[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4":3,"related-4":86},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":36,"classification":37,"search_phrases":80,"slug":83,"view_count":84,"doi":8,"paper":8,"created_at":85},4,"智慧农业玩转\"算法\"，3700 亩示范区收获\"吨粮田\"丨万千气象看四川","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7662045800490385972\u002F","报道成都市新都区军屯镇天星村 3700 亩智慧农业中试基地最新进展。基地由四川省农科院作物所朱从桦博士团队主导，与新都区\"天府粮仓精品区\"建设协同推进；2023 年起通过 3700 亩土地小田变大田、北斗导航 + 5G 信号进田、80 多个摄像头与五六百个传感器部署，实现耕种管收\"一条龙\"无人化。2025 年水稻亩产达 630 公斤、小麦 501 公斤，全面达成成都农人向往的\"吨粮田\"目标。在 600 亩核心区，全链条降本增效叠加：大春、小春每亩收益超过 2000 元，每亩综合用工减少 0.8 个、节约成本近 100 元，无人驾驶路径规划节约燃油约 5%，\"四情\"（苗情、虫情、墒情、灾情）监测累计杀虫 60 万头，节约农药化肥投入约 10%。",null,"川观新闻记者 张红霞\n\n7月13日，气温升到39℃，高温的考验扑面而来。成都市新都区军屯智慧农业中试基地的翠绿稻田，带给“万千气象看四川”采访团一片清凉。\n\n高温炙烤，这片智慧农田如何应对？四川省农业科学院作物研究所博士朱从桦告诉我们他的方案——耐高温水稻品种、智慧感知精准补水、延迟收割，“设计的最高温度是60°C。万一遇到持续高温，也能实现稳产。”这片3700亩试验田，2025年全面达产，水稻亩产达630公斤、小麦产量达501公斤，顺利达标成都农人向往的亩产“吨粮田”。\n\n耕种管收一条龙“无人化”，从2023年起，这个备受注目的智慧试验田，用扎实的田间数据、一降一升的效益叠加，展示农业“智改数转”也有广阔空间。\n\n**一降：农业全链条降本，红利有多少？**\n\n“当时我来这里的时候，田块很碎，产出很低，农业还是传统搞法。”2022年春末夏初，朱从桦受邀来到军屯镇天星村，其时国内正兴起智慧农业热，多位院士领衔探路。新都区也提出要建设“天府粮仓精品区”，发展高品质粮油基地。\n\n双方一拍即合。3700亩土地流转、集中，小田变大田、田埂裁弯取直，北斗导航下的5G信号送进田野，80多个摄像头、五六百个传感器随之进入——2023年大春季，朱从桦与团队在这片土地重启新章。天星村党总支书记钟盛刚是位实干者，紧密配合他的步伐。\n\n![Image 1](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-axegupay5k\u002Fe5fbf480993447c9adb94b250136e680~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1789107757&x-signature=c2NaZsjXz47HqUMg5BgA%2FnmZYzE%3D)\n2023年，新都区发展智慧农业，在军屯镇建起3700亩示范区。\n\n丰收农机专合社机手巫金波率先改造了他的农机，变身“无人驾驶”。“我有7台农机具做了智能化改装，省人省时省钱，尤其是插秧机，让我非常满意。”新都区昌平农机作业专合社负责人陈稻松说。\n\n以600亩核心区作为支点，朱从桦边干边算账——智慧农业能不能跑通，得用实实在在的效益说话。\n\n账算得很细，全链条显出综合效益：在插秧环节，一台插秧机少用了一个工，多干了3小时。每亩综合用工减少0.8个，节约成本近100元。无人驾驶设备会规划最合理路线，可节约燃油约5%。搭建苗情、虫情、墒情、灾情“四情”监测平台，累计杀虫60万头，可节约农药化肥的投入约10%。田间水管的成本从每亩80元降到30元。\n\n“在600亩核心区，大、小春加总，每亩收益可以超过2000元。在3100亩示范区，每亩收益在500—600元之间。”朱从桦认为，这套智慧农业系统还有改进空间，“我们才去了上海嘉定外港无人农场考察，准备下一步打通农机、无人机间的数据互通。”\n\n**一升：地力上升，品质大米卖出优价**\n\n采访间，一杯米茶端至面前，那是核心区内的龙头企业——四川流航农业有限公司（下称“流航农业”）开发的新产品。2023年初，流航农业听说新都将打造智慧农场，便把种植基地迁到了天星村。\n\n跟随省农科院的步伐，流航农业投入数百万元，建160亩优质大米种植基地。改土改水、机械耕种，不用农药和化肥，全力打造“72道锁鲜”技术的“一碗鲜米”品牌，每斤售价21元，通过电商发展会员。\n\n三年来，流航农业发展了600亩种植基地，其中300亩土壤全面变好，“可以又看到蚯蚓了”，企业负责人罗阳萍说。流航农业布局了高、中、低端大米品牌，使得整体大米均价每斤超过了10元。\n\n![Image 2](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002Fa3a497faf2ec56bdf6638857f70e0b5b~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1789107757&x-signature=gpykL5Clsc9rbjdxnGXT3zdftGw%3D)\n流航农业使用无人机执行植保任务。\n\n智慧农业的好处，从种植端传递到消费端，得到了市场验证。这让朱从桦、罗阳萍都看到了希望。\n\n不仅地力升了，在四至边界不变的情况下，核心区的种植面积也悄悄增加了。\n\n据中国工程院院士罗锡文团队实地测算，在北斗导航系统助力下，无人农机的作业行走偏差始终保持在2.5厘米内。与人工驾驶相比，可以因此提高土地利用率2%，仅600亩核心区就新增12亩耕地，核心区年增产水稻\u002F小麦约13.2吨。\n\n“智慧农场的任务是做好示范。下一步，还要在降低成本、增加效益上下大功夫。只有农民投入智能农机算得过来账，农业‘智改数转’才真正有生命。”朱从桦说。\n\n受访者供图","《川观新闻》2026 年 07 月 14 日 00:11","2026-07-13T16:11:00Z","报道",10,false,66,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},18,20,16,2,1,"报道四川新都3700亩智慧农业示范区实现吨粮田，详述降本增效与地力提升，数据扎实，具省级示范意义。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","无人农场","北斗导航","四川","降本增效",{"code":32,"slug":33,"name":34,"path":35,"parent_code":8},"A","field-crops","大田作物","\u002Ftopic\u002Ffield-crops",[],{"status":38,"locked":14,"version":39,"method":40,"evidence":41},"partial","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":46,"reason":79},[43,50,57,63,69,74],{"code":44,"score":45,"supported":46,"title":47,"abstract":48,"tags":49},"I1",12,true,[26],[26],[26],{"code":51,"score":52,"supported":46,"title":53,"abstract":54,"tags":56},"A1",3,[],[55],"水稻",[],{"code":58,"score":52,"supported":46,"title":59,"abstract":60,"tags":62},"A2",[],[61],"小麦",[],{"code":64,"score":52,"supported":46,"title":65,"abstract":66,"tags":68},"F4",[],[67],"农药",[],{"code":70,"score":21,"supported":14,"title":71,"abstract":72,"tags":73},"F5",[],[],[28],{"code":75,"score":21,"supported":14,"title":76,"abstract":77,"tags":78},"F6",[],[],[27],"一级领域明确，二级方向需要细分",[81,82],"北斗导航 无人农场 智慧农业 降本增效","北斗导航 无人农场","北斗导航无人农场智慧农业降本增效-4",9,"2026-07-27T05:05:18.547604Z",{"total":87,"page":21,"page_size":87,"items":88},6,[89,155,220,354,429,494],{"id":90,"title":91,"url":92,"summary":93,"summary_zh":8,"content":94,"source_name":95,"source_url":8,"published_at":96,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":97,"score_detail":98,"sources":101,"tags":103,"primary_topic":108,"secondary_topics":109,"classification":110,"search_phrases":150,"slug":153,"view_count":45,"doi":8,"paper":8,"created_at":154},65,"让\"数字\"说话 用\"智能\"种养——黑龙江绥化\u002F大庆\u002F黑河智慧农业新实践综述","https:\u002F\u002Fnew.qq.com\u002Frain\u002Fa\u002F20260728A037D600","2026-07-28 黑龙江日报记者实地走访绥化、大庆、黑河3市，呈现全省\"智慧+\"实践：绥化市按\"1+2+3+10\"体系建成32个智慧农（牧、渔）场，北林区落地国家级\"北斗+智慧农业\"试点支撑玉米大面积单产提升；全市率先启动AI激光除草机器人试验示范，6县（市、区）6000余亩有机鲜食玉米、有机黑豆田应用；肇东市五里明农场无膜浅埋滴灌水肥一体化技术节水30%、节肥23%；\"农业托管智慧链平台\"入选国家数据局首批50个数字中国建设典型案例，1800多万亩托管土地接入系统。大庆林甸县全省唯一县级奶牛数字化管理平台已投用，17处规模牧场5.9万头奶牛佩戴智能耳标，发情、产奶、采食、健康状况实时回传。","来到佳木斯抚远市乌苏现代农业产业园，走进8万平方米的智能温室，眼前景象与窗外的东北原野恍如两个世界。荷兰进口的豪根道智能中控系统实时监测温度、湿度、光照、二氧化碳浓度等数十项数据，自动调控天窗、幕布、灌溉。立体吊架无土栽培系统让空间利用率最大化，水肥一体化循环系统节水率高达95%。\n\n产业园负责人告诉记者，这里产出的每一颗番茄都可保证零农残、零激素、零转基因，物理与生物双重绿色防控体系代替了化学农药。“我们不是靠天吃饭，是靠数据种地。”在自动化分选包装线上，除了人工采摘，分选、质检、称重、贴标、码垛全部由机器完成，日包装产能10吨，产品全部符合全球良好农业规范。这个项目总投资3.53亿元，旨在打造智能化、数字化、集约化、绿色化的智慧设施农业标杆。\n\n在黑河市爱辉区西岗子镇盘肠沟寒地小龙虾养殖基地，物联网智慧管控同样让人眼前一亮。21口池塘全部布设水质传感器、自动增氧设备和远程投料终端，水体溶氧低于5毫克\u002F升自动开启增氧，高于7毫克\u002F升自动关停。这套系统让饵料损耗下降30%，用电节约30%以上，小龙虾生长速度提升5%~10%，100亩水面每年节省生产成本4万余元。\n\n黑河市农业农村局相关负责人介绍，基地通过菌藻共生生态养殖和智能化育苗攻关，攻克了寒地虾苗越冬难题。今年全市小龙虾养殖面积发展到1091亩，投放虾苗1000万尾，盘肠沟基地年产商品虾20吨，已签订10吨订单销往北京等高端市场。在黑河，冷水鱼精深加工也有了突破——总投资1亿元的浔然谷冷水鱼加工厂正在瑷珲对俄进出口加工基地建设，投产后每年可加工冷水鱼2000吨。","黑龙江日报 · 2026-07-28","2026-07-28T00:00:00Z",72,{"impact":17,"substance":18,"depth":99,"authority":13,"freshness":84,"relevant":21,"comment":100},15,"省级智慧农业综合报道，含具体数据与案例，时效性好，但深度稍欠。",[102],{"name":95,"url":92},[12,26,28,104,105,106,107],"黑龙江","AI激光除草","数字中国","奶牛数字化",{"code":32,"slug":33,"name":34,"path":35,"parent_code":8},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":111},{"candidates":112,"agricultural_evidence":46,"reason":79},[113,117,123,129,135,141,146],{"code":44,"score":45,"supported":46,"title":114,"abstract":115,"tags":116},[26],[26],[26],{"code":118,"score":52,"supported":46,"title":119,"abstract":120,"tags":122},"A3",[],[121],"玉米",[],{"code":124,"score":52,"supported":46,"title":125,"abstract":126,"tags":128},"A8",[],[127],"单产提升",[],{"code":130,"score":52,"supported":46,"title":131,"abstract":132,"tags":134},"C2",[],[133],"奶牛",[],{"code":136,"score":52,"supported":46,"title":137,"abstract":138,"tags":140},"F3",[],[139],"水肥一体化",[],{"code":64,"score":52,"supported":46,"title":142,"abstract":143,"tags":145},[],[144],"除草",[],{"code":70,"score":21,"supported":14,"title":147,"abstract":148,"tags":149},[],[],[28],[151,152],"奶牛数字化 AI激光除草 北斗导航 数字中国","奶牛数字化 AI激光除草","奶牛数字化AI激光除草北斗导航数字中国-65","2026-07-29T23:54:12.405931Z",{"id":156,"title":157,"url":158,"summary":159,"summary_zh":160,"content":8,"source_name":161,"source_url":158,"published_at":162,"category":163,"cover_url":8,"hotness":13,"is_selected":14,"score":90,"score_detail":164,"sources":168,"tags":170,"primary_topic":175,"secondary_topics":176,"classification":177,"search_phrases":199,"slug":202,"view_count":203,"doi":204,"paper":205,"created_at":219},5404,"Validation of a Day-of-Year Standardized Canopy Indicator for Regional Crop Monitoring: Suitability and Decoupling Boundaries","https:\u002F\u002Fdoi.org\u002F10.20944\u002Fpreprints202610.1707.v1","Translating satellite-derived crop canopy anomalies into regional production signals is critical for agricultural monitoring. However, standard anomaly indicators assume a stable, direct coupling between greenness and production, ignoring phenological shifts, sub-seasonal cropping dynamics, and harvested acreage fluctuations. I evaluate the validation boundaries and expected conditions of a pixel-level, day-of-year (DOY)-first Leaf Area Index (LAI) Z-score anomaly indicator with a leave- year-out baseline (2003–2022) across five contrasting global breadbaskets: Australia, Indo-Gangetic Plains (IGP), North China Plain (NCP), US Corn Belt, and Ukraine. The analysis shows that DOY- first standardization reduces temporal composite timing mismatches, though coupling with regional statistics varies systematically. Retrospective validation reveals that direct canopy-yield coupling remains robust exclusively in rainfed Australia (Pearson’s r = 0.90), where yield variability dominates production variance (explaining 90% of variance) and moisture stress limits canopy development. In contrast, three interpretation boundaries are identified: (1) greening trend-sensitivity in the IGP, where detrending reduces the association to r = 0.53; (2) temporal representativeness bias in the double-cropped NCP, requiring crop-calendar windowing to recover the wheat signal (r = 0.51); and (3) area-shock-sensitivity in Ukraine (where harvested area contractions explain 78% of production variance), decoupling canopy vigor from production (r = 0.40). Furthermore, the LAI Z-score provides a more interpretable canopy-response measure than the Vegetation Condition Index (VCI) in dense canopies where NDVI saturates. These validation levels are synthesized into a prototype diagnostic decision framework to support indicator configuration in operational monitoring systems.","将卫星反演的作物冠层异常转化为区域产量信号对农业监测至关重要。然而，标准异常指标假定绿度与产量之间存在稳定、直接的耦合关系，忽略了物候偏移、次季节作物动态以及收获面积波动。我评估了一种像元级、以年积日（DOY）为首要标准化维度的叶面积指数（LAI）Z分数异常指标在五个对比鲜明的全球粮仓——澳大利亚、印度河-恒河平原（IGP）、华北平原（NCP）、美国玉米带和乌克兰——的验证边界与预期适用条件，该指标采用留一年基线（2003—2022年）。分析表明，以DOY为首要标准化维度可减少时间合成时相不匹配，但其与区域统计数据的耦合关系存在系统性差异。回顾性验证显示，冠层与产量的直接耦合仅在雨养条件下的澳大利亚保持稳健（Pearson's r = 0.90），该地区产量变异性主导产量方差（解释90%的方差），且水分胁迫限制冠层发育。相比之下，识别出三个解释边界：（1）IGP的绿度趋势敏感性，去趋势后关联性降至r = 0.53；（2）双季种植的NCP的时间代表性偏差，需按作物日历开窗以恢复小麦信号（r = 0.51）；（3）乌克兰的面积冲击敏感性（收获面积缩减解释78%的产量方差），导致冠层活力与产量解耦（r = 0.40）。此外，在NDVI饱和的密集冠层中，LAI Z分数提供了比植被条件指数（VCI）更具可解释性的冠层响应度量。这些验证层级被综合为一个原型诊断决策框架，以支持业务化监测系统中的指标配置。","Preprints.org","2026-10-19T00:00:00Z","论文",{"impact":45,"substance":165,"depth":17,"authority":87,"freshness":166,"relevant":21,"comment":167},21,8,"预印本提出按年积日标准化的LAI异常指标，并在五大农业区验证其适用边界，方法有新意但尚未经同行评审，属细分领域进展。",[169],{"name":161,"url":158},[26,171,172,173,174],"遥感","作物监测","产量估测","叶面积指数",{"code":32,"slug":33,"name":34,"path":35,"parent_code":8},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":178},{"candidates":179,"agricultural_evidence":46,"reason":79},[180,185,190,195],{"code":58,"score":87,"supported":46,"title":181,"abstract":182,"tags":184},[],[61,183],"wheat",[],{"code":118,"score":87,"supported":46,"title":186,"abstract":187,"tags":189},[],[121,188],"corn",[],{"code":191,"score":52,"supported":14,"title":192,"abstract":193,"tags":194},"I3",[],[],[173,172,174,171],{"code":44,"score":21,"supported":14,"title":196,"abstract":197,"tags":198},[],[],[26],[200,201],"LAI Z-score 作物监测","遥感 作物产量 估测","LAIZ-score作物监测-5404",0,"10.20944\u002Fpreprints202610.1707.v1",{"doi":204,"openalex_id":206,"authors":207,"venue":161,"cited_by_count":203,"oa_url":158,"card":211,"direction":217,"ingested_from":218},"W7222967882",[208],{"name":209,"orcid":210},"Xiaolong Song","https:\u002F\u002Forcid.org\u002F0000-0002-2106-6629",{"tldr":212,"method":213,"finding":214,"direction":215,"opportunity":216},"验证了按年积日标准化的LAI Z-score冠层指标在五大农业区的适用边界。","用2003–2022年留一年基线，在五个全球粮仓区做LAI DOY标准化与产量相","仅雨养澳大利亚冠层-产量强耦合(r=0.90)，其余区域受趋势、物候和面积冲击影响而解耦。","农业遥感与作物表型","可发展融合物候窗口、去趋势与收获面积因子的分区自适应冠层异常指标诊断框架。","农业人工智能与决策模型","openalex","2026-10-20T23:30:40.675672Z",{"id":221,"title":222,"url":223,"summary":224,"summary_zh":225,"content":8,"source_name":226,"source_url":223,"published_at":227,"category":163,"cover_url":8,"hotness":13,"is_selected":14,"score":228,"score_detail":229,"sources":233,"tags":235,"primary_topic":240,"secondary_topics":241,"classification":242,"search_phrases":292,"slug":295,"view_count":203,"doi":296,"paper":297,"created_at":353},5314,"A data‐driven image extraction and analysis pipeline for plant phenotyping in controlled environments","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fppj2.70116","Abstract Advances in automation, imaging, and artificial intelligence have enabled large‐scale plant phenotyping, but image analysis remains a critical bottleneck for crop improvement and biological discovery. We developed an integrated multispectral phenotyping framework using imagery from the Texas A&M AgriLife Automated Precision Phenotyping Greenhouse and expanded plant growth and phenotyping (PGP v2) data across maize ( Zea mays L.), cotton ( Gossypium hirsutum ), rice ( Oryza sativa ), and sorghum ( Sorghum bicolor L.). The pipeline integrates pseudo‐red‐green‐blue composite image generation, plant detection and segmentation, image stitching, vegetation‐index analysis, texture analysis, morphological trait extraction, and temporal comparison of image‐derived features to quantify changes in plant structure, spectral reflectance, and texture over time. Among the evaluated segmentation approaches, segment anything model (SAM) v3 provided the highest and most consistent accuracy across diverse crop structures, although it required greater computational time than classical methods. Segment anything model for long sequences (SAM2Long)maintained plant‐instance associations across vertically stacked frames, while scale‐invariant feature transform–based stitching reconstructed plant mosaics when individual plants extended beyond a single field of view. For each plant and imaging date, the pipeline generated an 863‐dimensional feature vector spanning vegetation indices, spectral statistics, texture descriptors, and morphological traits. The framework was evaluated through two case studies: treatment‐level temporal analysis of mutagenized sorghum lines and cold‐stress phenotyping of maize using a separate imaging system. In both studies, the extracted features supported statistical and multivariate analyses of phenotypic variation and enabled separation of plants based on treatment‐ or stress‐related responses. The combined dataset and workflow provide structured, automated, and well‐documented phenotypic analysis across multiple crops, experimental settings, and imaging systems for controlled‐environment plant science and crop improvement.","摘要　自动化、成像和人工智能的进步使得大规模植物表型分析成为可能，但图像分析仍然是作物改良和生物学发现的关键瓶颈。我们利用德克萨斯农工大学农业生命科学自动化精准表型温室（Texas A&M AgriLife Automated Precision Phenotyping Greenhouse）的图像，开发了一个集成多光谱表型分析框架，并扩展了玉米（Zea mays L.）、棉花（Gossypium hirsutum）、水稻（Oryza sativa）和高粱（Sorghum bicolor L.）的植物生长与表型分析（plant growth and phenotyping，PGP v2）数据。该流程整合了伪红绿蓝合成图像生成、植物检测与分割、图像拼接、植被指数分析、纹理分析、形态性状提取以及图像衍生特征的时间比较，以量化植物结构、光谱反射率和纹理随时间的变化。在评估的分割方法中，segment anything model（SAM）v3在不同作物结构下提供了最高且最一致的准确性，尽管其所需计算时间多于经典方法。面向长序列的segment anything model（SAM2Long）在垂直堆叠帧之间维持了植物实例关联，而基于尺度不变特征变换（scale-invariant feature transform）的拼接在单株植物超出单一视野时重建了植物拼接图。对于每株植物和每个成像日期，该流程生成了一个863维特征向量，涵盖植被指数、光谱统计量、纹理描述符和形态性状。该框架通过两个案例研究进行了评估：诱变高粱品系的处理水平时间分析，以及使用独立成像系统对玉米进行的冷胁迫表型分析。在这两项研究中，提取的特征支持了表型变异的统计分析和多变量分析，并能够根据处理或胁迫相关响应区分植物。合并的数据集和工作流程为受控环境植物科学和作物改良提供了跨多种作物、实验设置和成像系统的结构化、自动化且记录完善的表型分析。","The Plant Phenome Journal","2026-10-18T00:00:00Z",81,{"impact":17,"substance":230,"depth":17,"authority":231,"freshness":84,"relevant":21,"comment":232},22,14,"该研究提出一套面向多作物的自动化多光谱表型分析流程，方法新颖、数据规模可观，对智慧育种与受控环境植物科学研究具有较高参考价值。",[234],{"name":226,"url":223},[26,236,237,238,239],"农业人工智能","图像分割","表型组学","多光谱成像",{"code":32,"slug":33,"name":34,"path":35,"parent_code":8},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":243},{"candidates":244,"agricultural_evidence":46,"reason":79},[245,250,255,262,269,276,283,288],{"code":51,"score":87,"supported":46,"title":246,"abstract":247,"tags":249},[],[55,248],"rice",[],{"code":118,"score":87,"supported":46,"title":251,"abstract":252,"tags":254},[],[121,253],"maize",[],{"code":256,"score":87,"supported":46,"title":257,"abstract":258,"tags":261},"A5",[],[259,260],"高粱","sorghum",[],{"code":263,"score":87,"supported":46,"title":264,"abstract":265,"tags":268},"A6",[],[266,267],"棉花","cotton",[],{"code":270,"score":87,"supported":46,"title":271,"abstract":272,"tags":275},"B7",[],[273,274],"温室","greenhouse",[],{"code":277,"score":278,"supported":46,"title":279,"abstract":280,"tags":282},"I2",5,[],[281],"artificial intelligence",[236,237],{"code":191,"score":4,"supported":46,"title":284,"abstract":285,"tags":287},[],[286],"multispectral",[239],{"code":44,"score":21,"supported":14,"title":289,"abstract":290,"tags":291},[],[],[26],[293,294],"Texas A&M 自动化表型温室","玉米 高粱 多光谱表型","TexasAM自动化表型温室-5314","10.1002\u002Fppj2.70116",{"doi":296,"openalex_id":298,"authors":299,"venue":226,"cited_by_count":203,"oa_url":223,"card":348,"direction":215,"ingested_from":218},"W7222893982",[300,302,305,308,311,313,315,318,321,324,327,330,333,336,339,342,344,346],{"name":301,"orcid":8},"Fahimeh Orvati Nia",{"name":303,"orcid":304},"Joshua Peeples","https:\u002F\u002Forcid.org\u002F0000-0001-7861-7789",{"name":306,"orcid":307},"Seth C. Murray","https:\u002F\u002Forcid.org\u002F0000-0002-2960-8226",{"name":309,"orcid":310},"Andrew J. McFarland","https:\u002F\u002Forcid.org\u002F0009-0000-3516-8274",{"name":312,"orcid":8},"Troy Vann",{"name":314,"orcid":8},"Shima Salehi",{"name":316,"orcid":317},"Robert G. Hardin","https:\u002F\u002Forcid.org\u002F0000-0002-0714-8281",{"name":319,"orcid":320},"David D. Baltensperger","https:\u002F\u002Forcid.org\u002F0000-0003-4511-5680",{"name":322,"orcid":323},"Amir M. H. Ibrahim","https:\u002F\u002Forcid.org\u002F0000-0002-0584-753X",{"name":325,"orcid":326},"J. Alex Thomasson","https:\u002F\u002Forcid.org\u002F0000-0002-5557-105X",{"name":328,"orcid":329},"Henry Y. Fadamiro","https:\u002F\u002Forcid.org\u002F0000-0002-4530-9680",{"name":331,"orcid":332},"Nithya K. Subramanian","https:\u002F\u002Forcid.org\u002F0000-0002-1659-7396",{"name":334,"orcid":335},"Suresh D. Pillai","https:\u002F\u002Forcid.org\u002F0000-0002-9766-8765",{"name":337,"orcid":338},"Rebecca Roston","https:\u002F\u002Forcid.org\u002F0000-0002-3063-5002",{"name":340,"orcid":341},"Joslin Ishimwe","https:\u002F\u002Forcid.org\u002F0009-0003-6999-7718",{"name":343,"orcid":8},"Diptadeep Basak",{"name":345,"orcid":8},"Nazar Oladepo",{"name":347,"orcid":8},"Uday Santhosh Raju Vysyaraju",{"tldr":349,"method":350,"finding":351,"direction":215,"opportunity":352},"构建多光谱图像提取分析流程，实现多作物表型自动化量化。","用温室多光谱图像，集成SAM v3分割、SIFT拼接与863维特征提取。","SAM v3分割最准，特征可区分高粱诱变与玉米冷胁迫响应。","可探索轻量化分割模型与跨成像系统迁移，降低计算成本并拓展田间表型。","2026-10-19T23:30:17.276726Z",{"id":355,"title":356,"url":357,"summary":358,"summary_zh":359,"content":8,"source_name":360,"source_url":357,"published_at":361,"category":163,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":362,"sources":365,"tags":367,"primary_topic":370,"secondary_topics":371,"classification":372,"search_phrases":404,"slug":407,"view_count":203,"doi":408,"paper":409,"created_at":428},4901,"Feature-level fusion of Sentinel-1 SAR and Sentinel-2 optical imagery for crop-type mapping in humid tropical mountainous terrain","https:\u002F\u002Fdoi.org\u002F10.64960\u002Feasr.2026.263460","Accurate crop-type mapping in humid tropical mountains is challenged by persistent cloud cover, rugged topography, and fragmented smallholder parcels. This study evaluates a feature-level fusion workflow that integrates Sentinel-2 optical indices and Sentinel-1 SAR backscatter for crop-type mapping in Candipuro District, Lumajang, East Java, Indonesia. Sentinel-2 surface reflectance and Sentinel-1 IW data acquired in June–July 2023 were harmonised in Google Earth Engine to a common 10 m pixel grid, so that all comparison maps were evaluated on the same spatial support. The optical component comprised NDVI, NDBI, and NDWI, whereas the radar component used the VH\u002FVV polarisation ratio. A DEM was used only to characterise the mountainous setting and to assist terrain interpretation, and was not included as a predictor in the classifier. The stacked feature image was classified using a Random Forest model trained with 101 field-survey ground control points representing eight land-cover\u002Fcrop-related classes. Accuracy was assessed using 393 stratified random validation points. The fused-image classification achieved an overall accuracy of 93% and a kappa coefficient of 0.90. The fusion workflow yielded richer thematic differentiation than the optical-only comparison scenarios, particularly for water bodies, sugarcane, and shrubland. However, class-level results reveal substantial uncertainty for corn fields and moderate confusion in built-up and water classes. Therefore, the present workflow should be interpreted as a site-specific, single-date proof of concept rather than a fully transferable operational solution. The results indicate that Sentinel-1\u002FSentinel-2 feature fusion is promising for crop-type mapping in cloud-prone mountainous landscapes, while future work should incorporate multi-temporal phenology, richer vegetation indices, SAR texture features, uncertainty mapping, and broader field sampling.","在湿润的热带山区，准确的作物类型制图面临持续云覆盖、崎岖地形和破碎的小农户地块等挑战。本研究评估了一种特征级融合工作流，该工作流整合了Sentinel-2光学指数与Sentinel-1 SAR后向散射数据，用于印度尼西亚东爪哇省卢马姜县坎迪普罗区的作物类型制图。2023年6月至7月获取的Sentinel-2地表反射率和Sentinel-1 IW数据在Google Earth Engine中统一至共同的10 m像元网格，以确保所有对比制图均在相同的空间支撑上进行评估。光学组分包括NDVI、NDBI和NDWI，雷达组分则使用VH\u002FVV极化比值。DEM仅用于表征山区环境并辅助地形解译，未作为预测变量纳入分类器。堆叠特征影像采用随机森林模型进行分类，该模型以101个野外调查地面控制点进行训练，代表八个土地覆盖\u002F作物相关类别。精度评估使用393个分层随机验证点。融合影像分类的总体精度达到93%，Kappa系数为0.90。与仅光学对比方案相比，融合工作流产生了更丰富的专题区分能力，尤其在水体、甘蔗和灌木地方面。然而，类别层面的结果揭示了玉米田存在较大不确定性，建成区和水体类别存在中等程度的混淆。因此，本工作流应被解读为特定站点的单日期概念验证，而非完全可迁移的业务化方案。结果表明，Sentinel-1\u002FSentinel-2特征融合在多云山区景观的作物类型制图中具有前景，未来工作应纳入多时相物候、更丰富的植被指数、SAR纹理特征、不确定性制图以及更广泛的野外采样。","Engineering and Applied Science Research","2026-10-12T00:00:00Z",{"impact":166,"substance":18,"depth":363,"authority":45,"freshness":84,"relevant":21,"comment":364},17,"方法扎实、精度可观的遥感作物制图概念验证研究，但属单点单时相案例，公共影响有限，适合作为技术参考而非每日精选头条。",[366],{"name":360,"url":357},[26,236,171,368,369],"作物识别","哨兵卫星",{"code":32,"slug":33,"name":34,"path":35,"parent_code":8},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":373},{"candidates":374,"agricultural_evidence":46,"reason":79},[375,379,385,392,396,400],{"code":118,"score":87,"supported":46,"title":376,"abstract":377,"tags":378},[],[121,188],[],{"code":263,"score":87,"supported":46,"title":380,"abstract":381,"tags":384},[],[382,383],"甘蔗","sugarcane",[],{"code":386,"score":87,"supported":46,"title":387,"abstract":388,"tags":391},"G2",[],[389,390],"小农户","smallholder",[],{"code":44,"score":21,"supported":14,"title":393,"abstract":394,"tags":395},[],[],[26],{"code":277,"score":21,"supported":14,"title":397,"abstract":398,"tags":399},[],[],[236],{"code":191,"score":21,"supported":14,"title":401,"abstract":402,"tags":403},[],[],[171],[405,406],"Sentinel-1 Sentinel-2 作物分类","印尼 东爪哇 作物制图","Sentinel-1Sentinel-2作物分类-4901","10.64960\u002Feasr.2026.263460",{"doi":408,"openalex_id":410,"authors":411,"venue":360,"cited_by_count":203,"oa_url":422,"card":423,"direction":215,"ingested_from":218},"W7221544367",[412,415,418,420],{"name":413,"orcid":414},"Indarto Indarto","https:\u002F\u002Forcid.org\u002F0000-0001-6319-6731",{"name":416,"orcid":417},"Gunawan Gunawan","https:\u002F\u002Forcid.org\u002F0000-0001-7914-3669",{"name":419,"orcid":8},"Mahrus Irsyam",{"name":421,"orcid":8},"Fahmi Arif Kurnanto","https:\u002F\u002Fph01.tci-thaijo.org\u002Findex.php\u002Feasr\u002Farticle\u002Fdownload\u002F263460\u002F176575",{"tldr":424,"method":425,"finding":426,"direction":215,"opportunity":427},"融合Sentinel-1 SAR与Sentinel-2光学特征，在印尼热带山地实现93%精度的作物类","Google Earth Engine中10米格网特征级融合NDVI\u002FNDBI\u002F","融合影像总体精度93%、kappa 0.90，优于仅光学方案，但玉米和建成区仍存在明显混淆。","可引入多时相物候、SAR纹理与不确定性制图，提升热带多云山区小农户破碎地块的作物识别与可迁移性。","2026-10-14T23:30:28.943594Z",{"id":430,"title":431,"url":432,"summary":433,"summary_zh":8,"content":434,"source_name":435,"source_url":8,"published_at":361,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":436,"score_detail":437,"sources":440,"tags":442,"primary_topic":448,"secondary_topics":449,"classification":450,"search_phrases":489,"slug":492,"view_count":21,"doi":8,"paper":8,"created_at":493},4765,"在农业农村现代化关键点上持续发力","https:\u002F\u002Fwww.qstheory.cn\u002F20261012\u002Fc6238e31742540c887fb80611fcdb460\u002Fc.html","求是网刊发关于兵团农业农村现代化的理论文章,部署三项重点。一是积极培育农业低空经济新业态,布局AI加农业专项行动;二是推动稳粮、优棉、强果、兴畜、创特色,扩大优质食味稻、专用小麦、高产高油大豆供给;三是推进农产品精深加工、发展智慧冷链物流,贯通仓储、运输、配送全环节。","  持续深化团场改革，激发农业发展活力。一是持续深化团场综合配套改革，完善土地、职工、民兵“三位一体”机制，持续增强团场发展的内生动力和发展活力。针对团场连队基础设施与公共服务短板，推动城乡要素双向流动，促进人才、资金、技术等现代生产要素向团场连队有序集聚。健全人才引进与培育机制，鼓励科技人员、高校毕业生、退役军人等高素质人才到团场连队创业就业。持续推进公共服务均等化，助力实现区域全面融合、共同繁荣的发展目标。二是在规划建设方面，坚持精准施策，全面提升规划、建设、治理融合发展水平，统筹推进城镇高质量发展。各师市要立足自身资源禀赋与区位条件，科学编制区域发展规划，明确城市、团场、连队的功能定位与发展方向，加快构建城乡融合、功能互补、共同繁荣的城乡发展格局。三是充分发挥兵团农业发展优势，健全兵地共同推进乡村振兴的沟通协商机制，统筹推进兵地基础设施建设和人居环境改善，深化公共服务资源共享，推动兵团连队与地方邻近村开展结对共建，进一步推动兵地深度嵌入、融合发展。\n\n  强化农业科技创新，培育农业新质生产力。一是深入实施种业振兴行动，加快突破性品种选育推广，有序推进生物育种产业化应用。发挥兵团在棉花、玉米种子领域的基础优势，加大生物育种技术研发力度，推进分子标记辅助选择、基因编辑等现代育种技术应用，培育更多具有自主知识产权的优良品种。支持兵团围绕种业振兴、智慧农业、深度节水、土壤改良等领域开展农业关键核心技术攻关，高水平建设种业创新平台，加快培育突破性品种，破解兵团农业领域“卡脖子”技术难题。二是加快高端智能农机装备研发应用，持续巩固提升兵团农业机械化水平。积极培育农业低空经济新业态，拓展无人机在植保作业、农田监测、农资运输等领域应用场景。构建农业科技领军企业培育库，支持企业牵头组建创新联合体，加快培育龙头型、成长型农业科技企业。推动人工智能与农业生产经营深度融合，实施“人工智能+农业”专项行动，促进物联网、大数据、机器人等技术在精准施肥、智能灌溉、病虫害监测等生产环节规模化应用。三是进一步提升节水技术水平，在现有膜下滴灌、“干播湿出”等技术基础上，加快攻克深度节水、智能灌溉关键技术，推广应用智能水肥一体化技术，持续巩固兵团农业高效节水灌溉全国领先地位。探索建立农业用水总量控制与定额管理制度，深化农业水价综合改革，促进水资源可持续利用。\n\n  提升农业综合生产能力，夯实农产品稳产保供根基。一是稳定粮食生产。深入实施新一轮千亿斤粮食产能提升行动，持续推进蔬菜、林果、畜禽、水产等特色优势产业发展。牢固树立并深入践行大食物观，坚持农林牧渔协同发展，推动构建多元化食物供给体系，全方位、多途径开发食物资源，拓宽食物供给来源。按照“稳粮、优棉、强果、兴畜、创特色”的农业发展要求，将棉花种植面积稳定在千万亩级，持续巩固棉花产业优势地位，同时优化粮食品种结构，扩大优质食味稻、专用小麦、高产高油大豆等优质农产品供给。二是推进高标准农田建设。按照分区分类原则高质量推进高标准农田建设，完善立项、建设、验收与管护的全链条管理机制，推进大中型灌区现代化建设与改造，强化盐碱地治理，提升耕地质量。进一步提升高标准农田占耕地面积比重，从根本上改善农业生产的土地基础条件，为农业稳产高产提供坚实支撑。三是推动农产品品质提升。推动兵团农业向产量与品质并重转型，健全农业标准体系，完善农产品质量安全承诺达标合格证制度，构建以市场需求为导向的品质评价与质量分级制度。强化兵团农产品质量安全监管，确保农产品质量安全监测总体合格率稳定在较高水平，推动更多兵团优质农产品实现优质优价。\n\n  构建现代农业产业体系，加快推动产业转型升级。一是推动农产品精深加工。围绕“优、精、特”农业发展方向，坚持智能化升级、绿色化生产、融合化发展路径，促进种养环节增值，推动农产品供给由“原字号”初级产品向高附加值“制成品”转型。延伸拓展棉花、玉米、红枣、辣椒等特色农产品加工链条，发展精深加工与生物制造产业，挖掘农产品多元利用价值；加快智慧冷链物流网络建设，贯通仓储、运输、配送全环节，保障农产品跨区域高效安全流通；促进农业与文旅、康养等产业深度融合，培育发展田园综合体等新业态，拓展农业多元功能。充分开发利用荒漠、草场、林地与水域资源，把戈壁荒滩的潜在价值转化为从田间到车间的产业发展优势。二是壮大兴农富民产业。健全紧密型联农带农利益联结机制，发展壮大各具特色的团场连队经济。培育一批产业链条长、科技含量高、带动能力强的产业领军企业，做强农产品精深加工产业集群。持续做强农业优势产业，大力发展农产品加工流通业，促进农产品增值，让职工群众共享产业增值收益。做大做强棉花及纺织服装全产业链，积极承接东部地区产业转移，建设综合性纺织工业基地与特色服装产业集群。\n\n  建设宜居宜业和美连队，提升职工群众生活品质。一是学习运用“千万工程”经验，分区分类推进和美连队建设。接续实施乡村振兴“百连示范工程”扩面提质行动，进一步扩大示范覆盖范围、提升示范建设质量，推进高水平示范连队建设，发挥典型引领带动作用。持续健全连队治理长效机制，坚持和发展新时代“枫桥经验”，深入推进文明乡风建设工程。二是大力发展连队本土特色经济，保护传承军垦文化。立足各连队的区位条件、资源特色，因地制宜发展庭院经济、休闲农业、乡村旅游等新产业新业态，激活连队零散闲置的各类资源，以千家万户庭院“小美”赋能连队生态宜居、产业兴旺的“大美”建设，拓宽职工群众就地就近增收渠道。在连队建设全过程中，注重保护兵团特有的军垦文化风貌，守护并延续兵团精神的历史文脉，让红色军垦基因得到传承弘扬，使连队建设既充分体现新时代现代化发展水平，配套完善现代化基础设施与公共服务，又保留兵团屯垦戍边的独特标识，打造彰显军垦特色、生态宜居的田园式家园。\n\n  推进绿色低碳循环发展，擦亮农业生态底色。一是深入推进节水增效。健全高标准节水灌溉技术体系，在现有节水农业发展基础上，大面积推广应用智能水肥一体化技术，持续提高农业水资源利用效率，减少水资源无效消耗。探索建立符合兵团农业发展实际的农业用水总量控制与定额管理制度，以刚性制度约束引导农业合理配水用水，进一步促进区域水资源可持续利用。二是强化农业面源污染综合治理。深入推进化肥农药减量增效行动，大力推广有机肥替代化肥、病虫草害绿色防控等成熟技术，从源头减少农业面源污染排放。持续推进畜禽养殖粪污资源化利用，推动形成种养结合、循环发展的农业模式，实现养殖废弃物就地就近消纳、循环利用。健全农业废弃物回收利用体系。统筹推进农作物秸秆综合利用和农田残膜回收，全链条降低农业废弃物对生态环境的影响。","求是网 2026-10-12",82,{"impact":438,"substance":17,"depth":19,"authority":99,"freshness":84,"relevant":21,"comment":439},24,"央媒刊发的兵团农业现代化系统部署，政策条款与产业路径清晰，但属方向性综合论述，新数据与独家信息有限。",[441],{"name":435,"url":432},[26,443,444,445,446,447],"低空经济","高标准农田","种业振兴","农业现代化","智慧冷链",{"code":32,"slug":33,"name":34,"path":35,"parent_code":8},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":451},{"candidates":452,"agricultural_evidence":46,"reason":79},[453,459,463,469,475,480,485],{"code":454,"score":45,"supported":46,"title":455,"abstract":457,"tags":458},"J2",[456],"农业农村现代化",[456],[446],{"code":58,"score":52,"supported":46,"title":460,"abstract":461,"tags":462},[],[61],[],{"code":464,"score":52,"supported":46,"title":465,"abstract":466,"tags":468},"A4",[],[467],"大豆",[],{"code":470,"score":52,"supported":46,"title":471,"abstract":472,"tags":474},"E3",[],[473],"冷链",[],{"code":476,"score":21,"supported":14,"title":477,"abstract":478,"tags":479},"F1",[],[],[445],{"code":481,"score":21,"supported":14,"title":482,"abstract":483,"tags":484},"H1",[],[],[444],{"code":44,"score":21,"supported":14,"title":486,"abstract":487,"tags":488},[],[],[26],[490,491],"兵团 种业振兴 生物育种","兵团 农业低空经济 无人机植保","兵团种业振兴生物育种-4765","2026-10-13T00:08:34.007796Z",{"id":495,"title":496,"url":497,"summary":498,"summary_zh":499,"content":8,"source_name":500,"source_url":497,"published_at":501,"category":163,"cover_url":8,"hotness":13,"is_selected":14,"score":502,"score_detail":503,"sources":505,"tags":507,"primary_topic":512,"secondary_topics":513,"classification":514,"search_phrases":543,"slug":546,"view_count":21,"doi":547,"paper":548,"created_at":573},4328,"Agricultural water-land optimization for multiple cropping under crop growth stages and farmer budget constraints","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104990","CONTEXT Optimizing water and land resources for multiple cropping face three major challenges: temporal mismatches, periodic land overload, and disconnects from farmers' budget constraints. OBJECTIVE This study proposes a tiered framework that synchronizes crop-stage water needs, monthly supply, land limits, and budget ceilings to generate feasible, differentiated allocation plans. METHOD The year was divided into 35 sub-periods based on crop growth-stage transitions, with two-way mapping among stages, sub-periods, and months to resolve mismatches. Binary planting variables capture crop distribution and generate time-series area constraints. A dual-path budget grading framework is embedded in the multi-objective model to account for data availability. Where survey data exist, per-area budget is the clustering indicator; Ward's clustering method and silhouette coefficient determine K. Otherwise, standardized budget scenarios are constructed using minimum feasible cost and land-use potential. The model is solved by NSGA-II, and incremental benefit-cost ratio analysis guides tiered recommendations. RESULTS AND CONCLUSIONS Applied to Gaozhou Irrigation District, the method achieved water satisfaction 91.75%–100% across growth stages. Net benefit increased 6.4% from 96,426.51 CNY (13,393 USD) to 102,587.59 CNY (14,248 USD), and water deficit reduced 29.7% to 753 m 3 . With budget ceilings 25,700, 44,300, 65,600 CNY, rice area expands without per-unit irrigation change; peanut area and per-unit irrigation rise only at low-medium transition; further increments drive area expansion but raise water deficit. The incremental benefit-cost ratio values are 1.30 and 1.53 CNY\u002FCNY for low-to-medium and medium-to-high transitions, respectively. SIGNIFICANCE By converting theoretical optima into budget-differentiated feasible strategies, the framework supports precision irrigation scheduling and provides a practical basis for designing targeted agricultural subsidies and water-saving policies.","背景 优化水土地资源以实现多熟种植面临三大挑战：时间错配、周期性土地超载，以及与农户预算约束脱节。目的 本研究提出一个分层框架，将作物阶段需水、月度供给、土地限制和预算上限同步考虑，以生成可行且差异化的配置方案。方法 根据作物生长阶段转换将全年划分为35个子时段，并通过阶段、子时段和月份之间的双向映射来解决错配问题。二元种植变量用于刻画作物分布并生成时间序列面积约束。在多目标模型中嵌入双路径预算分级框架，以考虑数据可得性。在有调查数据的情况下，以单位面积预算作为聚类指标；采用Ward聚类法和轮廓系数确定K。否则，利用最小可行成本和土地利用潜力构建标准化预算情景。模型采用NSGA-II求解，并通过增量效益成本比分析指导分层建议。结果与结论 将该方法应用于高州灌区，各生长阶段的水分满足度达到91.75%–100%。净效益从96,426.51元（13,393美元）增加到102,587.59元（14,248美元），增幅为6.4%，水分亏缺减少29.7%至753 m³。在预算上限为25,700元、44,300元、65,600元时，水稻面积扩大而单位面积灌溉量不变；花生面积和单位面积灌溉量仅在中低过渡阶段上升；进一步增加会推动面积扩张，但会提高水分亏缺。低到中和中到高过渡阶段的增量效益成本比分别为1.30和1.53元\u002F元。意义 通过将理论最优解转化为预算差异化的可行策略，该框架支持精准灌溉调度，并为设计有针对性的农业补贴和节水政策提供了实践依据。","Agricultural Systems","2026-10-06T00:00:00Z",79,{"impact":19,"substance":230,"depth":17,"authority":231,"freshness":84,"relevant":21,"comment":504},"核心期刊论文，提出分阶段水土资源优化框架并在高州灌区验证，方法新颖、数据扎实，对精准灌溉与节水政策有参考价值。",[506],{"name":500,"url":497},[26,508,509,510,511],"农业补贴","多目标优化","灌溉调度","水资源优化",{"code":32,"slug":33,"name":34,"path":35,"parent_code":8},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":515},{"candidates":516,"agricultural_evidence":46,"reason":79},[517,521,527,534,539],{"code":51,"score":87,"supported":46,"title":518,"abstract":519,"tags":520},[],[55,248],[],{"code":464,"score":87,"supported":46,"title":522,"abstract":523,"tags":526},[],[524,525],"花生","peanut",[],{"code":528,"score":87,"supported":46,"title":529,"abstract":530,"tags":533},"H3",[],[531,532],"灌溉","irrigation",[],{"code":535,"score":4,"supported":46,"title":536,"abstract":537,"tags":538},"G3",[],[508],[508],{"code":44,"score":21,"supported":14,"title":540,"abstract":541,"tags":542},[],[],[26],[544,545],"高州灌区 水稻 花生 灌溉","多目标优化 水资源优化 农业补贴 智慧农业","高州灌区水稻花生灌溉-4328","10.1016\u002Fj.agsy.2026.104990",{"doi":547,"openalex_id":549,"authors":550,"venue":500,"cited_by_count":203,"oa_url":497,"card":568,"direction":217,"ingested_from":218},"W7220721550",[551,553,556,559,561,563,565],{"name":552,"orcid":8},"杜宇",{"name":554,"orcid":555},"Yuzhi Tang","https:\u002F\u002Forcid.org\u002F0000-0003-2225-9905",{"name":557,"orcid":558},"Kaiwen Li","https:\u002F\u002Forcid.org\u002F0009-0007-0133-6277",{"name":560,"orcid":8},"Chengbin Yang",{"name":562,"orcid":8},"Yihang Zheng",{"name":564,"orcid":8},"LuJia",{"name":566,"orcid":567},"Li He","https:\u002F\u002Forcid.org\u002F0000-0002-2935-0069",{"tldr":569,"method":570,"finding":571,"direction":217,"opportunity":572},"提出分层框架，在作物生长阶段和农户预算约束下优化多熟制水与土地资源配置。","按35个子时段映射生长阶段，嵌入双路径预算分级，用NSGA-II求解多目标模型。","高州灌区水满足度91.75%-100%，净收益增6.4%，缺水减29.7%，预算分级影响作物面积与灌","可将预算分级框架与实时遥感、物联网数据结合，发展动态预算约束下的自适应灌溉决策。","2026-10-07T23:30:04.193429Z"]