[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-735":3,"related-735":57},{"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":23,"tags":25,"primary_topic":8,"secondary_topics":31,"classification":32,"search_phrases":51,"slug":54,"view_count":55,"doi":8,"paper":8,"created_at":56},735,"湖北省农科院党委书记张世伟带队赴新疆调研在疆科研基地并参加学术交流","https:\u002F\u002Fwww.hbaas.ac.cn\u002Fview\u002F40952.html","湖北省农科院党委书记张世伟带队赴新疆参加学术交流会议并调研该院在疆科研基地,考察棉花、辣椒等新品种示范基地,与湖北省援疆前方指挥部座谈,为湖北-新疆农业科技协作搭建更高平台。",null,"湖北省农业科学院 2026-08-14","2026-08-14T00:00:00Z","报道",10,false,51,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},15,12,8,11,5,1,"省级农科院跨区域科技协作动态，有一定行业价值，但内容偏通稿，深度一般。",[24],{"name":9,"url":6},[26,27,28,29,30],"棉花","新疆","湖北省农科院","辣椒","张世伟",[],{"status":33,"locked":13,"version":34,"method":35,"evidence":36},"needs_review","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":41,"reason":50},[38,45],{"code":39,"score":40,"supported":41,"title":42,"abstract":43,"tags":44},"A6",4,true,[],[26],[26],{"code":46,"score":40,"supported":41,"title":47,"abstract":48,"tags":49},"B1",[],[29],[29],"多个产业证据相当，需要确认主归属",[52,53],"湖北省农科院 张世伟 新疆 棉花","湖北省农科院 张世伟","湖北省农科院张世伟新疆棉花-735",3,"2026-08-19T23:57:29.874438Z",{"total":58,"page":21,"page_size":58,"items":59},6,[60,111,173,255,315,362],{"id":61,"title":62,"url":63,"summary":64,"summary_zh":8,"content":65,"source_name":66,"source_url":8,"published_at":67,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":68,"score_detail":69,"sources":75,"tags":77,"primary_topic":81,"secondary_topics":86,"classification":87,"search_phrases":105,"slug":108,"view_count":109,"doi":8,"paper":8,"created_at":110},4624,"中国农科院西部中心新疆昌吉千亩棉花示范方平均亩产601.4公斤","https:\u002F\u002Fwri.caas.cn\u002Fmtbd\u002F81c85d1a59794f6981378701dbecdb5f.htm","中国农业科学院西部农业研究中心在新疆昌吉老龙河示范基地打造千亩棉花示范方,2026年9月29日举办棉花优质高产关键技术集成示范观摩会。经专家组现场测产,千亩示范方平均亩产籽棉达601.4公斤,在北疆6-8月高温持续26天的极端气候条件下实现产量、品质、效益三丰收。示范品种包括中棉113优系、中新棉1号、中新棉3号,集成高光效群体调控技术与智慧棉田水肥精准供给。","近日，记者从中国农业科学院西部农业研究中心（科技援疆指挥部）（以下简称西部中心）获悉，西部中心在新疆昌吉老龙河示范基地打造的千亩棉花示范方取得喜人成效。经专家组现场测产，籽棉平均亩产达601.4公斤，为北疆棉区应对极端气候、实现棉花优质高产提供了可复制、可推广的技术样板。\n\n据介绍，2026年新疆气候条件复杂，整体呈现“前期低温、中后期持续极端高温”情况。6-8月正值棉花结铃关键期，北疆高温持续26天，持续高温胁迫极易引发蕾铃脱落、严重制约棉花产量形成。9月29日，西部中心联合昌吉州农牧业技术推广中心、昌吉国家农业高新技术产业示范区及当地农业技术推广部门，在老龙河综合试验基地举办“棉花优质高产关键技术集成示范”观摩会。来自植棉县市、乡镇的农技人员、种植户、合作社负责人齐聚田间，实地观摩新品种、新技术示范成效，交流极端气候下棉田丰产的实践经验。\n\n现场，西部中心副研究员孔德培介绍了优质高产多抗棉花新品种，主要包括中棉113优系、中新棉1号、中新棉3号等。该系列品种生育期118-120天，抗枯萎耐黄萎病、抗旱耐盐碱，衣分45%以上，纤维品质达“双30”以上，产量潜力550-600公斤\u002F亩，结铃吐絮集中，适宜机械化采收。\n\n西部中心研究员宋美珍讲解高光效群体优势调控技术，通过构建“壮根健株、增铃数防中空、增铃重防花粉败育、优质多抗（抗高温、抗干旱、抗病虫等）高光效群体结构”，改善棉田通风透光条件，提升光温水肥利用率；应用该技术可节约农药15%以上，人工成本降低30%以上，产量提升10%以上，亩增效200-400元，实现增产节本提质。昌吉州农牧业技术推广中心研究员魏建华讲解棉花病虫害识别与绿色综合防控实操要点。西部中心助理研究员张潇镭介绍高产智慧棉田创建模式，借助传感器、气象站、巡检机器人、无人机等构建立体监测体系，依托物联网平台精准供给水肥，肥料利用率提升20%-30%，用水量减少30%以上。\n\n河北农业大学教授李存东代表专家组公布测产结果，千亩示范方平均亩产籽棉601.4公斤，在高温逆境条件下实现产量、品质、效益三丰收。项目团队表示，团队研发的集成技术，瞄准新疆棉花生产现实痛点，形成应对前期低温、中后期高温的综合技术方案。下一步，西部中心将加快新品种、新技术成果下沉推广，指导棉农科学应对极端天气，助力棉花大面积单产提升。","中国农科院西部农业研究中心 2026-10-10","2026-10-10T00:00:00Z",84,{"impact":70,"substance":70,"depth":71,"authority":72,"freshness":73,"relevant":21,"comment":74},22,17,14,9,"国家级科研机构在新疆昌吉千亩棉花示范方实测亩产601.4公斤，集成新品种、高光效调控与智慧棉田技术，数据具体、信源权威，对北疆棉区抗逆高产具推广价值。",[76],{"name":66,"url":63},[78,26,27,79,80],"种业振兴","智慧棉田","高产栽培",{"code":39,"slug":82,"name":83,"path":84,"parent_code":85},"cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[],{"status":88,"locked":13,"version":34,"method":35,"evidence":89},"classified",{"candidates":90,"agricultural_evidence":41},[91,95,100],{"code":39,"score":17,"supported":41,"title":92,"abstract":93,"tags":94},[26],[26],[26],{"code":96,"score":21,"supported":13,"title":97,"abstract":98,"tags":99},"A8",[],[],[80],{"code":101,"score":21,"supported":13,"title":102,"abstract":103,"tags":104},"F1",[],[],[78],[106,107],"中国农科院西部中心 棉花 昌吉","中棉113 中新棉1号 棉花品种","中国农科院西部中心棉花昌吉-4624",0,"2026-10-11T00:09:41.436557Z",{"id":112,"title":113,"url":114,"summary":115,"summary_zh":8,"content":116,"source_name":117,"source_url":8,"published_at":118,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":119,"score_detail":120,"sources":125,"tags":127,"primary_topic":131,"secondary_topics":137,"classification":138,"search_phrases":168,"slug":171,"view_count":12,"doi":8,"paper":8,"created_at":172},26,"南疆棉田形成“感知—决策—执行”智慧栽培闭环","https:\u002F\u002Fcri.caas.cn\u002Fxwdt\u002Fmtbd\u002F5d60f1578007432180b9f36c5f0b4361.htm","2000亩示范田将物联网数据、数字化栽培标准和智能滴灌联动，自动生成灌溉、施肥和化控方案。示范结果显示，灌溉施肥用工节省85%以上，节水25%至30%，肥料利用率提高20%以上。","### [光明日报]AI决策+智能滴灌！助力南疆棉花提质增效\n\n发布时间:2026-07-25 来源 ：**光明日报客户端**作者：**杨舒**\n\n2026年7月21日，由中国农业科学院棉花研究所与塔里木大学联合主办的“南疆棉花农艺农机融合精准高效栽培关键技术集成与应用”现场观摩会在新疆生产建设兵团第一师九团举办。2000亩示范田集中展示了“AI决策+智能装备+农艺农机融合”栽培技术体系，为新疆南疆地区植棉提质增效提供了可复制推广的样板。\n\n从“经验种地”到“数据种地”的转变，AI智能决策系统让棉田拥有了“智慧大脑”。据中棉所棉花智慧栽培团队首席科学家李亚兵研究员介绍，针对南疆棉花生产在保苗壮苗、水肥高效利用、化学调控等方面存在的农艺农机融合度不高等问题，中棉所进一步优化自主研发的智慧栽培技术，将海量物联网数据与团队积淀多年的棉花数字化栽培管理标准体系深度融合，研发了AI智能决策系统，该系统可以自动诊断棉花生长状态，生成精准的灌溉、施肥、化控等技术集成管理方案，实现棉田管理的精准化和科学化。\n\n该示范田配备了土壤、红外温度、光合有效辐射等传感器监测设备进行实时数据采集，AI智能决策系统根据数据分析结果给出棉花高效栽培集成管理方案，利用智能施肥系统、智能控制阀门等控制设备和小流量恒压滴灌系统进行精准的水肥管理，形成了从田间信息感知到智能决策再到精准执行的完整闭环。通过各项精准高效栽培技术集成，该示范田节省灌溉施肥用工85%以上，节水25%～30%，肥料利用率提高20%以上。\n\n“这套技术体系依托地块级实时数据，实现智能决策与精准栽培管理，破解了传统植棉管理粗放、水肥利用率低等痛点，技术成熟实用，可有效助力植棉主体降本增收。”新疆生产建设兵团农业技术推广总站毕显杰研究员在观摩后给予高度评价，认为该技术体系兼顾节本增效与绿色发展，为南疆棉花生产提质增效提供了可复制、可推广的技术方案。\n\n下一步，中棉所将加快精准高效栽培技术集成与示范推广，把农民能用、会用、好用的智慧植棉技术送到田间地头，切实解决农民实际生产问题，推动良种、良法、智能装备与数字化管理深度融合，持续为棉花产业高质量发展提供坚实的科技力量。\n\n打印本页\n\n关闭本页","中国农业科学院棉花研究所、光明日报 · 2026-07-21","2026-07-21T00:00:00Z",79,{"impact":121,"substance":70,"depth":122,"authority":16,"freshness":123,"relevant":21,"comment":124},24,16,2,"报道南疆棉花智慧栽培技术集成示范，形成感知-决策-执行闭环，具有产业推广价值，但时效性较低。",[126],{"name":117,"url":114},[128,26,27,129,130],"智慧农业","AI决策","精准栽培",{"code":132,"slug":133,"name":134,"path":135,"parent_code":136},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",[],{"status":88,"locked":13,"version":34,"method":35,"evidence":139},{"candidates":140,"agricultural_evidence":41},[141,147,153,159,163],{"code":132,"score":58,"supported":41,"title":142,"abstract":143,"tags":146},[],[144,145],"施肥","肥料",[],{"code":148,"score":55,"supported":41,"title":149,"abstract":150,"tags":152},"H3",[],[151],"灌溉",[],{"code":154,"score":55,"supported":41,"title":155,"abstract":156,"tags":158},"I5",[],[157],"物联网",[],{"code":39,"score":21,"supported":13,"title":160,"abstract":161,"tags":162},[],[],[26],{"code":164,"score":21,"supported":13,"title":165,"abstract":166,"tags":167},"I1",[],[],[128],[169,170],"智慧农业 精准栽培 AI决策 新疆","智慧农业 精准栽培","智慧农业精准栽培AI决策新疆-26","2026-07-27T23:59:41.058899Z",{"id":174,"title":175,"url":176,"summary":177,"summary_zh":178,"content":8,"source_name":179,"source_url":176,"published_at":180,"category":181,"cover_url":8,"hotness":12,"is_selected":13,"score":119,"score_detail":182,"sources":185,"tags":187,"primary_topic":192,"secondary_topics":197,"classification":203,"search_phrases":227,"slug":230,"view_count":109,"doi":231,"paper":232,"created_at":254},5541,"Year-round modeling of soil water-heat-salt transport and crop growth under film-mulched drip irrigation with freeze-thaw cycles","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.105024","Context Soil water-heat-salt migration and crop growth in film-mulched drip irrigation fields in seasonally frozen regions are influenced by partial mulching and drip irrigation during the growth period, as well as soil freeze-thaw processes during the fallow period. Understanding year-round soil water-heat-salt dynamics and crop growth is essential for sustainable agricultural water use. Objective However, existing year-round models often use one-dimensional (1D) approaches during the growth period, which neglect horizontal salt migration under partial mulching and drip irrigation, leading to an overestimation of salt leaching efficiency. This limitation can be addressed by developing a year-round model that incorporates the distinct dynamics of both growth and fallow periods. Methods In this study, we developed a year-round coupled model, CAWM-S, by integrating the previously developed Crop and Water Model based on HYDRUS-2D (CAWM-H2D) with the SHAW model, which considers soil freeze-thaw processes. The key features of CAWM-S include detailed depiction of 2D soil water-heat-salt migration, crop growth and yield formation, and energy balance at the film-mulched soil surface during the growth period, as well as the redistribution of soil water-salt due to freeze-thaw processes in the fallow period. The model was calibrated and validated using monitored data from two consecutive year-round periods in a film-mulched drip irrigation cotton field in southern Xinjiang, a region with seasonal frozen soils, under different irrigation water salinity levels. This validation is treatment-wise and limited to the same site and two-year period; independent validation across other sites, years, crops, and irrigation systems remains necessary. Results and conclusions The simulated results for soil water, temperature, salinity, crop growth indicators, and yield generally matched the measured data across the two years with varying salinity levels, with treatment-averaged R 2 values ranging from 0.48 to 0.98 and NSE values 0.42 to 0.97. Furthermore, we analyzed the effects of different irrigation volume and salinity combinations on soil desalination rates, evapotranspiration and its components, crop yield, and water productivity, revealing a quadratic relationship between optimal irrigation volume and water salinity under film-mulched drip irrigation. Validation results show that CAWM-S effectively quantifies coupled soil water-heat-salt dynamics and crop growth, and predicts salt redistribution across year-round cycles in seasonally frozen regions. Significance It provides an effective tool for supporting sustainable agriculture by aiding water saving, control of soil salinization and improvement of crop water productivity in the film-mulched drip irrigation fields within seasonally frozen regions.","背景 季节性冻土区覆膜滴灌农田的土壤水热盐迁移与作物生长，受生育期内部分覆膜和滴灌以及休止期土壤冻融过程的影响。理解全年土壤水热盐动态及作物生长对于农业可持续用水至关重要。目的 然而，现有全年模型在生育期多采用一维（1D）方法，忽略了部分覆膜滴灌条件下的水平盐分迁移，导致对盐分淋洗效率的高估。这一局限可通过开发兼顾生育期与休止期不同动态特征的全年模型加以解决。方法 本研究将前期开发的基于HYDRUS-2D的作物与水分模型（CAWM-H2D）与考虑土壤冻融过程的SHAW模型相耦合，构建了全年耦合模型CAWM-S。CAWM-S的主要特点包括：详细刻画生育期二维土壤水热盐迁移、作物生长与产量形成以及覆膜土壤表面能量平衡，同时描述休止期冻融过程引起的土壤水盐再分布。模型采用南疆季节性冻土区覆膜滴灌棉田连续两个全年周期的监测数据，在不同灌溉水矿化度水平下进行率定与验证。该验证按处理进行，且仅限于同一站点和两年时段；仍需在其他站点、年份、作物及灌溉系统下开展独立验证。结果与结论 在两个不同矿化度水平的年份中，土壤水分、温度、盐分、作物生长指标及产量的模拟结果与实测数据总体吻合，处理平均R²为0.48~0.98，NSE为0.42~0.97。此外，分析了不同灌水量与矿化度组合对土壤脱盐率、蒸散及其组分、作物产量和水分生产率的影响，揭示了覆膜滴灌条件下最优灌水量与灌溉水矿化度之间的二次关系。验证结果表明，CAWM-S能够有效量化土壤水热盐耦合动态与作物生长，并预测","Agricultural Systems","2026-10-21T00:00:00Z","论文",{"impact":122,"substance":70,"depth":183,"authority":72,"freshness":73,"relevant":21,"comment":184},18,"构建了覆盖冻融期的全年水热盐与作物生长耦合模型，方法有新意、验证数据扎实，对盐碱地滴灌节水有实用价值，但属单点两年验证的学术成果，产业影响有限。",[186],{"name":179,"url":176},[26,188,189,190,191],"盐碱地治理","节水灌溉","覆膜滴灌","土壤水盐运移",{"code":148,"slug":193,"name":194,"path":195,"parent_code":196},"irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[198],{"code":199,"slug":200,"name":201,"path":202,"parent_code":196},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"status":88,"locked":13,"version":34,"method":35,"evidence":204},{"candidates":205,"agricultural_evidence":41},[206,211,216,221],{"code":148,"score":183,"supported":41,"title":207,"abstract":208,"tags":210},[193],[151,193,209],"evapotranspiration",[189],{"code":199,"score":16,"supported":41,"title":212,"abstract":213,"tags":215},[200],[214,200],"土壤",[188],{"code":39,"score":40,"supported":41,"title":217,"abstract":218,"tags":220},[],[219],"cotton",[26],{"code":222,"score":55,"supported":41,"title":223,"abstract":224,"tags":226},"H8",[],[225],"sustainable agriculture",[],[228,229],"南疆 覆膜滴灌 棉花","CAWM-S 模型 冻融","南疆覆膜滴灌棉花-5541","10.1016\u002Fj.agsy.2026.105024",{"doi":231,"openalex_id":233,"authors":234,"venue":179,"cited_by_count":109,"oa_url":176,"card":247,"direction":251,"ingested_from":253},"W7223120642",[235,238,240,243,245],{"name":236,"orcid":237},"Dong Lin","https:\u002F\u002Forcid.org\u002F0000-0001-8433-9658",{"name":239,"orcid":8},"Tongkai Guo",{"name":241,"orcid":242},"Zunqiu Xu","https:\u002F\u002Forcid.org\u002F0000-0002-9393-3605",{"name":244,"orcid":8},"Wenping Bi",{"name":246,"orcid":8},"Xiaomin Mao",{"tldr":248,"method":249,"finding":250,"direction":251,"opportunity":252},"构建全年耦合模型CAWM-S，模拟覆膜滴灌棉田水热盐运移与作物生长。","将HYDRUS-2D的CAWM-H2D与冻融模型SHAW耦合，用南疆两年监测数据","模型精度较高（R²0.48-0.98），揭示最优灌溉量与灌水盐度呈二次关系。","农业遥感与作物表型","可扩展至多站点、多作物与不同灌溉制度的独立验证，并耦合遥感数据实现区域尺度模拟。","openalex","2026-10-22T11:20:12.238655Z",{"id":256,"title":257,"url":258,"summary":259,"summary_zh":260,"content":8,"source_name":261,"source_url":258,"published_at":262,"category":181,"cover_url":8,"hotness":12,"is_selected":13,"score":263,"score_detail":264,"sources":266,"tags":268,"primary_topic":272,"secondary_topics":273,"classification":274,"search_phrases":299,"slug":302,"view_count":21,"doi":303,"paper":304,"created_at":314},5233,"Cotton pest and disease multi-class classification with weather and temporal predictors features across Indian agroclimatic zones","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.73s.45","The Pink Bollworm (Pectinophora gossypiella) remains one of the most destructive pests affecting cotton productivity, with infestation levels strongly driven by climatic fluctuations and crop phenology.This study presents a machine learning-based framework for early multi-classification and prediction of Pink Bollworm incidence using agro-meteorological variables.The dataset includes maximum and minimum air temperature, relative humidity, rainfall, sunshine hours, evaporation, and wind speed, all of which influence Pink Bollworm development, migration, and reproductive cycles.After preprocessing, applying cyclic encoding to temporal variables, and generating lagged climatic features, multiple machine learning algorithms-including SVM, Neural Networks, KNN, Regression models, Ensemble methods, and Naïve Bayes-were trained and systematically compared.SVM model demonstrated the best test accuracy, effectively capturing dynamic climate-pest interactions.The resulting MATLAB-based classification tool enables rapid assessment and supports climate-informed pest surveillance.A stratified 80:20 train-test split was employed, with 5-fold cross-validation on the training set for hyperparameter tuning, ensuring no data leakage between partitions.The validation and training accuracies of these models are 89.4% and 96 % respectively.Overall, the model offers a practical and interpretable solution for early detection of Pink Bollworm risk, thereby contributing to informed decision-making in integrated pest management (IPM) and precision agriculture.","棉红铃虫（Pectinophora gossypiella）仍是影响棉花产量最具破坏性的害虫之一，其发生程度受气候波动和作物物候的强烈驱动。本研究提出了一种基于机器学习的框架，利用农业气象变量对棉红铃虫的发生进行早期多分类与预测。数据集包括最高和最低气温、相对湿度、降雨量、日照时数、蒸发量和风速，这些因素均影响棉红铃虫的发育、迁移和繁殖周期。经过预处理、对时间变量应用循环编码并生成滞后气候特征后，训练并系统比较了多种机器学习算法，包括支持向量机（SVM）、神经网络、K近邻（KNN）、回归模型、集成方法和朴素贝叶斯。SVM模型表现出最佳的测试准确率，有效捕捉了气候与害虫之间的动态相互作用。所构建的基于MATLAB的分类工具可实现快速评估，并支持气候信息驱动的害虫监测。采用分层80：20的训练-测试划分，并在训练集上进行5折交叉验证以调优超参数，确保各分区之间无数据泄漏。这些模型的验证准确率和训练准确率分别为89.4%和96%。总体而言，该模型为棉红铃虫风险的早期检测提供了一种实用且可解释的解决方案，从而有助于综合害虫管理（IPM）和精准农业中的科学决策。","International Journal of Drug Delivery Technology","2026-10-17T00:00:00Z",55,{"impact":18,"substance":183,"depth":72,"authority":58,"freshness":73,"relevant":21,"comment":265},"研究用多类机器学习模型结合气象与时序特征预测棉铃虫风险，方法扎实但属细分领域应用研究，信源期刊权威性一般，公共影响有限。",[267],{"name":261,"url":258},[128,269,26,270,271],"机器学习","农业气象","病虫害预警",{"code":39,"slug":82,"name":83,"path":84,"parent_code":85},[],{"status":88,"locked":13,"version":34,"method":35,"evidence":275},{"candidates":276,"agricultural_evidence":41},[277,281,288,294],{"code":39,"score":16,"supported":41,"title":278,"abstract":279,"tags":280},[219],[26,219],[26],{"code":164,"score":282,"supported":41,"title":283,"abstract":284,"tags":287},7,[],[285,286],"精准农业","precision agriculture",[128],{"code":289,"score":282,"supported":41,"title":290,"abstract":291,"tags":293},"I2",[],[269,292],"machine learning",[269],{"code":295,"score":40,"supported":41,"title":296,"abstract":297,"tags":298},"H7",[],[270],[270],[300,301],"棉铃虫 机器学习 预测","棉花 病虫害 气象因子","棉铃虫机器学习预测-5233","10.25258\u002Fijddt.16.73s.45",{"doi":303,"openalex_id":305,"authors":306,"venue":261,"cited_by_count":109,"oa_url":258,"card":307,"direction":313,"ingested_from":253},"W7222826491",[],{"tldr":308,"method":309,"finding":310,"direction":311,"opportunity":312},"用农业气象变量与时间特征构建机器学习模型，实现印度棉区棉铃虫多级发生预测。","气象数据加周期编码与滞后特征，比较SVM等模型，5折交叉验证。","SVM测试精度最高达89.4%，能有效刻画气候与虫害动态关系。","农业人工智能与决策模型","可引入遥感植被指数与实时气象物联网数据，构建跨区域可迁移的病虫害预警系统。","智慧农业 \u002F 农业物联网","2026-10-18T23:30:07.725427Z",{"id":316,"title":317,"url":318,"summary":319,"summary_zh":8,"content":320,"source_name":321,"source_url":8,"published_at":322,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":68,"score_detail":323,"sources":326,"tags":328,"primary_topic":332,"secondary_topics":333,"classification":334,"search_phrases":357,"slug":360,"view_count":21,"doi":8,"paper":8,"created_at":361},5031,"智慧棉田成就新疆新一代科技棉农","https:\u002F\u002Fwww.news.cn\u002Flocal\u002F20261015\u002F048734cea69b466eac74966f7b4d0074\u002Fc.html","金秋十月,天山南北棉花吐絮迎来采收。在塔克拉玛干沙漠北缘的尉犁县'超级棉田',采棉机来回穿梭,朵絮归仓。新疆是中国最大优质棉花生产基地,2025年新疆棉花产量占全国92.8%,总产、单产连续32年居全国第一。2021年极飞科技在尉犁县启动'超级棉田'项目,目前管理环节无人化作业率已达75%,栽培管理模式在全疆推广面积已超200万亩。今年更新的X150新型农业无人机可自动配药、加药、充电、规划航线,自主喷药作业。'90后'家庭农场主郭腾承包2.5万亩棉田,日常管护只需50名工人,返乡种棉成为越来越多年轻人的选择。","  新华社乌鲁木齐10月14日电（记者潘莹、宿传义、高晗）金秋十月，天山南北棉花吐絮，迎来采收。在塔克拉玛干沙漠北缘的尉犁县“超级棉田”，伴随着一台台采棉机来回穿梭，洁白的棉花被采摘、压缩、打包，朵絮归仓。\n\n  “前不久，田里用上一款新款农业无人机，不需要飞手操作，棉花采收环节更加智能化。”“超级棉田”项目负责人艾海鹏说。\n\n  新疆是中国最大优质棉花生产基地，2025年新疆棉花产量占全国产量的92.8%，总产、单产连续32年居全国第一。如今，在新疆，这样的智慧化场景正逐渐贯穿棉花生产全过程，并加速从示范走向普及，一批懂技术、善经营、会管理的“新一代棉农”应运而生。\n\n  在新疆巴音郭楞蒙古自治州尉犁县“超级棉田”中，农业无人机在田间喷洒脱叶剂（2026年9月20日摄，无人机照片）。新华社发（汪志鹏 摄）\n\n  尉犁县气候干燥、光热充足，是中国优质商品棉种植基地，棉花种植面积稳定在100多万亩。2021年，在尉犁县支持下，农业机器人企业极飞科技启动“超级棉田”项目，派出艾海鹏、凌磊两位“90后”管理经营3000亩棉田，探索可复制、可推广的无人化农业管理模式。\n\n  两人从解决棉花管理中最耗人工的灌溉难题入手，持续升级无人化、智能化监测管理的新技术、新设备，让“超级棉田”管理模式与大规模棉花种植高度适配，实现产量更高、品质更优。\n\n  “通过多年努力，‘超级棉田’已实现水、肥、药的智能化管理，目前管理环节无人化作业率已达75%。”艾海鹏说。截至2025年底，“超级棉田”的栽培管理模式在全疆推广面积已超200万亩。\n\n  今年，“超级棉田”又更新了一批新装备：耕种环节用上最新的APC4自驾仪，播种机可自动断膜断带，进一步节省人工。最让管理者津津乐道的，当属X150新型农业无人机。这款无人机可自动配药、加药、充电、规划航线、自主喷药作业，适配除草、防虫、防病等一系列田间需求。\n\n  在棉花吐絮关键期，记者在“超级棉田”作业现场看到，艾海鹏在手机上选好模板、点击“立即开始”，机器人便自主起降、补能，既不需要飞手，也不需要遥控器。手机屏上，药箱空满状态和地面药罐余量一目了然。\n\n  “往年打药虽然也用无人机，但还需要飞手控制轨迹、及时补药换电池。现在把飞机放这儿就不用管了。晚上回去睡觉，第二天早上过来，它已经按要求完成了全部植保任务。”艾海鹏说，目前这款新型农业无人机已在全国推广。\n\n  “我们的目的是想要吸引越来越多年轻人回到农业这一行业。一个行业有年轻人加入，才能有朝气，有更大的发展空间。”艾海鹏说。\n\n  在新疆巴音郭楞蒙古自治州尉犁县“超级棉田”中，采棉机在采收棉花（2026年10月14日摄，无人机照片）。新华社发\n\n  在天山北麓的昌吉市佃坝镇东沟村，“90后”家庭农场主郭腾正盯着屏幕，调度巨大的采棉机在棉海里缓缓行进，源源不断吐出打包好的棉包。\n\n  郭腾是土生土长的昌吉人，一家两代人的种棉经历，正是新疆棉花从“靠人力”到“靠科技”转型发展的鲜活缩影。\n\n  他说，父辈种棉是实打实的苦差事：棉田管护加采收要投入大量人工，采收成本高，种植户收入却很有限。\n\n  “如今农村可发展的空间大了。”郭腾介绍，自己毕业后在城里闯荡过一段时间，随着新疆棉田科技含量越来越高，看到新一代棉农正面临机遇无限的职业图景，决定回乡种棉花。\n\n  如今，郭腾的家庭农场已配齐整套自主农机：4台采棉机、6台植保无人机、十余台播种机、3台大马力拖拉机；棉田用上水肥一体化精准滴灌、无人机植保，犁地、播种、打药、采收，全流程机械化。\n\n  “一台采棉机一天能收400至450亩，每亩采收环节油费加人工成本仅60元。”郭腾说，他承包的2.5万亩棉田日常管护只需50名工人，自己在手机上就能查看田间情况、调度农机作业。\n\n  返乡种棉正成为越来越多年轻人的选择。郭腾发现，与他长期合作的团队里，返乡年轻人越来越多。“只要掌握技术，采棉季每月赚5万元不成问题。”他说。\n\n  随着越来越多科技装备、先进技术在新疆广袤棉田推广普及，新疆棉田加速智慧化，更多年轻人在天山南北的棉田里，找到创业舞台。","新华社 2026 年 10 月 15 日","2026-10-14T23:50:00Z",{"impact":121,"substance":324,"depth":71,"authority":16,"freshness":18,"relevant":21,"comment":325},20,"央媒实地报道，以新疆超级棉田与新一代棉农为样本，呈现农业无人机自主作业与无人化管理模式从示范走向普及的产业级进展，数据与多方信源扎实，具主题聚合价值。",[327],{"name":321,"url":318},[128,329,26,330,331],"农业无人机","无人化农场","新疆棉田",{"code":39,"slug":82,"name":83,"path":84,"parent_code":85},[],{"status":88,"locked":13,"version":34,"method":35,"evidence":335},{"candidates":336,"agricultural_evidence":41},[337,341,347,353],{"code":39,"score":40,"supported":41,"title":338,"abstract":339,"tags":340},[],[26],[26],{"code":342,"score":55,"supported":41,"title":343,"abstract":344,"tags":346},"A4",[],[345],"花生",[],{"code":348,"score":55,"supported":41,"title":349,"abstract":350,"tags":352},"G2",[],[351],"家庭农场",[],{"code":164,"score":21,"supported":13,"title":354,"abstract":355,"tags":356},[],[],[128],[358,359],"新疆 超级棉田 极飞科技","尉犁县 智慧棉田 无人机","新疆超级棉田极飞科技-5031","2026-10-16T00:13:02.993245Z",{"id":363,"title":364,"url":365,"summary":366,"summary_zh":8,"content":8,"source_name":367,"source_url":8,"published_at":8,"category":181,"cover_url":8,"hotness":12,"is_selected":13,"score":368,"score_detail":369,"sources":372,"tags":374,"primary_topic":378,"secondary_topics":379,"classification":385,"search_phrases":408,"slug":411,"view_count":109,"doi":8,"paper":412,"created_at":420},4966,"基于改进YOLO 11n模型的棉花田间复杂环境障碍物检测方法","http:\u002F\u002Fwww.qikanzj.com\u002Fhek\u002Fnyjxxb\u002Fmulu\u002F455619.html","韩科立、王振坤等(中国农业机械化科学研究院集团有限公司;现代农装科技股份有限公司;农业装备技术全国重点实验室)针对棉花田间复杂环境障碍物被遮挡致准确检测难、边缘设备算力有限的问题,提出一种基于改进YOLO 11n模型的田间障碍物检测方法。采用StarNet作为主要特征提取网络并引入DBA模块增强多尺度特征交互能力;使用KAGNConv替换C3k2瓶颈结构增强灵活性与可解释性;集成分离与增强注意力模块SEAM至检测头增强遮挡场景能力。试验结果表明,改进模型YOLO 11n-SKS精确率、召回率、mAP50、mAP50-95分别提升2.3、2.1、1.3、1.4个百分点,达到91.7%、88.3%、91.9%、62.3%。","《农业机械学报》",71,{"impact":122,"substance":370,"depth":183,"authority":72,"freshness":123,"relevant":21,"comment":371},21,"改进YOLO 11n实现棉花田间遮挡障碍物检测，方法新颖、指标提升明确，属农业人工智能细分领域实质进展，但发布日期未知、时效性偏弱。",[373],{"name":367,"url":365},[128,375,26,376,377],"农业人工智能","障碍物检测","采棉机",{"code":39,"slug":82,"name":83,"path":84,"parent_code":85},[380],{"code":289,"slug":381,"name":382,"path":383,"parent_code":384},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":88,"locked":13,"version":34,"method":35,"evidence":386},{"candidates":387,"agricultural_evidence":41},[388,392,397,404],{"code":39,"score":17,"supported":41,"title":389,"abstract":390,"tags":391},[26],[26],[26],{"code":289,"score":17,"supported":41,"title":393,"abstract":395,"tags":396},[394],"YOLO",[394],[375],{"code":398,"score":58,"supported":41,"title":399,"abstract":400,"tags":403},"F5",[],[401,402],"农业机械","机械化",[],{"code":164,"score":21,"supported":13,"title":405,"abstract":406,"tags":407},[],[],[128],[409,410],"中国农业机械化科学研究院 采棉机 障碍物检测","YOLO 11n 棉花 田间障碍物","中国农业机械化科学研究院采棉机障碍物检测-4966",{"doi":8,"openalex_id":8,"authors":413,"venue":8,"cited_by_count":109,"oa_url":8,"card":414,"direction":311,"ingested_from":419},[],{"tldr":415,"method":416,"finding":417,"direction":311,"opportunity":418},"提出改进YOLO 11n模型，实现棉花田间复杂遮挡环境下障碍物高精度检测。","以StarNet为骨干，引入DBA、KAGNConv与SEAM注意力模块，改进Y","改进模型精确率91.7%、召回率88.3%、mAP50达91.9%，各项指标均提升。","可探索轻量化模型在边缘设备实时部署，并扩展至多作物多类障碍物检测。","agent","2026-10-15T00:06:08.577388Z"]