[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1502":3,"related-1502":88},{"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":29,"secondary_topics":34,"classification":35,"search_phrases":72,"slug":75,"view_count":76,"doi":8,"paper":77,"created_at":87},1502,"Precision Agriculture in Maize Production: A Systematic Review of Technologies, Applications, and Yield Optimisation","https:\u002F\u002Fwww.mdpi.com\u002F2073-4395\u002F16\u002F17\u002F1681","系统综述按照 PRISMA 2020 指南对 2020—2026 年间精准农业在玉米生产中应用的研究进行筛选，最终纳入 129 项研究。研究类型涵盖田间实验（28.6%）、遥感与精准农业整合研究（25.5%）、机器学习应用（19.4%）、气候导向精准农业策略（23.4%）、土壤退化研究（3.1%）。结果指出精准农业技术能显著提升玉米生产力、养分利用效率、水分利用效率和产量预测精度；但当前精准农业的推广仍受制于实施成本高、技术复杂性与数据可获得性等约束。原文标题：《Precision Agriculture in Maize Production: A Systematic Review of Technologies, Applications, and Yield Optimisation》。",null,"MDPI Agronomy 16(17) 1681","2026-09-01T00:00:00Z","论文",10,false,78,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,13,7,1,"系统综述全面梳理精准农业在玉米生产中的应用，数据详实，对农业信息化有参考价值。",[23],{"name":9,"url":6},[25,26,27,28],"系统综述","机器学习","玉米","精准农业",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},"A3","maize","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[],{"status":36,"locked":13,"version":37,"method":38,"evidence":39},"classified","2026-10-22.2","rules",{"candidates":40,"agricultural_evidence":43},[41,47,53,59,66],{"code":30,"score":42,"supported":43,"title":44,"abstract":45,"tags":46},15,true,[31],[27,31],[27],{"code":48,"score":42,"supported":43,"title":49,"abstract":51,"tags":52},"I1",[50],"precision agriculture",[28,50],[28],{"code":54,"score":55,"supported":43,"title":56,"abstract":57,"tags":58},"I2",4,[],[26],[26],{"code":60,"score":61,"supported":43,"title":62,"abstract":63,"tags":65},"H2",3,[],[64],"土壤",[],{"code":67,"score":61,"supported":43,"title":68,"abstract":69,"tags":71},"I3",[],[70],"遥感",[],[73,74],"机器学习 精准农业 系统综述 玉米","机器学习 精准农业","机器学习精准农业系统综述玉米-1502",2,{"doi":8,"openalex_id":8,"authors":78,"venue":8,"cited_by_count":79,"oa_url":8,"card":80,"direction":84,"ingested_from":86},[],0,{"tldr":81,"method":82,"finding":83,"direction":84,"opportunity":85},"系统综述2020-2026年精准农业在玉米生产中的应用，纳入129项研究，评估技术、应用及产量优化效","遵循PRISMA 2020指南，筛选129项研究，分类统计田间实验、遥感、机器学","精准农业显著提升玉米产量、养分和水分利用效率及预测精度，但受成本、技术复杂性和数据限制。","智慧农业 \u002F 农业物联网","可研究低成本、易操作的精准农业技术集成方案，或开发数据共享平台以降低技术门槛，促进小农户采纳。","agent","2026-09-03T00:06:44.675279Z",{"total":89,"page":20,"page_size":89,"items":90},6,[91,144,210,286,356,402],{"id":92,"title":93,"url":94,"summary":95,"summary_zh":8,"content":8,"source_name":96,"source_url":8,"published_at":8,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":97,"score_detail":98,"sources":100,"tags":102,"primary_topic":105,"secondary_topics":106,"classification":107,"search_phrases":132,"slug":135,"view_count":76,"doi":8,"paper":136,"created_at":143},4477,"玉米生产精准农业系统综述：技术、应用与产量优化（2020—2026）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37500368","依据PRISMA 2020指南，系统检索Scopus与Web of Science共464篇文献，最终纳入129项研究；样本构成为田间试验（28.6%）、遥感与精准农业整合研究（25.5%）、机器学习应用（19.4%）、气候知情精准农业策略（23.4%）和土壤退化研究（3.1%）；研究表明精准农业技术通过定点管理和数据驱动决策支持，提升了玉米生产力、养分利用效率、水利用效率和产量预测准确性；指出采用精准农业仍受制于实施成本高、技术复杂、数据有限等因素。","Precision Agriculture in Maize Production Systematic Review 2026",74,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":61,"relevant":20,"comment":99},"基于PRISMA 2020的系统综述，纳入129项研究，数据规模与方法规范性强，对玉米精准农业技术路径与瓶颈有实质参考价值，但发布日期不明、时效性偏弱。",[101],{"name":96,"url":94},[103,104,26,27,28,70],"智慧农业","产量预测",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[],{"status":36,"locked":13,"version":37,"method":38,"evidence":108},{"candidates":109,"agricultural_evidence":43},[110,114,119,124,128],{"code":48,"score":18,"supported":43,"title":111,"abstract":112,"tags":113},[28],[28],[103,28],{"code":30,"score":115,"supported":43,"title":116,"abstract":117,"tags":118},12,[27],[27],[27],{"code":67,"score":120,"supported":43,"title":121,"abstract":122,"tags":123},5,[],[70],[104,70],{"code":54,"score":55,"supported":43,"title":125,"abstract":126,"tags":127},[],[26],[26],{"code":60,"score":61,"supported":43,"title":129,"abstract":130,"tags":131},[],[64],[],[133,134],"玉米 精准农业 系统综述","玉米 遥感 机器学习 产量","玉米精准农业系统综述-4477",{"doi":8,"openalex_id":8,"authors":137,"venue":8,"cited_by_count":79,"oa_url":8,"card":138,"direction":84,"ingested_from":86},[],{"tldr":139,"method":140,"finding":141,"direction":84,"opportunity":142},"系统综述2020—2026年玉米精准农业技术、应用与产量优化研究。","按PRISMA 2020检索Scopus与WoS，纳入129项研究做分类分析。","精准农业通过定点管理与数据决策提升玉米产量、养分和水利用效率。","成本高、技术复杂与数据不足制约推广，低成本轻量化方案与本地化数据共享是研究空白。","2026-10-09T00:05:02.451957Z",{"id":145,"title":146,"url":147,"summary":148,"summary_zh":149,"content":8,"source_name":150,"source_url":147,"published_at":151,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":152,"score_detail":153,"sources":158,"tags":160,"primary_topic":163,"secondary_topics":164,"classification":170,"search_phrases":188,"slug":191,"view_count":79,"doi":192,"paper":193,"created_at":209},4759,"Machine Learning-based Prediction of SVI Parameter in Maize: A Comparative Study and Feature Importance Analysis","https:\u002F\u002Fdoi.org\u002F10.24925\u002Fturjaf.v14i10.2870-2879.9043","Background: Accurate estimation of seedling vigor indices (SVI) is critical for monitoring plant health and predicting yields in precision agriculture. This study comparatively evaluates the performance of different machine learning algorithms in estimating the SVI parameter. Methods: Germination data were collected from 39 maize genotypes under three different salinity conditions (0 mM, 100 mM, and 200 mM NaCl), including the parameters Gmax, MGT, GI, SL, RL, SdL, SMR, RMR, and SVI. The dataset was preprocessed through normalization to the [0–1] range. The SVI parameter was estimated using four different machine learning methods: Random Forest, CatBoost, LightGBM, and Support Vector Regression (SVR). To evaluate the performance of the models, both 10-fold cross-validation and 80%–20% hold-out validation techniques were employed. The model performance was examined using RMSE, MSE, MAE, and R² metrics. Results: The findings show that all models have a high explanatory power in the training dataset. Specifically, the CatBoost model showed the highest success in the training phase (R²=0.9962), whereas the SVR model achieved the highest generalization performance on the test dataset (R²=0.9712, RMSE=0.0582). Feature importance analysis results revealed that the 'App' parameter had the highest impact on the target variable in most models, but different structural interactions were prominent in the LightGBM model. The results demonstrate that machine learning techniques provide high accuracy in SVI estimation and that the tendency towards overfitting is limited. Conclusions: In conclusion, this study confirms that machine learning techniques are powerful and reliable tools for estimating spectral indices in precision agriculture applications. The integration of SVR and ensemble-based models into agricultural decision support systems is expected to significantly contribute to optimizing resource use and improving yield predictions.","背景：准确估计幼苗活力指数（SVI）对于精准农业中监测植物健康和预测产量至关重要。本研究比较评估了不同机器学习算法在估计SVI参数方面的性能。方法：从39个玉米基因型在三种不同盐度条件（0 mM、100 mM和200 mM NaCl）下收集发芽数据，包括Gmax、MGT、GI、SL、RL、SdL、SMR、RMR和SVI等参数。数据集通过归一化至[0–1]范围进行预处理。采用四种不同的机器学习方法估计SVI参数：随机森林、CatBoost、LightGBM和支持向量回归（SVR）。为评估模型性能，采用了10折交叉验证和80%–20%留出验证技术。使用RMSE、MSE、MAE和R²指标检验模型性能。结果：研究结果表明，所有模型在训练数据集中均具有较高的解释力。具体而言，CatBoost模型在训练阶段表现出最高的成功率（R²=0.9962），而SVR模型在测试数据集上取得了最高的泛化性能（R²=0.9712，RMSE=0.0582）。特征重要性分析结果显示，在大多数模型中，“App”参数对目标变量的影响最大，但在LightGBM模型中不同的结构交互作用更为突出。结果表明，机器学习技术在SVI估计中提供了高精度，且过拟合倾向有限。结论：总之，本研究证实机器学习技术是精准农业应用中估计光谱指数的强大而可靠的工具。将SVR和基于集成的模型整合到农业决策支持系统中，预计将显著有助于优化资源利用和改善产量预测。","Turkish Journal of Agriculture - Food Science and Technology","2026-10-11T00:00:00Z",63,{"impact":154,"substance":16,"depth":155,"authority":115,"freshness":156,"relevant":20,"comment":157},8,16,9,"方法对比扎实、结论可靠，但属细分领域论文，产业影响有限，适合主题聚合而非头条精选。",[159],{"name":150,"url":147},[103,161,26,27,162],"农业人工智能","耐盐育种",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[165],{"code":54,"slug":166,"name":167,"path":168,"parent_code":169},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":36,"locked":13,"version":37,"method":38,"evidence":171},{"candidates":172,"agricultural_evidence":43},[173,180,184],{"code":54,"score":174,"supported":43,"title":175,"abstract":177,"tags":179},19,[176],"machine learning",[26,176,178],"decision support",[161,26],{"code":30,"score":42,"supported":43,"title":181,"abstract":182,"tags":183},[31],[27,31],[27],{"code":48,"score":19,"supported":43,"title":185,"abstract":186,"tags":187},[],[28,50],[103],[189,190],"玉米 SVI 机器学习","玉米 耐盐 幼苗活力指数","玉米SVI机器学习-4759","10.24925\u002Fturjaf.v14i10.2870-2879.9043",{"doi":192,"openalex_id":194,"authors":195,"venue":150,"cited_by_count":79,"oa_url":147,"card":202,"direction":206,"ingested_from":208},"W7221462188",[196,199],{"name":197,"orcid":198},"Mustafa Turan Arslan","https:\u002F\u002Forcid.org\u002F0000-0001-5498-6571",{"name":200,"orcid":201},"Gülay Zülkadir","https:\u002F\u002Forcid.org\u002F0000-0003-3488-4011",{"tldr":203,"method":204,"finding":205,"direction":206,"opportunity":207},"用四种机器学习模型基于39个玉米基因型盐胁迫发芽数据预测幼苗活力指数SVI。","39个玉米基因型在三种盐浓度下的发芽数据，归一化后用RF、CatBoost、Li","SVR泛化最优（R²=0.9712），CatBoost训练拟合最高；App参数对SVI影响最大。","农业人工智能与决策模型","可扩展到多作物多胁迫环境，结合光谱或图像表型数据提升SVI预测的田间适用性。","openalex","2026-10-12T23:30:44.762497Z",{"id":211,"title":212,"url":213,"summary":214,"summary_zh":215,"content":8,"source_name":216,"source_url":213,"published_at":217,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":218,"score_detail":219,"sources":223,"tags":225,"primary_topic":229,"secondary_topics":230,"classification":237,"search_phrases":268,"slug":271,"view_count":20,"doi":272,"paper":273,"created_at":285},4694,"Precision Agriculture Approaches for Nutrient Management in Maize: A Comprehensive Review of Productivity, Efficiency and Economic Benefits","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fjeai\u002F2026\u002Fv48i104559","Maize nutrient management is an unusually demanding target for precision agriculture because crop demand, soil nutrient supply, weather, rooting conditions and management history vary simultaneously across space and time. Uniform fertiliser programmes can therefore be efficient in one part of a field and inefficient in another, while a recommendation that is appropriate before planting may become suboptimal after rainfall, mineralisation and crop establishment have altered nutrient availability. This critical narrative review evaluates precision approaches for nutrient management in maize, with emphasis on productivity, nutrient-use efficiency and farm-level economic performance. Literature published from 1 January 1990 to 2 August 2026 was examined using agricultural and multidisciplinary scholarly sources, supplemented by citation searching and bibliographic verification. The evidence was organised around the decision chain linking measurement, diagnosis, prescription and nutrient application. Strongest empirical support exists for site-specific and in-season nitrogen management because nitrogen is mobile, strongly coupled to weather and readily expressed in canopy signals. Chlorophyll meters, active optical sensors, aerial and unmanned aerial vehicle imagery, management zones, crop models and machine-learning approaches can improve the timing or spatial targeting of nitrogen, but diagnostic accuracy does not automatically translate into an economically superior fertiliser prescription. Multi-nutrient decision-support systems broaden precision management beyond nitrogen and can improve the balance of nitrogen, phosphorus and potassium, particularly where farmer practice is poorly aligned with crop demand. Across the evidence base, yield gains are often modest when conventional fertilisation is already adequate; benefits more consistently arise through reduced excess nutrient use, improved nutrient-use efficiency, better risk management or correction of under-fertilisation. Profitability is highly conditional on field heterogeneity, fertiliser and grain prices, baseline management, technology cost, scale and weather. Future progress requires multi-year on-farm validation of complete decision chains, stronger treatment of uncertainty and multi-stress confounding, improved multi-nutrient diagnostics, and economic evaluations that include fixed, transaction and information costs. Precision nutrient management is best understood as an adaptive decision framework rather than a single sensor or variable-rate technology.","玉米养分管理对精准农业而言是一个异常苛刻的目标，因为作物需求、土壤养分供应、天气、根系条件和管理历史在空间和时间上同时变化。因此，均匀施肥方案在田块某一部分可能高效，而在另一部分则可能低效；而播种前适宜的推荐方案，在降雨、矿化和作物建成改变养分有效性之后，也可能变得次优。这篇批判性叙述综述评估了玉米养分管理的精准方法，重点关注生产力、养分利用效率和农场层面经济表现。利用农业与多学科学术来源，检索了1990年1月1日至2026年8月2日发表的文献，并以引文检索和书目核验作为补充。证据围绕连接测量、诊断、处方和养分施用的决策链进行组织。最强的实证支持存在于位点特异性和季内氮管理，因为氮具有移动性、与天气强耦合，并易于在冠层信号中表达。叶绿素仪、主动光学传感器、航空和无人机影像、管理分区、作物模型和机器学习方法可以改善氮的施用时机或空间靶向，但诊断准确性并不会自动转化为经济上更优的施肥处方。多养分决策支持系统将精准管理扩展到氮之外，并能改善氮、磷、钾的平衡，尤其是在农户实践与作物需求严重不匹配的情况下。在整个证据基础中，当常规施肥已经充足时，产量增益往往有限；效益更一致地来自减少过量养分使用、提高养分利用效率、改善风险管理或纠正施肥不足。盈利能力高度取决于田块异质性、肥料和谷物价格、基线管理、技术成本、规模和天气。未来进展需要对完整决策链进行多年农场验证，更有力地处理不确定性和多胁迫混杂，改进多养分诊断，以及纳入固定成本、交易成本和信息成本的经济评价。精准养分管理最好被理解为一个适应性决策框架","Journal of Experimental Agriculture International","2026-10-10T00:00:00Z",71,{"impact":115,"substance":220,"depth":221,"authority":18,"freshness":156,"relevant":20,"comment":222},20,17,"系统综述精准养分管理在玉米上的产量、效率与经济性证据，方法学扎实但属学术综述，产业落地价值需长期验证。",[224],{"name":216,"url":213},[103,226,27,28,227,228],"变量施肥","遥感监测","养分管理",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[231],{"code":232,"slug":233,"name":234,"path":235,"parent_code":236},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",{"status":36,"locked":13,"version":37,"method":38,"evidence":238},{"candidates":239,"agricultural_evidence":43},[240,244,248,255,260,264],{"code":48,"score":155,"supported":43,"title":241,"abstract":242,"tags":243},[50],[28,50],[103,28],{"code":30,"score":42,"supported":43,"title":245,"abstract":246,"tags":247},[31],[27,31],[27],{"code":232,"score":249,"supported":43,"title":250,"abstract":251,"tags":254},11,[],[252,253,228],"施肥","肥料",[228,226],{"code":60,"score":89,"supported":43,"title":256,"abstract":257,"tags":259},[],[64,258],"soil",[],{"code":54,"score":61,"supported":43,"title":261,"abstract":262,"tags":263},[],[26],[],{"code":67,"score":20,"supported":13,"title":265,"abstract":266,"tags":267},[],[],[227],[269,270],"玉米 精准施肥 氮肥管理","遥感 变量施肥 养分利用效率","玉米精准施肥氮肥管理-4694","10.9734\u002Fjeai\u002F2026\u002Fv48i104559",{"doi":272,"openalex_id":274,"authors":275,"venue":216,"cited_by_count":79,"oa_url":213,"card":280,"direction":206,"ingested_from":208},"W7221366291",[276,278],{"name":277,"orcid":8},"Piyali Pal",{"name":279,"orcid":8},"Disha Chattopadhyay",{"tldr":281,"method":282,"finding":283,"direction":206,"opportunity":284},"综述玉米精准养分管理在生产力、效率与经济效益上的证据与局限。","系统检索1990-2026年文献，按测量-诊断-处方-施用决策链组织证据。","氮素精准管理证据最强，但诊断精度不必然带来经济更优的施肥处方。","亟需多年多点田间验证完整决策链，并纳入不确定性、多养分诊断与信息成本的经济评价。","2026-10-11T23:30:51.450082Z",{"id":287,"title":288,"url":289,"summary":290,"summary_zh":8,"content":8,"source_name":291,"source_url":289,"published_at":292,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":293,"score_detail":294,"sources":297,"tags":299,"primary_topic":302,"secondary_topics":303,"classification":309,"search_phrases":334,"slug":337,"view_count":89,"doi":338,"paper":339,"created_at":355},3523,"Soil-driven variability in crop response to variable-rate seeding and fertilization in an irrigated maize–sunflower system","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10458-y","Soil-driven variability in crop response to variable-rate seeding and fertilization in an irrigated maize–sunflower system。Precision Agriculture","Precision Agriculture","2026-09-25T00:00:00Z",69,{"impact":115,"substance":16,"depth":221,"authority":295,"freshness":154,"relevant":20,"comment":296},14,"精准农业核心期刊论文，探讨土壤空间变异对变量播种与施肥效果的影响，方法新颖、结论可靠，对智慧农业田间管理有参考价值，但属细分领域研究，影响范围有限。",[298],{"name":291,"url":289},[103,226,27,28,300,301],"向日葵","变量播种",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[304,305],{"code":232,"slug":233,"name":234,"path":235,"parent_code":236},{"code":60,"slug":258,"name":306,"path":307,"parent_code":308},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":36,"locked":13,"version":37,"method":38,"evidence":310},{"candidates":311,"agricultural_evidence":43},[312,316,321,325,329],{"code":30,"score":115,"supported":43,"title":313,"abstract":314,"tags":315},[31],[31],[27],{"code":232,"score":115,"supported":43,"title":317,"abstract":319,"tags":320},[318],"fertilization",[318],[226],{"code":60,"score":249,"supported":43,"title":322,"abstract":323,"tags":324},[258],[258],[],{"code":48,"score":120,"supported":43,"title":326,"abstract":327,"tags":328},[],[50],[103,28],{"code":330,"score":20,"supported":13,"title":331,"abstract":332,"tags":333},"A4",[],[],[300],[335,336],"Precision Agriculture 变量播种 变量施肥","灌溉玉米 向日葵 土壤变异","PrecisionAgriculture变量播种变量施肥-3523","10.1007\u002Fs11119-026-10458-y",{"doi":338,"openalex_id":340,"authors":341,"venue":291,"cited_by_count":79,"oa_url":8,"card":8,"direction":8,"ingested_from":208},"W7214357812",[342,345,347,349,351,353],{"name":343,"orcid":344},"María Videgain","https:\u002F\u002Forcid.org\u002F0000-0002-3630-7931",{"name":346,"orcid":8},"J. A. Martínez-Casasnovas",{"name":348,"orcid":8},"S. Artero",{"name":350,"orcid":8},"A. Vigo",{"name":352,"orcid":8},"M. Vidal",{"name":354,"orcid":8},"F. J. García-Ramos","2026-09-26T23:30:03.127069Z",{"id":357,"title":358,"url":359,"summary":360,"summary_zh":8,"content":8,"source_name":361,"source_url":8,"published_at":362,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":152,"score_detail":363,"sources":365,"tags":367,"primary_topic":369,"secondary_topics":370,"classification":371,"search_phrases":390,"slug":393,"view_count":76,"doi":8,"paper":394,"created_at":401},2271,"MDPI Agriculture 16(17):1932 厄瓜多尔农场级玉米产量模型空间可迁移性研究","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F17\u002F1932","MDPI Agriculture刊载厄瓜多尔马纳比省农场记录级玉米产量预测模型研究,基于518份数据评估Elastic Net、随机森林和直方图梯度提升模型。结果显示所有模型配置产生负的合并R2值,空间交叉验证显示空间乐观偏差,提示农场管理数据不足以支持对未见地区单作物记录的可靠产量预测。","MDPI Agriculture 16(17):1932","2026-09-06T16:00:00Z",{"impact":154,"substance":220,"depth":155,"authority":18,"freshness":89,"relevant":20,"comment":364},"基于518份农场记录检验多种机器学习模型的跨区域可迁移性，得出负面结论，对农业数据驱动产量预测的适用边界有实质警示价值，但属细分方法学研究，影响范围有限。",[366],{"name":361,"url":359},[103,104,26,27,368],"空间迁移",{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[],{"status":36,"locked":13,"version":37,"method":38,"evidence":372},{"candidates":373,"agricultural_evidence":43},[374,378,382,386],{"code":30,"score":115,"supported":43,"title":375,"abstract":376,"tags":377},[27],[27],[27],{"code":48,"score":20,"supported":13,"title":379,"abstract":380,"tags":381},[],[],[103],{"code":54,"score":20,"supported":13,"title":383,"abstract":384,"tags":385},[],[],[26],{"code":67,"score":20,"supported":13,"title":387,"abstract":388,"tags":389},[],[],[104],[391,392],"产量预测 智慧农业 机器学习 空间迁移","产量预测 智慧农业","产量预测智慧农业机器学习空间迁移-2271",{"doi":8,"openalex_id":8,"authors":395,"venue":8,"cited_by_count":79,"oa_url":8,"card":396,"direction":206,"ingested_from":86},[],{"tldr":397,"method":398,"finding":399,"direction":206,"opportunity":400},"评估三种机器学习模型在厄瓜多尔农场级玉米产量预测中的空间可迁移性。","基于518份农场记录，用Elastic Net、随机森林和直方图梯度提升做空间交","所有模型合并R2为负，存在空间乐观偏差，农场管理数据不足以可靠预测未见地区产量。","可探索融合遥感、气象与土壤等多源数据，提升小农户农场级产量模型的空间泛化能力。","2026-09-13T00:04:04.999192Z",{"id":403,"title":404,"url":405,"summary":406,"summary_zh":8,"content":8,"source_name":407,"source_url":8,"published_at":408,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":409,"score_detail":410,"sources":412,"tags":414,"primary_topic":415,"secondary_topics":416,"classification":417,"search_phrases":440,"slug":443,"view_count":61,"doi":444,"paper":445,"created_at":452},1366,"【系统综述】玉米精准农业：技术、应用与产量优化的综合评价（2020—2026）","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16171681","按 PRISMA 2020 流程检索 Scopus 与 Web of Science，464 条记录中纳入 129 项研究。涵盖田间试验 28.6%、遥感与 PA 集成 25.5%、机器学习 19.4%、气候知情策略 23.4%、土壤退化 3.1%。综述论证精准农业通过特定地点管理与数据驱动决策，有效提高玉米生产力、养分与水分利用效率、产量预测准确性；指出实施成本、技术复杂度和数据可得性仍是推广瓶颈。","Agronomy · MDPI · 2026-09-01","2026-08-31T16:00:00Z",73,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":76,"relevant":20,"comment":411},"系统综述覆盖2020-2026年129项研究，数据详实，对精准农业技术应用与瓶颈有全面分析，但时效性较低。",[413],{"name":407,"url":405},[161,27,28,70],{"code":30,"slug":31,"name":27,"path":32,"parent_code":33},[],{"status":36,"locked":13,"version":37,"method":38,"evidence":418},{"candidates":419,"agricultural_evidence":43},[420,424,428,432,436],{"code":30,"score":115,"supported":43,"title":421,"abstract":422,"tags":423},[27],[27],[27],{"code":48,"score":115,"supported":43,"title":425,"abstract":426,"tags":427},[28],[28],[28],{"code":54,"score":55,"supported":43,"title":429,"abstract":430,"tags":431},[],[26],[161],{"code":67,"score":55,"supported":43,"title":433,"abstract":434,"tags":435},[],[70],[70],{"code":60,"score":61,"supported":43,"title":437,"abstract":438,"tags":439},[],[64],[],[441,442],"农业人工智能 精准农业 玉米 遥感","农业人工智能 精准农业","农业人工智能精准农业玉米遥感-1366","10.3390\u002Fagronomy16171681",{"doi":444,"openalex_id":8,"authors":446,"venue":8,"cited_by_count":79,"oa_url":8,"card":447,"direction":84,"ingested_from":86},[],{"tldr":448,"method":449,"finding":450,"direction":84,"opportunity":451},"系统综述2020-2026年玉米精准农业技术、应用与产量优化，纳入129项研究。","PRISMA 2020流程，检索Scopus和Web of Science，纳入","精准农业提高玉米生产力、养分水分利用效率和产量预测准确性，但成本、技术复杂度、数据可得性是瓶颈。","可研究低成本、易用的精准农业技术集成方案，或针对小农户的数据可得性解决方案。","2026-09-02T00:05:06.975565Z"]