SPA mainly selected near-infrared bands; (2) RR and SVR achieved higher accuracy than KNN, with the full-spectrum and CARS feature sets showing superior performance and SPA showing the lowest accuracy; (3) PROSAIL-DNN-TL achieved reliable LCC estimation performance, with an average test R2 of 0.79 across 500 repeated experiments, and showed improved performance compared with conventional machine learning models; (4) PROSAIL-DNN-TL achieved reliable predictive performance when evaluated using datasets collected during the 2024 and 2025 growing seasons, with R2 values of 0.75 and 0.92, respectively. Overall, the proposed hybrid framework integrates physical knowledge from RTMs with data-driven modelling through transfer learning, providing a potential approach for crop chlorophyll monitoring. However, the SPAD-to-LCC conversion used in this study was not specifically calibrated for the instrument and crop, and therefore, the absolute LCC values should be interpreted with caution.","准确、高效地估算叶片叶绿素含量（leaf chlorophyll content，LCC）对作物生理监测和精准农业至关重要。当前遥感估算LCC的方法主要依赖机器学习和深度学习方法，这类方法具有较强的非线性建模能力，但需要充足且具有代表性的样本。辐射传输模型（radiative transfer models，RTMs）能够基于物理机制模拟冠层光谱响应并生成大规模数据集，从而克服纯数据驱动方法的局限性。然而，由于模型参数化带来的不确定性以及模拟数据与观测数据之间的差异，其在不同环境条件下的应用仍面临挑战。本研究提出了一种混合框架PROSAIL-DNN-TL，将PROSAIL辐射传输模型与全网络微调迁移学习相结合，用于冬小麦LCC估算。首先，利用PROSAIL生成的85 680个模拟样本预训练深度神经网络（deep neural network，DNN），随后利用田间观测数据（n = 270）进行全网络微调。同时建立了仅使用田间数据训练的传统DNN模型以及基于不同特征选择策略的机器学习模型作为对比。结果表明：（1）UVE选择的波段分布在可见光、红边和近红外区域；CARS在可见光区域保留了更多波段，而SPA主要选择近红外波段；（2）RR和SVR的精度高于KNN，全光谱和CARS特征集表现较优，SPA精度最低；（3）PROSAIL-DNN-TL取得了可靠的LCC估算性能，在500次重复实验中平均测试R²为0.79，且相比传统机器学习模型表现出更优的性能；（4）利用2024年和2025年生长季采集的数据集进行评估时，PROSAIL-DNN-TL均表现出可靠的预测性能，R²分别为0.75和0.92。总体而言，所提出的混合框架通过迁移学习将辐射传输模型的物理知识与数据驱动建模相结合，为作物叶绿素监测提供了一种潜在途径。然而，本研究中使用的SPAD到LCC的转换并未针对仪器和作物进行专门校准，因此绝对LCC值应谨慎解读。","Agronomy","2026-10-07T00:00:00Z",{"impact":17,"substance":16,"depth":17,"authority":97,"freshness":98,"relevant":19,"comment":426},"将PROSAIL辐射传输模型与深度神经网络迁移学习结合，用8万余模拟样本预训练、270个田间样本微调，冬小麦叶绿素反演精度可靠，方法新颖且数据规模扎实，对作物生理监测与精准农业有参考价值。",[428],{"name":423,"url":420},[24,25,430,431,432],"冬小麦","迁移学习","叶绿素监测",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[435,436],{"code":54,"slug":250,"name":251,"path":252,"parent_code":253},{"code":181,"slug":437,"name":438,"path":439,"parent_code":253},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":36,"locked":37,"version":38,"method":39,"evidence":441},{"candidates":442,"agricultural_evidence":13},[443,449,455,463],{"code":30,"score":444,"supported":13,"title":445,"abstract":447,"tags":448},26,[446,31],"winter wheat",[27,446,31],[430],{"code":54,"score":18,"supported":13,"title":450,"abstract":452,"tags":454},[451],"hyperspectral",[57,453],"remote sensing",[25],{"code":181,"score":12,"supported":13,"title":456,"abstract":457,"tags":462},[],[458,459,460,461],"深度学习","机器学习","machine learning","deep learning",[431],{"code":72,"score":116,"supported":13,"title":464,"abstract":465,"tags":466},[],[104,113],[24],[468,469],"PROSAIL 冬小麦 叶绿素","高光谱 叶绿素 反演","PROSAIL冬小麦叶绿素-4433","10.3390\u002Fagronomy16191971",{"doi":471,"openalex_id":473,"authors":474,"venue":423,"cited_by_count":140,"oa_url":420,"card":484,"direction":145,"ingested_from":147},"W7220844556",[475,477,479,482],{"name":476,"orcid":8},"Xueqing Zhu",{"name":478,"orcid":8},"Ying Nian",{"name":480,"orcid":481},"Jikai Liu","https:\u002F\u002Forcid.org\u002F0000-0003-2365-5221",{"name":483,"orcid":8},"Xinwei Li",{"tldr":485,"method":486,"finding":487,"direction":145,"opportunity":488},"提出PROSAIL-DNN-TL框架，用PROSAIL模拟数据预训练DNN并全网络微调，反演冬小麦叶","PROSAIL辐射传输模型生成85680样本预训练DNN，270个田间样本全网络","500次重复实验平均测试R²为0.79，2024和2025年生长季验证R²分别为0.75和0.92，","SPAD到LCC转换未针对仪器和作物标定，可研究跨传感器、跨作物、跨生长季的迁移学习泛化与绝对叶绿素标定。","2026-10-08T23:30:29.383957Z"]