[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3866":3,"related-3866":116},{"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":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":83,"slug":86,"view_count":87,"doi":88,"paper":89,"created_at":115},3866,"The nexus of formulation, application and digital technologies: very-low volume formulations as an enabler for future small, automated, precision application vehicles","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10460-4","Abstract Purpose Precision agriculture (PA) utilises data to enable more accurate application of agricultural inputs such as plant protection products (PPP) with precision and variable rate application (VRA) equipment. New evolving application technologies offer the ability to downsize this to small, automated vehicles with many advantages concerning cost, efficiency, sustainability, safety, and operator requirements. A new and important component of precision agriculture is the design of formulations: current generation PPP formulations were not designed for very-low volume application (VLV, 5–50 L\u002Fha for 2D crops) and can lose performance at VLV. Formulations designed to perform at VLV have the potential to maintain or in some cases even increase performance at VLV and enable the application equipment to be downsized to small, automated vehicles such as unmanned ground vehicles (UGV) and unmanned aerial vehicles (UAV). This work investigates the performance of VLV optimised formulations from lab-scale to field-scale and how this may enable future VLV precision application of PPPs. Method VLV optimised suspension concentrate (SC) formulations were prepared with low dose-rates of high-spreading and uptake-enhancing formulants (adjuvants) and evaluated for leaf deposit spreading and coverage, leaf cuticle penetration and biological efficacy. Results At VLV, formulations containing high-spreading formulants maintained good coverage and formulations containing uptake-enhancing formulants showed enhanced uptake in cuticle penetration tests. In greenhouse tests on tomato plants, formulations without these formulants lost performance at VLV (15 L\u002Fha) compared to higher spray volumes (200 L\u002Fha) against disease infection while formulations containing these formulants demonstrated better performance nearer to that demonstrated at higher spray volumes. In field tests on rice, a formulation containing high-spreading formulants showed higher efficacy against disease infection at VLV when applied by UAV relative to a formulation without these formulants applied at the same spray volume. Conclusion Formulations designed for VLV spray application can achieve good efficacy not only at standard spray application volumes but also at VLV with UAV application and is a formulation design technology that can enable future VLV precision application.","摘要 目的 精准农业（PA）利用数据，通过精准和变量施用（VRA）设备，实现植物保护产品（PPP）等农业投入品的更精准施用。新兴的施药技术能够将其缩小至小型自动化车辆，在成本、效率、可持续性、安全性及操作人员要求等方面具有诸多优势。精准农业的一个新的重要组成部分是制剂设计：当前一代PPP制剂并非为超低容量（VLV，二维作物为5–50 L\u002Fha）施用而设计，在VLV下可能丧失性能。专为在VLV下发挥性能而设计的制剂有可能在VLV下维持甚至在某些情况下提升性能，并使施药设备能够缩小至小型自动化车辆，如无人地面车辆（UGV）和无人机（UAV）。本研究探讨了VLV优化制剂从实验室规模到田间规模的性能，以及这如何能够实现未来PPP的VLV精准施用。方法 制备了VLV优化的悬浮剂（SC）制剂，其中含有低剂量的高铺展性和吸收增强型助剂，并评估了其叶面沉积铺展与覆盖度、叶表皮渗透性及生物 efficacy。结果 在VLV下，含有高铺展性助剂的制剂保持了良好的覆盖度，含有吸收增强型助剂的制剂在表皮渗透试验中表现出增强的吸收。在番茄植株的温室试验中，不含这些助剂的制剂在VLV（15 L\u002Fha）下相较于较高喷雾量（200 L\u002Fha）在抗病害感染方面丧失了性能，而含有这些助剂的制剂则表现出更好的性能，更接近较高喷雾量下的表现。在水稻田间试验中，含有高铺展性助剂的制剂在UAV施用VLV时，相较于不含这些助剂且以相同喷雾量施用的制剂，表现出更高的抗病害感染 efficacy。结论 专为VLV喷雾施用设计的制剂不仅能在标准喷雾施用量下取得良好 efficacy，在UAV施用的VLV下同样如此，是一种能够实现未来VLV精准施用的制剂设计技术。",null,"Precision Agriculture","2026-10-01T00:00:00Z","论文",10,true,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"该研究提出面向超低容量喷雾的制剂设计新思路，实验室到田间验证了其与无人机等小型自动化装备的适配性，为精准施药与农药减量提供可行路径，专业增量突出。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","精准农业","农药减量","植保无人机","无人农机",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","A",[],{"status":39,"locked":40,"version":41,"method":42,"evidence":43},"classified",false,"2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":14},[45,50,57,65,72,78],{"code":32,"score":20,"supported":14,"title":46,"abstract":47,"tags":49},[],[34,48,33],"稻田",[],{"code":51,"score":52,"supported":14,"title":53,"abstract":54,"tags":56},"I1",8,[],[27,55],"precision agriculture",[26,27],{"code":58,"score":59,"supported":14,"title":60,"abstract":61,"tags":64},"B1",6,[],[62,63],"番茄","tomato",[],{"code":66,"score":59,"supported":14,"title":67,"abstract":68,"tags":71},"B7",[],[69,70],"温室","greenhouse",[],{"code":73,"score":74,"supported":40,"title":75,"abstract":76,"tags":77},"F4",2,[],[],[28,29],{"code":79,"score":21,"supported":40,"title":80,"abstract":81,"tags":82},"F5",[],[],[30],[84,85],"超低容量喷雾 无人机 水稻","精准变量施药 无人地面车","超低容量喷雾无人机水稻-3866",5,"10.1007\u002Fs11119-026-10460-4",{"doi":88,"openalex_id":90,"authors":91,"venue":10,"cited_by_count":106,"oa_url":6,"card":107,"direction":113,"ingested_from":114},"W7214987182",[92,95,98,100,102,104],{"name":93,"orcid":94},"Malcolm A. Faers","https:\u002F\u002Forcid.org\u002F0000-0001-5616-0300",{"name":96,"orcid":97},"Emilia Hilz","https:\u002F\u002Forcid.org\u002F0009-0009-2645-8283",{"name":99,"orcid":9},"Sybille Lamprecht",{"name":101,"orcid":9},"Xu Wang",{"name":103,"orcid":9},"Feng Qi",{"name":105,"orcid":9},"Santiago Molinari",0,{"tldr":108,"method":109,"finding":110,"direction":111,"opportunity":112},"研究超低容量优化制剂从实验室到田间的表现，证明其可支撑无人机等小型自动化精准施药。","制备含高铺展\u002F吸收促进助剂的悬浮剂，测试叶面覆盖、角质层渗透及温室与稻田防效。","VLV优化制剂在15 L\u002Fha下防效接近200 L\u002Fha，无人机稻田施药效果优于普通制剂。","智慧农业 \u002F 农业物联网","制剂设计与小型施药装备协同优化是空白，可研究VLV下助剂-雾滴-靶标互作及智能变量施药决策。","数字乡村与农业信息化","openalex","2026-10-01T23:30:02.574260Z",{"total":59,"page":21,"page_size":59,"items":117},[118,179,246,326,403,454],{"id":119,"title":120,"url":121,"summary":122,"summary_zh":9,"content":123,"source_name":124,"source_url":9,"published_at":125,"category":126,"cover_url":9,"hotness":13,"is_selected":40,"score":127,"score_detail":128,"sources":133,"tags":135,"primary_topic":139,"secondary_topics":140,"classification":141,"search_phrases":174,"slug":177,"view_count":106,"doi":9,"paper":9,"created_at":178},4930,"盐城一片稻田的'AI处方':粮食年均增产8%以上 每亩增收超百元","http:\u002F\u002Fwww.came.net.cn\u002FsecondLevelPage\u002Finfo\u002F218\u002F227189","10月8日,江苏盐城亭湖区智慧农场,'亭农云'平台整合土壤墒情传感器、田间气象站、虫情测报设备,24小时值守。AI模型对土壤养分、湿度、光照、虫情综合研判,自动生成'田间处方',对比传统种植,水肥资源浪费明显减少,粮食年均产量较普通地块提升8%以上,每亩增收超百元。一体化智能灌溉泵站配合电磁阀,一人10分钟能管好600亩田的水,新增有效耕种面积28亩,较传统渠系节地4.6%。","10月8日，在亭湖区智慧农场，亭湖区农业技术综合服务中心副主任陈乃祥蹲在东南角的田埂上，拨开一丛水稻，几株稻穗的颖壳上裹着黑色粉状物，捻一下，粉末沾在指尖，是黑穗病。\n\n“搁以前，四五个人跑两三天，才能巡完600亩稻田。”陈乃祥拍掉指尖的粉末站起身，“如今智能设备全天值守，系统自动识别，AI研判、精准施药。”\n\n话音刚落，一架植保无人机腾空而起，沿着预设航线飞向农田。\n\n这片稻田，是盐城以人工智能赋能传统农业的一个缩影。\n\n走进综合服务中心，屏幕上，整片稻田的状态尽收眼底。土壤墒情传感器、田间微型气象站、虫情测报设备24小时值守田间，农情数据实时回传“亭农云”平台，形成一个动态更新的农田数据库。\n\n![Image 1](http:\u002F\u002F202.127.42.160:3009\u002Fupload_file\u002F2026\u002F10\u002F14\u002F20261014144727766.png)\n\n“以前种地靠经验，施肥灌溉全凭眼力，多浇一寸水、多施一把肥是常事。”农场负责人王其玉回忆，每逢高温干旱或病虫害高发时节，管护人员要顶着烈日跑遍整片田，劳动强度大，还容易错过最佳管护窗口。\n\n如今，算法接过了老农的“经验账本”。AI模型对土壤养分、湿度、光照、虫情等数据综合研判，自动生成“田间处方”，哪一块田缺水、哪一片需要补肥、哪里存在虫害风险，一目了然。\n\n“传感器埋进土里，相当于给农田配备全天候‘体检医生’。”陈乃祥介绍，系统会根据水稻不同生长周期动态调整水肥供给，对比传统种植，水肥资源浪费明显减少，粮食年均产量较普通地块提升8%以上，每亩增收超百元。\n\n水的问题，同样交给算法。农场将原先“北大南小”的两块田整合为大田，创新采用“管渠结合、灌排一体”的田间渠系模式，斗渠改用大口径管道，农渠灌排两用。一体化智能灌溉泵站配合农渠首末端电磁阀，一人10分钟能管好600亩田的水。仅此一项，就新增有效耕种面积28亩，较传统灌排渠系模式节地4.6%。\n\n水稻植保，是水稻生产中的关键环节。传统模式靠人工巡查，覆盖面有限，发现虫害时往往已经扩散，用药量大、防治时机滞后。\n\n在这片智慧农场，一套“虫情监测—AI研判—无人机精准施药”的闭环管护体系，守护着稻田。AI图像识别系统自动统计虫口数量、识别害虫种类，田间摄像头实时捕捉稻株长势，结合气象站的温度、湿度、降雨数据，让预警跑在病害发生前。\n\n“系统通过对虫情数据的分析研判，确定防治对象、防治适期和频次，形成差异化植保作业方案，病虫害防治更精准。”市植物保护站副站长曹丽算了一笔账，农资成本降了，农药残留少了，稻米品质稳了，高温天气下人工植保的安全风险也避开了。\n\n管护体系，铺到了更多稻田里。全市依托“盐农云”平台搭建的智慧大田驾驶舱，将卫星遥感、无人机巡田、地面物联网设备拧成一股绳，1200余万亩稻麦实现全域动态监测。上线“盐小农”AI智能体，支持地块手绘评估、作物识别、长势监测、病害防治、产量预估等功能，通过遥感、传感、气象三重数据交叉校验，破解通用农业AI预测失真难题。\n\n视线转向广袤的大田，智能化装备成为田间主力军，弯腰劳作的农户越来越少。\n\n北斗导航赋能机器协同作业，覆盖耕地整地、播种插秧、植保防护、成熟收割全流程，自主规划路径、自动避障、自主作业。\n\n“规模化种植最头疼的是农时窗口短。”王其玉说，无人农机群组可多台设备协同开工，以往数十人才能干完的大田管护工作，如今少数技术人员在管控室就能统筹千亩农田。\n\n机器把重活接了过去，人也没闲着。“设备运维、模型调优、异常情况处置，离不开人。”陈乃祥现在去田里，多半是核实系统标出的异常点位，不用再一垄一垄地巡。\n\n机器承担起重复繁重的农事劳动，人转向技术管理与数据分析，“体力型”劳动力正转变成“技术型”。\n\n这背后，是全市层面的系统布局。今年3月，全省“人工智能+农业”推进会暨农业农村局长会议正式部署实施“人工智能+农业141”行动。盐城紧随其后，出台《盐城市科技赋能农业强市建设行动计划》，系统布局“人工智能+农业”。同时，依托“盐农云”农业农村大数据平台，探索“大屏管治理、手机惠农户、AI解难题”的智慧农业新路径。\n\n布局的成效，写在田野上。全市建成智慧农业园区18个、智慧农场63个，农业生产信息化率达60%，处于全省第一方阵；智能农机总量超2.3万台（套），农作物耕种收综合机械化率达90.5%。\n\n曾经“看天吃饭”的农田，正在AI与数字技术的加持下，开启“知天而作、数据种地”的全新农耕时代。\n\n亭湖区农业技术综合服务中心副主任陈乃祥说：“人工智能赋能农业，实验室算法再好，也要落到田地里接受检验。智慧农场的核心，不是简单把设备铺到田里，而是沉淀本土农田的真实数据，训练适配本地土壤、气候、作物的AI模型。\n\n传统农民靠代代积累的种地经验，智慧农业把千亩农田的经验沉淀为数据，转化成可复制的生产方案。我们当前遇到的最大课题，一方面是硬件设备要适应田间复杂多变的环境，另一方面，要让普通农户看得懂、用得上数字化工具，不能让智慧农业停留在示范地块。\n\n下一步，将持续推进农业数据融合，总结可复制的经验模式，将智慧农场的成功经验分享给周边种植大户、合作社，让更多农户享受到数字农业带来的红利，以数智力量夯实粮食安全根基。”","中国农业机械化信息网 2026 年 10 月 13 日","2026-10-13T00:00:00Z","报道",72,{"impact":17,"substance":129,"depth":130,"authority":13,"freshness":131,"relevant":21,"comment":132},20,17,7,"盐城智慧农场以AI处方实现增产增收，数据详实、多方信源，具行业示范价值。",[134],{"name":124,"url":121},[26,136,137,30,138],"农业人工智能","精准植保","盐农云",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":40,"version":41,"method":42,"evidence":142},{"candidates":143,"agricultural_evidence":14},[144,148,155,161,165,169],{"code":32,"score":52,"supported":14,"title":145,"abstract":146,"tags":147},[48],[],[],{"code":149,"score":150,"supported":14,"title":151,"abstract":152,"tags":154},"H2",3,[],[153],"土壤",[],{"code":156,"score":150,"supported":14,"title":157,"abstract":158,"tags":160},"H3",[],[159],"灌溉",[],{"code":79,"score":21,"supported":40,"title":162,"abstract":163,"tags":164},[],[],[30],{"code":51,"score":21,"supported":40,"title":166,"abstract":167,"tags":168},[],[],[26],{"code":170,"score":21,"supported":40,"title":171,"abstract":172,"tags":173},"I2",[],[],[136],[175,176],"盐城 亭湖区 智慧农场","盐农云 人工智能","盐城亭湖区智慧农场-4930","2026-10-15T00:05:53.453405Z",{"id":180,"title":181,"url":182,"summary":183,"summary_zh":184,"content":9,"source_name":185,"source_url":182,"published_at":186,"category":12,"cover_url":9,"hotness":13,"is_selected":40,"score":187,"score_detail":188,"sources":192,"tags":194,"primary_topic":197,"secondary_topics":198,"classification":199,"search_phrases":221,"slug":224,"view_count":106,"doi":225,"paper":226,"created_at":245},4834,"Comparative Analysis of Spatial Statistical Methods for Modelling Rice Yield Variability in Uniformity Trials","https:\u002F\u002Fdoi.org\u002F10.37394\u002F232028.2026.6.9","Spatial heterogeneity is a fundamental characteristic of agricultural landscapes, and accurately modelling its impact on crop yield is critical for precision agriculture. This study presents a comparative analysis of spatial statistical and machine learning approaches to model yield variability in a field exhibiting strong spatial dependence. Initial geostatistical analysis confirmed significant positive spatial autocorrelation (Moran's I = 0.7355, p \u003C 2.2e-16). A series of models were evaluated, progressing from linear and polynomial trend surfaces to spatial regression (Lag and Error), mixed effects, and a Random Forest ensemble. The results demonstrate that while traditional spatial models effectively captured and explained the spatial autocorrelation, a Random Forest model significantly outperformed all others in predictive accuracy, achieving a 31% lower Root Mean Square Error (36.05) than the best spatial regression model and explaining 71.02% of the variance. Among the spatial models, a quadratic trend surface with a row × column interaction provided the most parsimonious fit, revealing an accelerating yield increase along rows and a U-shaped pattern across columns. The Random Forest model's residuals showed no statistically significant remaining spatial autocorrelation (Moran's I p-value = 0.97); however, we caution that failure to reject spatial randomness does not prove its absence. Equivalence testing (TOST) and power analysis support the conclusion that spatial dependence was adequately captured. We conclude that machine learning ensembles like Random Forest offer superior predictive power for yield mapping, though spatial regression models remain valuable for providing parsimonious, interpretable insights into the underlying structural gradients driving yield variability.","空间异质性是农业景观的基本特征，准确模拟其对作物产量的影响对于精准农业至关重要。本研究对空间统计方法与机器学习方法进行了比较分析，以模拟具有强空间依赖性的田块中的产量变异性。初步地统计分析确认了显著的正空间自相关（Moran's I = 0.7355，p \u003C 2.2e-16）。研究评估了一系列模型，从线性趋势面和多项式趋势面逐步推进到空间回归（滞后模型和误差模型）、混合效应模型以及随机森林集成模型。结果表明，尽管传统空间模型能够有效捕捉并解释空间自相关，但随机森林模型在预测精度上显著优于所有其他模型，其均方根误差（36.05）比最佳空间回归模型低31%，并解释了71.02%的方差。在空间模型中，带有行×列交互项的二次趋势面提供了最简约的拟合，揭示了沿行方向产量增加的加速趋势以及沿列方向的U型模式。随机森林模型的残差未显示出统计学上显著的剩余空间自相关（Moran's I p值 = 0.97）；然而，我们提醒，未能拒绝空间随机性并不能证明其不存在。等效性检验（TOST）和功效分析支持空间依赖性已被充分捕捉的结论。我们得出结论：诸如随机森林之类的机器学习集成方法在产量制图方面具有更优越的预测能力，尽管空间回归模型对于提供简约且可解释的见解——揭示驱动产量变异性的潜在结构性梯度——仍然具有重要价值。","International Journal of Computational and Applied Mathematics & Computer Science","2026-10-12T00:00:00Z",68,{"impact":52,"substance":189,"depth":130,"authority":190,"freshness":20,"relevant":21,"comment":191},21,13,"方法学扎实的作物产量空间建模对比研究，对精准农业与产量遥感建模有参考价值，但属细分领域学术成果，公共影响有限。",[193],{"name":185,"url":182},[26,136,27,195,196],"遥感估产","空间统计",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":40,"version":41,"method":42,"evidence":200},{"candidates":201,"agricultural_evidence":14},[202,206,210,216],{"code":32,"score":52,"supported":14,"title":203,"abstract":204,"tags":205},[33],[],[],{"code":51,"score":52,"supported":14,"title":207,"abstract":208,"tags":209},[],[27,55],[26,27],{"code":170,"score":131,"supported":14,"title":211,"abstract":212,"tags":215},[],[213,214],"机器学习","machine learning",[136],{"code":217,"score":21,"supported":40,"title":218,"abstract":219,"tags":220},"I3",[],[],[195],[222,223],"水稻产量 空间统计 随机森林","水稻产量变异 空间自相关","水稻产量空间统计随机森林-4834","10.37394\u002F232028.2026.6.9",{"doi":225,"openalex_id":227,"authors":228,"venue":185,"cited_by_count":106,"oa_url":237,"card":238,"direction":244,"ingested_from":114},"W7221516422",[229,231,233,235],{"name":230,"orcid":9},"Adebayo O. P",{"name":232,"orcid":9},"Ahmed I",{"name":234,"orcid":9},"Garba I. M",{"name":236,"orcid":9},"Mustaph A. D","https:\u002F\u002Fwseas.com\u002Fjournals\u002Fcamcs\u002F2026\u002Fa18camcs-009(2026).pdf",{"tldr":239,"method":240,"finding":241,"direction":242,"opportunity":243},"比较空间统计与随机森林模型对水稻产量空间变异的建模效果。","基于均匀试验田产量数据，用Moran's I、空间回归、混合效应与随机森林对比。","随机森林预测精度最高，RMSE比最优空间回归低31%，解释71%方差。","农业遥感与作物表型","可探索机器学习与空间统计耦合的混合模型，兼顾预测精度与空间可解释性。","农业人工智能与决策模型","2026-10-13T23:30:41.841849Z",{"id":247,"title":248,"url":249,"summary":250,"summary_zh":251,"content":9,"source_name":252,"source_url":249,"published_at":253,"category":12,"cover_url":9,"hotness":13,"is_selected":40,"score":254,"score_detail":255,"sources":259,"tags":261,"primary_topic":265,"secondary_topics":266,"classification":278,"search_phrases":300,"slug":303,"view_count":74,"doi":304,"paper":305,"created_at":325},4427,"Development of Internet of Things-Based Soil Sensors for pH and Phosphorus Monitoring in Paddy Fields: Development, Accuracy, and Implementation Challenges","https:\u002F\u002Fdoi.org\u002F10.56581\u002Fijrerd.11.05.01-08","The development of Internet of Things (IoT) technology provides opportunities for faster and continuous soil monitoring to support precision agriculture.Monitoring soil pH and phosphorus is important in rice cultivation because both parameters are associated with soil chemical conditions and nutrient availability.This review aimed to examine the development of IoT-based soil sensors for monitoring soil pH and phosphorus, including sensor performance, factors affecting measurement results, and potential applications.A literature review was conducted on research and review articles published between 2019 and 2026.The literature was descriptively analyzed and synthesized based on technological development, sensor performance, and environmental and soil characteristics.The results indicate that pH and phosphorus sensors have been developed using various sensing approaches and have demonstrated promising performance under certain conditions; however, measurement results vary across parameters and soil conditions.Sensor performance is influenced by the sensing principle, soil characteristics, environmental conditions, calibration, and validation.IoT-based sensors have the potential to support real-time soil monitoring, but their application as quantitative measurement tools still requires validation and calibration under diverse soil conditions.","物联网（IoT）技术的发展为实现更快、连续性的土壤监测以支持精准农业提供了机遇。监测土壤pH和磷在水稻种植中具有重要意义，因为这两个参数均与土壤化学状况和养分有效性相关。本综述旨在考察用于监测土壤pH和磷的基于物联网的土壤传感器的发展现状，包括传感器性能、影响测量结果的因素以及潜在应用。本文对2019年至2026年间发表的研究论文和综述文章进行了文献综述。基于技术发展、传感器性能以及环境和土壤特征，对文献进行了描述性分析和综合。结果表明，pH和磷传感器已采用多种传感方法进行开发，并在特定条件下展现出良好性能；然而，测量结果因参数和土壤条件的不同而存在差异。传感器性能受传感原理、土壤特性、环境条件、校准和验证的影响。基于物联网的传感器具有支持实时土壤监测的潜力，但其作为定量测量工具的应用仍需在不同土壤条件下进行验证和校准。","International journal of recent engineering research and development.","2026-10-06T00:00:00Z",62,{"impact":256,"substance":17,"depth":257,"authority":20,"freshness":52,"relevant":21,"comment":258},12,15,"综述性论文，系统梳理IoT土壤pH与磷传感器的发展、精度与落地挑战，对智慧农业土壤监测方向有参考价值，但非突破性成果。",[260],{"name":252,"url":249},[26,262,27,263,264],"物联网","土壤监测","水稻种植",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[267,273],{"code":268,"slug":269,"name":270,"path":271,"parent_code":272},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot","I",{"code":149,"slug":274,"name":275,"path":276,"parent_code":277},"soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":39,"locked":40,"version":41,"method":42,"evidence":279},{"candidates":280,"agricultural_evidence":14},[281,287,292,296],{"code":268,"score":17,"supported":14,"title":282,"abstract":284,"tags":286},[283],"internet of things",[262,283,285],"IoT",[262],{"code":32,"score":257,"supported":14,"title":288,"abstract":290,"tags":291},[289],"paddy",[34,33],[264],{"code":149,"score":19,"supported":14,"title":293,"abstract":294,"tags":295},[274],[153,274],[],{"code":51,"score":52,"supported":14,"title":297,"abstract":298,"tags":299},[],[27,55],[26,27],[301,302],"物联网 土壤传感器 稻田","土壤pH 监测","物联网土壤传感器稻田-4427","10.56581\u002Fijrerd.11.05.01-08",{"doi":304,"openalex_id":306,"authors":307,"venue":252,"cited_by_count":106,"oa_url":249,"card":320,"direction":111,"ingested_from":114},"W7220841659",[308,310,313,315,318],{"name":309,"orcid":9},"Fariha Laqania",{"name":311,"orcid":312},"Oviyanti Mulyani","https:\u002F\u002Forcid.org\u002F0000-0003-3941-8896",{"name":314,"orcid":9},"Ade Setiawan",{"name":316,"orcid":317},"Pujawati Suryatmana","https:\u002F\u002Forcid.org\u002F0000-0002-4012-8645",{"name":319,"orcid":9},"Wahyu Daradjat",{"tldr":321,"method":322,"finding":323,"direction":111,"opportunity":324},"综述2019-2026年稻田pH与磷的物联网土壤传感器发展、精度及实施挑战。","文献综述，按技术发展、传感器性能与土壤环境特征归纳分析。","传感器在特定条件下表现良好，但精度受原理、土壤、环境与校准影响，定量应用仍需验证。","稻田复杂土壤条件下pH\u002F磷传感器的原位校准与多源数据融合验证是待突破的研究空白。","2026-10-08T23:30:13.316611Z",{"id":327,"title":328,"url":329,"summary":330,"summary_zh":331,"content":9,"source_name":332,"source_url":329,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":40,"score":333,"score_detail":334,"sources":337,"tags":339,"primary_topic":343,"secondary_topics":344,"classification":350,"search_phrases":366,"slug":369,"view_count":21,"doi":370,"paper":371,"created_at":402},3974,"A real-time estimation method for wheeled agricultural machinery slip parameters in paddy fields based on the prediction-residual approach","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112478","A real-time estimation method for wheeled agricultural machinery slip parameters in paddy fields based on the prediction-residual approach。Computers and Electronics in Agriculture","基于预测残差法的水稻田轮式农业机械滑转参数实时估计方法。Computers and Electronics in Agriculture","Computers and Electronics in Agriculture",69,{"impact":256,"substance":17,"depth":335,"authority":19,"freshness":20,"relevant":21,"comment":336},16,"提出基于预测残差的水田轮式农机滑移参数实时估计方法，方法新颖且面向实际作业场景，但属细分技术论文，产业影响有限。",[338],{"name":332,"url":329},[26,27,340,341,342],"农业机械","水稻生产","导航定位",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[345],{"code":79,"slug":346,"name":347,"path":348,"parent_code":349},"machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","F",{"status":39,"locked":40,"version":41,"method":42,"evidence":351},{"candidates":352,"agricultural_evidence":14},[353,357,362],{"code":32,"score":17,"supported":14,"title":354,"abstract":355,"tags":356},[289],[34,48,289],[341],{"code":79,"score":257,"supported":14,"title":358,"abstract":360,"tags":361},[359],"agricultural machinery",[340,359],[340],{"code":51,"score":74,"supported":40,"title":363,"abstract":364,"tags":365},[],[],[26,27],[367,368],"水田 农业机械 滑移率 实时估计","预测残差 滑转参数 估计","水田农业机械滑移率实时估计-3974","10.1016\u002Fj.compag.2026.112478",{"doi":370,"openalex_id":372,"authors":373,"venue":332,"cited_by_count":106,"oa_url":9,"card":397,"direction":111,"ingested_from":114},"W7215087308",[374,377,380,382,384,386,389,391,394],{"name":375,"orcid":376},"Dawen Feng","https:\u002F\u002Forcid.org\u002F0000-0002-1307-8902",{"name":378,"orcid":379},"Boyang Wang","https:\u002F\u002Forcid.org\u002F0000-0003-3613-8792",{"name":381,"orcid":9},"Jing He",{"name":383,"orcid":9},"Yuqi Chen",{"name":385,"orcid":9},"Zhongxian Man",{"name":387,"orcid":388},"Jie He","https:\u002F\u002Forcid.org\u002F0000-0003-2134-0998",{"name":390,"orcid":9},"Zhaodi Liu",{"name":392,"orcid":393},"Gaolong Chen","https:\u002F\u002Forcid.org\u002F0000-0002-7415-0867",{"name":395,"orcid":396},"Lian Hu","https:\u002F\u002Forcid.org\u002F0000-0002-4875-7868",{"tldr":398,"method":399,"finding":400,"direction":111,"opportunity":401},"提出基于预测-残差法的轮式农机水田滑移参数实时估计方法。","预测-残差法，结合农机运动学模型与实时传感数据估计滑移参数。","该方法能在水田复杂环境下实时准确估计农机滑移参数。","可探索多源传感融合与深度学习提升水田滑移估计鲁棒性，并迁移至其他松软地面农机。","2026-10-02T23:30:02.471920Z",{"id":404,"title":405,"url":406,"summary":407,"summary_zh":9,"content":408,"source_name":409,"source_url":9,"published_at":410,"category":126,"cover_url":9,"hotness":13,"is_selected":40,"score":411,"score_detail":412,"sources":414,"tags":416,"primary_topic":418,"secondary_topics":419,"classification":420,"search_phrases":449,"slug":452,"view_count":21,"doi":9,"paper":9,"created_at":453},3101,"AI 接管稻田：四川眉山永丰村 300 亩 AI 试点水稻亩产 826.8-863.6 公斤","https:\u002F\u002Fai-damn.com\u002Fai-takes-over-the-rice-fields-863-6-kg-per-mu-in-sichuan-pilot-1789513373662","9-14 四川省眉山市东坡区太和镇永丰村千亩高标准农田 300 亩 AI 试点田通过专家组测产验收：\"华浙优 210\"（高产优质杂交稻）亩产 826.8 公斤、\"胜两优 222\"（超高产籼粳杂交稻）亩产 863.6 公斤、\"全优 169\"（超高产杂交籼稻）亩产 858.8 公斤。AI 系统通过无人机巡检采集数据，对种植、水肥调控和病虫害早期预警提供精准建议。四川农业大学水稻栽培专家马均教授表示，结合良种、良法与 AI 精准管理可有效释放水稻增产潜力，为大规模单产提升提供可复制技术路径；今年永丰村共有 240 余个新品种在产量\u002F株型\u002F米质上表现良好，智能精准播种技术与 AI 应用已初步见效。","## AI Takes Over the Rice Fields: 863.6 kg per Mu in Sichuan Pilot\n\nIn the rolling fields of Yongfeng Village, Tahe Town, Dongpo District, Meishan City, Sichuan Province, something unusual happened this harvest season. On September 14, as combines rolled through the thousand-mu high-standard farmland, 300 mu of it had been managed not by traditional farming wisdom alone, but by an **AI model** specifically designed for rice cultivation.\n\nGone are the days of \"judging fields by experience.\" Now, it's all about **making decisions based on data**.\n\n### From Experience to Data\n\nThe embankments were crowded with agricultural experts and curious farmers, all gathered to witness a field test. An expert group organized by the Sichuan Provincial Science and Technology Department was evaluating a project led by Sichuan Agricultural University: the \"Integrated Demonstration and Application of High-quality, High-yield, and Efficient Production Technologies for Rice-Vegetable (Medicinal) Crops in the Chengdu Plain.\"\n\nSo how does it work? The AI system collects data through **drone inspections**, then provides precise recommendations on planting, water and fertilizer regulation, and pest and disease early warning.\n\nLocal large-scale grain farmer Zhao Youyong put it simply: \"Before, farming relied on experience for field inspections. Now, using drones and the AI system, we get timely information about pests and diseases, so we can handle them directly. Farming has become more convenient.\"\n\n### The Numbers That Matter\n\nThe expert group's standardized yield test delivered solid results. All three core varieties in the 300-mu AI pilot fields performed impressively:\n\n*   **\"Huazheyous 210\"** (high-yield, high-quality hybrid rice): 826.8 kg per mu\n*   **\"Shengliangyou 222\"** (super-high-yield indica-japonica hybrid rice): **863.6 kg per mu**\n*   **\"Quanyou 169\"** (super-high-yield hybrid indica rice): 858.8 kg per mu\n\nMa Jun, a rice cultivation expert at Sichuan Agricultural University, explained that these yields prove that combining quality seeds with appropriate methods and AI precision management can **effectively release the potential for rice yield increase**. It offers a replicable technical path for large-scale yield improvement.\n\nHe also noted that more than 240 new varieties demonstrated good performance in yield, plant shape, and rice quality in Yongfeng Village this year. The application of intelligent precision sowing technology and AI has already shown initial results.\n\n### What This Means for the Future\n\nThis pilot isn't just about one good harvest. It's a glimpse into how **AI can transform traditional agriculture**. By moving from experience-based to data-driven farming, growers can make more informed decisions, reduce risks, and potentially achieve higher yields sustainably.\n\nAs Ma Jun pointed out, the combination of quality seeds, appropriate methods, and AI precision management provides a technical path that can be replicated on a larger scale. For a country that feeds 20% of the world's population with less than 10% of its arable land, such innovations are more than welcome—they're essential.\n\n### Key Points\n\n*   **AI-managed pilot field** in Sichuan achieved rice yields up to **863.6 kg per mu**.\n*   **Drones and data** replaced traditional experience-based farming for planting, fertilization, and pest control.\n*   **Three rice varieties** all exceeded 826 kg per mu, proving the effectiveness of AI precision management.\n*   **Experts say** this approach offers a replicable path for large-scale yield improvement.\n*   **The future of farming** is shifting from \"judging fields by experience\" to \"making decisions based on data.\"","AI DAMN","2026-09-14T10:00:00Z",76,{"impact":18,"substance":18,"depth":130,"authority":20,"freshness":59,"relevant":21,"comment":413},"AI精准管理水稻试点实测亩产数据具体、多方信源，具备可复制的智慧农业示范价值，值得入选每日精选。",[415],{"name":409,"url":406},[26,136,34,27,417],"无人機巡田",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":40,"version":41,"method":42,"evidence":421},{"candidates":422,"agricultural_evidence":14},[423,429,435,441,445],{"code":32,"score":424,"supported":14,"title":425,"abstract":426,"tags":428},23,[34,48],[34,427],"杂交稻",[34],{"code":430,"score":150,"supported":14,"title":431,"abstract":432,"tags":434},"A8",[],[433],"单产提升",[],{"code":436,"score":150,"supported":14,"title":437,"abstract":438,"tags":440},"H1",[],[439],"高标准农田",[],{"code":51,"score":74,"supported":40,"title":442,"abstract":443,"tags":444},[],[],[26,27],{"code":170,"score":21,"supported":40,"title":446,"abstract":447,"tags":448},[],[],[136],[450,451],"四川眉山 永丰村 AI水稻","四川农业大学 水稻 AI试点","四川眉山永丰村AI水稻-3101","2026-09-22T00:05:33.996455Z",{"id":455,"title":456,"url":457,"summary":458,"summary_zh":459,"content":9,"source_name":460,"source_url":457,"published_at":461,"category":12,"cover_url":9,"hotness":13,"is_selected":40,"score":411,"score_detail":462,"sources":464,"tags":466,"primary_topic":468,"secondary_topics":469,"classification":474,"search_phrases":495,"slug":498,"view_count":21,"doi":499,"paper":500,"created_at":534},2512,"Deep learning-based classification of wet direct seeded rice, broadcasted direct seeded rice and transplanted rice using drone imagery for precision agriculture","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1698781","Accurate estimation of crop area using classification techniques applied to drone imagery plays an important role in precision agriculture. Traditional machine learning (ML) approaches have been widely used for agricultural image classification; however, advanced deep learning (DL) models generally provide superior feature extraction and classification capability for complex crop patterns. Differentiating various rice establishment methods is essential for precise area estimation. In this study, advanced deep learning models were employed to classify three types of rice cultivation: (i) Broadcasted Direct Seeded Rice (DSR), (ii) Wet Direct Seeded Rice (Wet DSR), and (iii) Transplanted Rice (TR) using drone imagery. The drone imagery was collected from an experimental field at Praanadhaara Organised Agro Forestry Private Limited, Bapatla District, Andhra Pradesh, India. The images were captured in the visible spectrum (Red, Green, and Blue bands) on three dates, viz., 15 October 2023, 27 October 2023, and 01 December 2023, from an altitude of 40 m and were used to train and test classification models. Classification was performed using six ResNet-50 based hybrid models, namely, ResNet-50+K-Nearest Neighbor (ResNet-50+KNN), ResNet-50+Support Vector Machine (ResNet-50+SVM), ResNet-50+Decision Trees (ResNet-50+DT), ResNet-50+Random Forest (ResNet-50+RF), ResNet-50+Naïve Bayes (ResNet-50+NB), and ResNet-50+Neural Network (ResNet-50+NN), along with two additional DL architectures, namely, You Only Look Once version 5 (YOLOv5) and You Only Look Once version 8 (YOLOv8). Model performance was evaluated using overall accuracy (OA), precision (P), recall (R), kappa coefficient (K), F1-score (F1), and mean Average Precision (mAP). Among the tested classifiers, the ResNet-50+NN model consistently achieved the highest average overall accuracies of 93.16%, 95.81%, and 93.31% at T 1 , T 2 , and T 3 , respectively, outperforming all other models, whose accuracies ranged from 78.05% to 92.07%, 86.11%–95.24%, and 77.47%–92.09% across the respective time intervals. The ResNet-50+NN model also recorded the highest precision (0.93–0.97), recall (0.92–0.97), F1-score (0.92–0.97), and kappa coefficient (0.89–0.96), demonstrating superior and consistent classification performance across all observation dates. The methodology developed in this work enables precise identification of rice establishment methods, improving crop mapping and monitoring. This identification enhances resource efficiency, optimizes input use, and supports site-specific management, contributing to sustainable precision agriculture.","利用分类技术对无人机影像进行作物面积精确估算，在精准农业中发挥着重要作用。传统机器学习（ML）方法已广泛用于农业图像分类；然而，先进的深度学习（DL）模型通常对复杂作物模式具有更优越的特征提取和分类能力。区分不同的水稻种植方式对于精确估算面积至关重要。本研究采用先进的深度学习模型，利用无人机影像对三种水稻种植类型进行分类：（i）撒播直播稻（DSR），（ii）湿润直播稻（Wet DSR），以及（iii）移栽稻（TR）。无人机影像采集自印度安得拉邦巴帕特拉县Praanadhaara Organised Agro Forestry Private Limited的试验田。图像在可见光谱（红、绿、蓝波段）下于三个日期拍摄，即2023年10月15日、2023年10月27日和2023年12月1日，飞行高度为40 m，用于训练和测试分类模型。分类采用六种基于ResNet-50的混合模型，即ResNet-50+K近邻（ResNet-50+KNN）、ResNet-50+支持向量机（ResNet-50+SVM）、ResNet-50+决策树（ResNet-50+DT）、ResNet-50+随机森林（ResNet-50+RF）、ResNet-50+朴素贝叶斯（ResNet-50+NB）和ResNet-50+神经网络（ResNet-50+NN），以及两种额外的深度学习架构，即You Only Look Once第5版（YOLOv5）和You Only Look Once第8版（YOLOv8）。采用总体精度（OA）、精确率（P）、召回率（R）、Kappa系数（K）、F1分数（F1）和平均精度均值（mAP）评估模型性能。在测试的分类器中，ResNet-50+NN模型在T₁、T₂和T₃分别持续取得最高的平均总体精度，为93.16%、95.81%和93.31%，优于所有其他模型，后者的精度在相应时间段分别为78.05%–92.07%、86.11%–95.24%和77.47%–92.09%。ResNet-50+NN模型还记录了最高的精确率（0.93–0.97）、召回率（0.92–0.97）、F1分数（0.92–0.97）和Kappa系数（0.89–0.96），在所有观测日期均表现出优越且稳定的分类性能。本研究开发的方法能够精确识别水稻种植方式，改进作物制图和监测。这种识别增强了资源","Frontiers in Remote Sensing","2026-09-14T00:00:00Z",{"impact":335,"substance":189,"depth":130,"authority":190,"freshness":20,"relevant":21,"comment":463},"基于无人机可见光影像与ResNet-50混合模型区分三类水稻种植方式，方法对比系统、精度数据扎实，对精准农业作物制图有参考价值，但属细分技术进展，影响范围有限。",[465],{"name":460,"url":457},[26,136,34,27,467],"遥感",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[470],{"code":170,"slug":471,"name":472,"path":473,"parent_code":272},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":39,"locked":40,"version":41,"method":42,"evidence":475},{"candidates":476,"agricultural_evidence":14},[477,483,487,491],{"code":170,"score":17,"supported":14,"title":478,"abstract":480,"tags":482},[479],"deep learning",[481,213,214,479],"深度学习",[136],{"code":51,"score":335,"supported":14,"title":484,"abstract":485,"tags":486},[55],[27,55],[26,27],{"code":32,"score":257,"supported":14,"title":488,"abstract":489,"tags":490},[33],[34,33],[34],{"code":217,"score":21,"supported":40,"title":492,"abstract":493,"tags":494},[],[],[467],[496,497],"农业人工智能 智慧农业 精准农业 水稻","农业人工智能 智慧农业","农业人工智能智慧农业精准农业水稻-2512","10.3389\u002Ffrsen.2026.1698781",{"doi":499,"openalex_id":501,"authors":502,"venue":460,"cited_by_count":106,"oa_url":528,"card":529,"direction":111,"ingested_from":114},"W7212834743",[503,505,507,509,511,514,516,518,520,523,525],{"name":504,"orcid":9},"Amrutha Lakshmi Gubbala",{"name":506,"orcid":9},"Santosha Rathod",{"name":508,"orcid":9},"Ramesh Dasyam",{"name":510,"orcid":9},"Mahender Kumar Rapolu",{"name":512,"orcid":513},"Arun Kumar Dasari","https:\u002F\u002Forcid.org\u002F0000-0001-7398-8601",{"name":515,"orcid":9},"Pundarikakshudu Kurra",{"name":517,"orcid":9},"Hanuma Raviteja Madireddy",{"name":519,"orcid":9},"Prajwal R. Shashishekhar",{"name":521,"orcid":522},"Ravi V. Mural","https:\u002F\u002Forcid.org\u002F0000-0002-5489-9918",{"name":524,"orcid":9},"Anil Kumar",{"name":526,"orcid":527},"R. M. Sundaram","https:\u002F\u002Forcid.org\u002F0000-0002-9857-8251","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1698781\u002Fpdf",{"tldr":530,"method":531,"finding":532,"direction":242,"opportunity":533},"用无人机可见光影像和深度学习模型区分直播稻、湿直播稻与移栽稻三种水稻种植方式。","无人机RGB影像三个时相，比较ResNet-50混合模型与YOLOv5\u002Fv8分类","ResNet-50+NN表现最优，三期总体精度达93.16%、95.81%、93.31%，优于其他模","可扩展到多光谱\u002F多时相与更大区域验证，并用于种植方式制图与面积精准估算。","2026-09-15T23:30:08.600535Z"]