[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"taxonomy":3,"taxonomy-items:\u002Ftopic\u002Fenvironment\u002Fsoil?technology=%E5%A4%9A%E6%A8%A1%E6%80%81":570,"taxonomy-facets:H2:":619},{"version":4,"topics":5},"2026-10-22.2",[6,71,127,199,270,331,387,433,479,533],{"code":7,"slug":8,"name":9,"path":10,"parent_code":11,"description":12,"count":13,"children":14},"I","digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",null,"浏览数字农业与前沿技术相关政策、产业动态与研究。",1341,[15,23,31,39,47,55,63],{"code":16,"slug":17,"name":18,"path":19,"parent_code":7,"description":20,"count":21,"children":22},"I1","smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture","智慧农业总体路径、模式与数字化转型",112,[],{"code":24,"slug":25,"name":26,"path":27,"parent_code":7,"description":28,"count":29,"children":30},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","人工智能算法、大模型与决策支持系统",634,[],{"code":32,"slug":33,"name":34,"path":35,"parent_code":7,"description":36,"count":37,"children":38},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","卫星与无人机遥感、长势监测与产量估测",325,[],{"code":40,"slug":41,"name":42,"path":43,"parent_code":7,"description":44,"count":45,"children":46},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis","地理信息、空间统计与区域计量方法",69,[],{"code":48,"slug":49,"name":50,"path":51,"parent_code":7,"description":52,"count":53,"children":54},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot","农业传感器、物联网组网与边缘计算",155,[],{"code":56,"slug":57,"name":58,"path":59,"parent_code":7,"description":60,"count":61,"children":62},"I6","digital-village","数字乡村与数据要素","\u002Ftopic\u002Fdigital-agriculture\u002Fdigital-village","数字乡村建设、数字鸿沟与数据治理",151,[],{"code":64,"slug":65,"name":66,"path":67,"parent_code":7,"description":68,"count":69,"children":70},"I7","research-methods","研究方法与评估","\u002Ftopic\u002Fdigital-agriculture\u002Fresearch-methods","综述、文献计量与因果识别方法",2,[],{"code":72,"slug":73,"name":74,"path":75,"parent_code":11,"description":76,"count":77,"children":78},"F","inputs-equipment","农业投入品与装备","\u002Ftopic\u002Finputs-equipment","浏览农业投入品与装备相关政策、产业动态与研究。",608,[79,87,95,103,111,119],{"code":80,"slug":81,"name":82,"path":83,"parent_code":72,"description":84,"count":85,"children":86},"F1","seed-industry","种业与品种管理","\u002Ftopic\u002Finputs-equipment\u002Fseed-industry","种质资源、品种审定与知识产权",162,[],{"code":88,"slug":89,"name":90,"path":91,"parent_code":72,"description":92,"count":93,"children":94},"F2","biotechnology","生物育种与基因技术","\u002Ftopic\u002Finputs-equipment\u002Fbiotechnology","分子设计育种、基因编辑与合成生物",63,[],{"code":96,"slug":97,"name":98,"path":99,"parent_code":72,"description":100,"count":101,"children":102},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","施肥技术、化肥减量与新型肥料",88,[],{"code":104,"slug":105,"name":106,"path":107,"parent_code":72,"description":108,"count":109,"children":110},"F4","crop-protection","农药与绿色防控","\u002Ftopic\u002Finputs-equipment\u002Fcrop-protection","农药管理、绿色植保与生物防治",135,[],{"code":112,"slug":113,"name":114,"path":115,"parent_code":72,"description":116,"count":117,"children":118},"F5","machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","农机装备、机械化作业与导航",121,[],{"code":120,"slug":121,"name":122,"path":123,"parent_code":72,"description":124,"count":125,"children":126},"F6","agricultural-robots","机器人与无人农场","\u002Ftopic\u002Finputs-equipment\u002Fagricultural-robots","农业机器人、无人农场与智能作业",36,[],{"code":128,"slug":129,"name":130,"path":131,"parent_code":11,"description":132,"count":133,"children":134},"H","environment","资源环境与气候变化","\u002Ftopic\u002Fenvironment","浏览资源环境与气候变化相关政策、产业动态与研究。",672,[135,143,151,159,167,175,183,191],{"code":136,"slug":137,"name":138,"path":139,"parent_code":128,"description":140,"count":141,"children":142},"H1","farmland","耕地保护与高标准农田","\u002Ftopic\u002Fenvironment\u002Ffarmland","耕地数量质量、高标准农田与农田建设",29,[],{"code":144,"slug":145,"name":146,"path":147,"parent_code":128,"description":148,"count":149,"children":150},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","土壤理化生物性状、盐碱地治理与固碳",207,[],{"code":152,"slug":153,"name":154,"path":155,"parent_code":128,"description":156,"count":157,"children":158},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","水资源配置、节水灌溉与旱作农业",150,[],{"code":160,"slug":161,"name":162,"path":163,"parent_code":128,"description":164,"count":165,"children":166},"H4","carbon","农业碳与绿色低碳","\u002Ftopic\u002Fenvironment\u002Fcarbon","碳排放核算、碳汇与绿色转型",44,[],{"code":168,"slug":169,"name":170,"path":171,"parent_code":128,"description":172,"count":173,"children":174},"H5","waste","面源污染与废弃物利用","\u002Ftopic\u002Fenvironment\u002Fwaste","面源污染治理与秸秆粪污等废弃物利用",8,[],{"code":176,"slug":177,"name":178,"path":179,"parent_code":128,"description":180,"count":181,"children":182},"H6","biodiversity","生态保护与生物多样性","\u002Ftopic\u002Fenvironment\u002Fbiodiversity","生态系统修复、生物多样性与土地利用变化",45,[],{"code":184,"slug":185,"name":186,"path":187,"parent_code":128,"description":188,"count":189,"children":190},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","气候变化影响、气候韧性农业与灾害预警",197,[],{"code":192,"slug":193,"name":194,"path":195,"parent_code":128,"description":196,"count":197,"children":198},"H8","sustainable-agriculture","可持续与保护性农业","\u002Ftopic\u002Fenvironment\u002Fsustainable-agriculture","可持续生产模式与保护性耕作",40,[],{"code":200,"slug":201,"name":202,"path":203,"parent_code":11,"description":204,"count":205,"children":206},"A","field-crops","大田作物","\u002Ftopic\u002Ffield-crops","浏览大田作物相关政策、产业动态与研究。",1227,[207,215,223,231,239,247,255,262],{"code":208,"slug":209,"name":210,"path":211,"parent_code":200,"description":212,"count":213,"children":214},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","以水稻为对象的生产、育种、植保、机械化与产业内容",337,[],{"code":216,"slug":217,"name":218,"path":219,"parent_code":200,"description":220,"count":221,"children":222},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","小麦及冬春麦区相关生产与科研",144,[],{"code":224,"slug":225,"name":226,"path":227,"parent_code":200,"description":228,"count":229,"children":230},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","玉米生产、育种、密植高产与复合种植",189,[],{"code":232,"slug":233,"name":234,"path":235,"parent_code":200,"description":236,"count":237,"children":238},"A4","soybean-oilseeds","大豆与油料","\u002Ftopic\u002Ffield-crops\u002Fsoybean-oilseeds","大豆、油菜、花生、向日葵、芝麻等油料与蛋白作物",166,[],{"code":240,"slug":241,"name":242,"path":243,"parent_code":200,"description":244,"count":245,"children":246},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","马铃薯、甘薯、高粱、谷子、荞麦等薯类杂粮",92,[],{"code":248,"slug":249,"name":250,"path":251,"parent_code":200,"description":252,"count":253,"children":254},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","棉花、甘蔗、烟草、蚕桑等工业原料型作物",87,[],{"code":256,"slug":257,"name":258,"path":259,"parent_code":200,"description":260,"count":141,"children":261},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","饲草产业与间套轮作、连作障碍等种植制度",[],{"code":263,"slug":264,"name":265,"path":266,"parent_code":200,"description":267,"count":268,"children":269},"A8","yield-food-security","单产提升与粮食安全","\u002Ftopic\u002Ffield-crops\u002Fyield-food-security","单产行动、产能建设与粮食安全、收购形势",143,[],{"code":271,"slug":272,"name":273,"path":274,"parent_code":11,"description":275,"count":276,"children":277},"B","horticulture","园艺作物","\u002Ftopic\u002Fhorticulture","浏览园艺作物相关政策、产业动态与研究。",531,[278,285,293,301,308,315,323],{"code":279,"slug":280,"name":281,"path":282,"parent_code":271,"description":283,"count":189,"children":284},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","蔬菜育种、栽培、病虫害与产业",[],{"code":286,"slug":287,"name":288,"path":289,"parent_code":271,"description":290,"count":291,"children":292},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","苹果、柑橘、猕猴桃、葡萄、热带亚热带果树",147,[],{"code":294,"slug":295,"name":296,"path":297,"parent_code":271,"description":298,"count":299,"children":300},"B3","tea-coffee","茶叶与咖啡","\u002Ftopic\u002Fhorticulture\u002Ftea-coffee","茶叶、咖啡、可可等饮品原料作物",51,[],{"code":302,"slug":303,"name":304,"path":305,"parent_code":271,"description":306,"count":125,"children":307},"B4","flowers","花卉与观赏植物","\u002Ftopic\u002Fhorticulture\u002Fflowers","花卉产业、月季等观赏园艺",[],{"code":309,"slug":310,"name":311,"path":312,"parent_code":271,"description":313,"count":141,"children":314},"B5","mushrooms","食用菌","\u002Ftopic\u002Fhorticulture\u002Fmushrooms","食用菌菌种、栽培与产业",[],{"code":316,"slug":317,"name":318,"path":319,"parent_code":271,"description":320,"count":321,"children":322},"B6","medicinal-plants","中药材与药食同源","\u002Ftopic\u002Fhorticulture\u002Fmedicinal-plants","道地药材、药用植物与药食同源开发",22,[],{"code":324,"slug":325,"name":326,"path":327,"parent_code":271,"description":328,"count":329,"children":330},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture","设施化保护地生产与植物工厂、无土栽培、都市农业",67,[],{"code":332,"slug":333,"name":334,"path":335,"parent_code":11,"description":336,"count":337,"children":338},"C","livestock","畜牧兽医","\u002Ftopic\u002Flivestock","浏览畜牧兽医相关政策、产业动态与研究。",198,[339,347,355,363,371,379],{"code":340,"slug":341,"name":342,"path":343,"parent_code":332,"description":344,"count":345,"children":346},"C1","pigs","生猪","\u002Ftopic\u002Flivestock\u002Fpigs","生猪养殖、产能与产业形势",14,[],{"code":348,"slug":349,"name":350,"path":351,"parent_code":332,"description":352,"count":353,"children":354},"C2","ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants","奶牛、肉牛、羊养殖与奶业",47,[],{"code":356,"slug":357,"name":358,"path":359,"parent_code":332,"description":360,"count":361,"children":362},"C3","poultry","家禽","\u002Ftopic\u002Flivestock\u002Fpoultry","蛋鸡、肉鸡、水禽养殖",18,[],{"code":364,"slug":365,"name":366,"path":367,"parent_code":332,"description":368,"count":369,"children":370},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","饲料安全、蛋白饲料与饲草供给",35,[],{"code":372,"slug":373,"name":374,"path":375,"parent_code":332,"description":376,"count":377,"children":378},"C5","animal-health","疫病防控与兽药","\u002Ftopic\u002Flivestock\u002Fanimal-health","动物疫病、疫苗、兽药与人兽共患病",50,[],{"code":380,"slug":381,"name":382,"path":383,"parent_code":332,"description":384,"count":385,"children":386},"C6","smart-livestock","养殖环境与智慧畜牧","\u002Ftopic\u002Flivestock\u002Fsmart-livestock","粪污资源化、动物福利与智能化养殖",10,[],{"code":388,"slug":389,"name":390,"path":391,"parent_code":11,"description":392,"count":197,"children":393},"D","aquaculture","渔业水产","\u002Ftopic\u002Faquaculture","浏览渔业水产相关政策、产业动态与研究。",[394,402,410,418,426],{"code":395,"slug":396,"name":397,"path":398,"parent_code":388,"description":399,"count":400,"children":401},"D1","pond-factory-aquaculture","池塘与工厂化养殖","\u002Ftopic\u002Faquaculture\u002Fpond-factory-aquaculture","池塘养殖、循环水与设施渔业",4,[],{"code":403,"slug":404,"name":405,"path":406,"parent_code":388,"description":407,"count":408,"children":409},"D2","offshore-aquaculture","深远海养殖与海洋牧场","\u002Ftopic\u002Faquaculture\u002Foffshore-aquaculture","深远海养殖工船、海洋牧场与渔业资源",5,[],{"code":411,"slug":412,"name":413,"path":414,"parent_code":388,"description":415,"count":416,"children":417},"D3","integrated-aquaculture","稻渔种养与生态渔业","\u002Ftopic\u002Faquaculture\u002Fintegrated-aquaculture","稻渔综合种养、增殖渔业与生态养殖",12,[],{"code":419,"slug":420,"name":421,"path":422,"parent_code":388,"description":423,"count":424,"children":425},"D4","aquatic-health","水质与病害","\u002Ftopic\u002Faquaculture\u002Faquatic-health","养殖水质调控与水生动物病害防控",0,[],{"code":427,"slug":428,"name":429,"path":430,"parent_code":388,"description":431,"count":69,"children":432},"D5","smart-aquaculture","智慧渔业","\u002Ftopic\u002Faquaculture\u002Fsmart-aquaculture","渔业数字化、智能投喂与养殖装备",[],{"code":434,"slug":435,"name":436,"path":437,"parent_code":11,"description":438,"count":439,"children":440},"E","food-supply","农产品加工与流通","\u002Ftopic\u002Ffood-supply","浏览农产品加工与流通相关政策、产业动态与研究。",107,[441,449,457,464,471],{"code":442,"slug":443,"name":444,"path":445,"parent_code":434,"description":446,"count":447,"children":448},"E1","food-processing","加工与食品制造","\u002Ftopic\u002Ffood-supply\u002Ffood-processing","初加工、精深加工与食品制造工艺",25,[],{"code":450,"slug":451,"name":452,"path":453,"parent_code":434,"description":454,"count":455,"children":456},"E2","nutrition","营养与功能食品","\u002Ftopic\u002Ffood-supply\u002Fnutrition","膳食营养、功能成分与大食物观",1,[],{"code":458,"slug":459,"name":460,"path":461,"parent_code":434,"description":462,"count":416,"children":463},"E3","cold-chain","冷链仓储物流","\u002Ftopic\u002Ffood-supply\u002Fcold-chain","保鲜包装、冷链与粮食仓储物流",[],{"code":465,"slug":466,"name":467,"path":468,"parent_code":434,"description":469,"count":369,"children":470},"E4","food-safety","质量安全与溯源","\u002Ftopic\u002Ffood-supply\u002Ffood-safety","质量安全检测、农药残留与全链条追溯",[],{"code":472,"slug":473,"name":474,"path":475,"parent_code":434,"description":476,"count":477,"children":478},"E5","branding-commerce","品牌流通与电商","\u002Ftopic\u002Ffood-supply\u002Fbranding-commerce","品牌建设、产销对接与农村电商",33,[],{"code":480,"slug":481,"name":482,"path":483,"parent_code":11,"description":484,"count":485,"children":486},"G","rural-services","农业服务与乡村发展","\u002Ftopic\u002Frural-services","浏览农业服务与乡村发展相关政策、产业动态与研究。",344,[487,495,502,510,518,526],{"code":488,"slug":489,"name":490,"path":491,"parent_code":480,"description":492,"count":493,"children":494},"G1","extension-transfer","农技推广与成果转化","\u002Ftopic\u002Frural-services\u002Fextension-transfer","农技推广体系、科技特派员与科技小院",139,[],{"code":496,"slug":497,"name":498,"path":499,"parent_code":480,"description":500,"count":439,"children":501},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","托管服务、土地流转与新型经营主体",[],{"code":503,"slug":504,"name":505,"path":506,"parent_code":480,"description":507,"count":508,"children":509},"G3","rural-finance","农村金融与保险","\u002Ftopic\u002Frural-services\u002Frural-finance","信贷担保、农业保险与财政支农",20,[],{"code":511,"slug":512,"name":513,"path":514,"parent_code":480,"description":515,"count":516,"children":517},"G4","rural-industry","乡村产业与县域经济","\u002Ftopic\u002Frural-services\u002Frural-industry","乡村产业、三产融合与县域经济",28,[],{"code":519,"slug":520,"name":521,"path":522,"parent_code":480,"description":523,"count":524,"children":525},"G5","rural-governance","乡村治理与人才","\u002Ftopic\u002Frural-services\u002Frural-governance","乡村治理、数字治理与人才培养",11,[],{"code":527,"slug":528,"name":529,"path":530,"parent_code":480,"description":531,"count":321,"children":532},"G6","rural-integration","帮扶与城乡融合","\u002Ftopic\u002Frural-services\u002Frural-integration","常态化帮扶、区域协作与农民增收",[],{"code":534,"slug":535,"name":536,"path":537,"parent_code":11,"description":538,"count":539,"children":540},"J","policy","政策与宏观","\u002Ftopic\u002Fpolicy","浏览政策与宏观相关政策、产业动态与研究。",132,[541,548,555,562],{"code":542,"slug":543,"name":544,"path":545,"parent_code":534,"description":546,"count":408,"children":547},"J1","policy-planning","政策制度与发展规划","\u002Ftopic\u002Fpolicy\u002Fpolicy-planning","部委政策、规划文件与解读",[],{"code":549,"slug":550,"name":551,"path":552,"parent_code":534,"description":553,"count":447,"children":554},"J2","modernization","农业强国与现代化","\u002Ftopic\u002Fpolicy\u002Fmodernization","农业强国、农业农村现代化与新质生产力",[],{"code":556,"slug":557,"name":558,"path":559,"parent_code":534,"description":560,"count":400,"children":561},"J3","global-agriculture","国际合作与全球农业","\u002Ftopic\u002Fpolicy\u002Fglobal-agriculture","国际农业合作与国别农业研究",[],{"code":563,"slug":564,"name":565,"path":566,"parent_code":534,"description":567,"count":568,"children":569},"J4","seasonal-agriculture","农时与节庆活动","\u002Ftopic\u002Fpolicy\u002Fseasonal-agriculture","农时生产调度、丰收节与消费季",98,[],{"total":455,"page":455,"page_size":508,"items":571},[572],{"id":573,"title":574,"url":575,"summary":576,"summary_zh":11,"content":577,"source_name":578,"source_url":11,"published_at":579,"category":580,"cover_url":11,"hotness":385,"is_selected":581,"score":329,"score_detail":582,"sources":584,"tags":586,"primary_topic":592,"secondary_topics":593,"classification":594,"search_phrases":614,"slug":617,"view_count":605,"doi":11,"paper":11,"created_at":618},373,"基于多模态时空对齐与因果利润建模的农业投入优化(MAION)","https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994","中国农业大学付正捷、张誉恒等于Sensors发表针对智慧农业投入优化的多模态网络MAION。该框架构建统一的'地块-时间窗'农业状态表示,通过跨模态时空对齐模块解决田间图像、气象环境、土壤状态和田间管理记录之间采样频率不一致、语义尺度异构问题;通过投入-产出因果利润建模模块评估不同投入行为对产量、成本和净利润的潜在影响;并以利润驱动的强化学习生成面向长期净收益最大化的投入策略。在产量、成本和净利润预测上RMSE分别为0.587、0.531和0.648,R2达0.914\u002F0.891\u002F0.883;经济决策中净收益改善17.68%,投入产出比1.71,显著优于随机森林、XGBoost、LSTM、GRU和Transformer等基线。","## 1. Introduction\n\nWith the continuous advancement of smart agriculture, agricultural production is shifting from experience-dependent judgment toward integrated management supported by data, models, and intelligent decision-making [[1](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B1-sensors-26-04994)]. Internet of Things sensors, unmanned aerial vehicle remote sensing, field image acquisition devices, meteorological monitoring systems, and agricultural management platforms have been increasingly deployed in farmland and orchard production scenarios, enabling continuous recording of soil moisture, temperature and humidity, light intensity, rainfall, crop growth status, pest and disease conditions, irrigation and fertilization records, and pesticide application information [[2](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B2-sensors-26-04994)]. These data provide a fine-grained perception basis for precision agriculture and allow crop growth processes and farmland environmental changes to be understood more comprehensively [[3](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B3-sensors-26-04994)]. However, data availability does not necessarily mean that collected data can be directly transformed into effective decisions [[4](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B4-sensors-26-04994)]. In practical production, managers are usually concerned not only with the accurate prediction of a single indicator, but also with how fertilization, irrigation, and pesticide application should be arranged under current crop status, meteorological conditions, and soil background so that input costs can be controlled while yield and quality are maintained [[5](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B5-sensors-26-04994)]. With increasing production costs, tightening resource constraints, and intensifying climate variability, simply pursuing yield maximization is no longer sufficient for modern agricultural management. A more reasonable balance among yield, cost, resource utilization, and net profit has therefore become an important issue in smart agricultural decision-making research [[6](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B6-sensors-26-04994)].\n\nTraditional agricultural management usually relies on farmer experience, expert rules, and statistical analysis models [[7](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B7-sensors-26-04994)]. Experience-driven methods are widely used because of their direct operation and low implementation cost, but their effectiveness depends heavily on personal experience and shows limited adaptability to climate variation, plot heterogeneity, and crop growth-stage changes [[8](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B8-sensors-26-04994)]. Expert systems can provide recommendations for irrigation, fertilization, and pest or disease control according to predefined rules; however, their rule structures are usually fixed and may lack flexibility when complex coupling relationships exist among environmental variables, crop states, and input behaviors. Statistical models and production function models can analyze relationships between agricultural inputs and outputs, but they often rely on linear or static assumptions and are insufficient for describing nonlinear responses, time-lag effects, and stage-dependent differences in agricultural systems [[9](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B9-sensors-26-04994)]. Moreover, many traditional methods still focus on a single production indicator, such as yield, disease incidence, or soil moisture, while the joint relationships among crop status, environmental conditions, input behavior, and economic return are rarely considered. Therefore, traditional methods remain inadequate for multi-source data fusion, dynamic input optimization, and profit-oriented intelligent decision-making [[10](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B10-sensors-26-04994)].\n\nDeep learning has provided a new technical pathway for smart agriculture and has been widely applied to crop recognition, pest and disease detection, yield prediction, quality assessment, and environmental monitoring [[11](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B11-sensors-26-04994)]. Convolutional neural networks can extract crop growth, canopy structure, and disease features from field images and unmanned aerial vehicle remote sensing images, while recurrent neural networks, long short-term memory networks, and Transformer models can process meteorological, soil, and crop growth time-series data. Multimodal learning methods have further attempted to integrate images, sensor data, and management records to improve agricultural state perception and yield prediction [[12](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B12-sensors-26-04994)]. These studies have promoted the transition from manual observation to automated analysis, but limitations remain in input optimization. Several recent studies have explored causal modeling, reinforcement learning, and multimodal learning for agricultural or related complex decision-making tasks. Zhang et al. [[13](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B13-sensors-26-04994)] proposed the CMRL causal meta-reinforcement learning framework, integrating reinforcement learning feedback, causal intervention, and meta-learning optimization for multimodal remote sensing classification, with overall accuracies of\n\n$86.27 \\%$\n,\n\n$95.51 \\%$\n, and\n\n$99.41 \\%$\non the MUUFL, Houston, and Trento datasets, respectively. Liu et al. [[14](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B14-sensors-26-04994)] proposed the ASGO-PAPIS framework, which combined deep learning and causal inference for multidimensional dairy production cost analysis and improved Precision, NDCG, and MAP by up to approximately 5 percentage points. Zhang et al. [[15](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B15-sensors-26-04994)] developed a cross-modal attention and PPO reinforcement learning framework for pesticide application optimization by fusing unmanned aerial vehicle hyperspectral data, soil meteorological data, and pest monitoring data, achieving an RMSE of\n\n$0.162$\n, a spraying accuracy of\n\n$88.3 \\%$\n, an\n\n$18.3 \\%$\nreduction in pesticide usage, and a pest suppression effect of\n\n$77.9 \\%$\n.\n\nAlthough multimodal learning, causal inference, and reinforcement learning have each demonstrated considerable potential for intelligent agricultural management, they address different stages of the decision-making process and therefore exhibit complementary strengths as well as inherent limitations. Multimodal fusion effectively integrates heterogeneous information from crop images, environmental observations, soil conditions, and management records, enabling comprehensive agricultural state perception [[16](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B16-sensors-26-04994)]. However, it primarily models statistical correlations and cannot reliably determine how changes in irrigation, fertilization, or pesticide application causally affect agricultural productivity and economic returns. Causal inference alleviates confounding effects caused by weather variability, soil heterogeneity, and management differences, providing more reliable estimates of intervention effects. Nevertheless, existing causal approaches mainly focus on effect estimation rather than generating optimal sequential management strategies throughout an entire growing season [[17](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B17-sensors-26-04994)]. Reinforcement learning is naturally suitable for optimizing long-term agricultural decisions, yet its performance strongly depends on accurate state representations and reliable reward signals. Inaccurate perception or biased intervention estimation may consequently result in unstable or economically suboptimal policies. Therefore, these three paradigms should be regarded as complementary rather than competing approaches. A unified framework integrating multimodal perception, causal reasoning, and reinforcement learning can simultaneously achieve comprehensive agricultural state representation, reliable intervention effect estimation, and long-term profit-oriented decision optimization.\n\nAccordingly, a multimodal causal reinforcement learning framework for agricultural input–profit optimization, namely the Multimodal Agricultural Input–Output Optimization Network, abbreviated as MAION, is proposed in this study. Visual data, environmental data, soil data, and agricultural management records are used as inputs, while yield, cost, net profit, and optimal input strategies are taken as outputs. An end-to-end modeling method from multi-source agricultural perception to economically optimal decision-making is thereby constructed. Unlike models that focus only on yield prediction or state recognition, MAION incorporates agricultural input behavior, production cost, and economic return into a unified learning objective. Through cross-modal spatiotemporal alignment, causal input–profit modeling, and profit-driven reinforcement learning decision-making, agricultural intelligent perception is connected with practical production decisions, thereby providing an executable modeling strategy for precision input, cost control, and net profit improvement. The main contributions of this study are summarized as follows:\n\n*   To address the lack of unified agricultural state representation caused by heterogeneous data sources with inconsistent temporal and semantic characteristics, a unified multimodal agricultural input–output modeling framework is developed to support profit-oriented decision making.\n\n*   To address the spatiotemporal inconsistency among crop images, environmental observations, soil measurements, and management records, a cross-modal spatiotemporal alignment strategy is introduced to establish consistent multimodal agricultural representations.\n\n*   To address the inability of existing predictive models to distinguish causal intervention effects from statistical correlations, a causal-aware input–profit modeling mechanism is developed to provide more reliable estimation of the economic effects of agricultural management actions.\n\n*   To address the limitation of conventional optimization methods in achieving long-term economic management, a profit-driven reinforcement learning strategy is designed to optimize sequential agricultural input decisions under long-term profit objectives.\n\n*   To address the challenge of robust deployment in practical agricultural environments, comprehensive cross-plot, cross-year, and missing-modality experiments are conducted to validate the generalization capability and practical effectiveness of the proposed framework.\n\n## 2. Related Work\n\n### 2.1. Multimodal Perception Methods in Smart Agriculture\n\nMultimodal perception in smart agriculture refers to the continuous observation and integrated representation of agricultural production systems using heterogeneous data sources, including images, sensors, remote sensing, and management records [[18](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B18-sensors-26-04994)]. Although these data differ in acquisition frequency, spatial coverage, and semantic level, they jointly provide important information for agricultural state perception [[19](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B19-sensors-26-04994)]. Therefore, multimodal perception is valuable not only because more data types are introduced, but also because complementary information from different sources can be used to identify crop growth status, environmental changes, and production risks more reliably [[20](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B20-sensors-26-04994)]. Image-based agricultural perception methods have been widely studied [[21](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B21-sensors-26-04994)]. Convolutional neural networks can automatically extract texture, color, edge, and morphological features from crop images, and have been applied to disease recognition, fruit detection, weed identification, and quality grading [[22](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B22-sensors-26-04994)]. Vision Transformers further improve the representation of long-range regional dependencies and complex background information, thereby enhancing adaptability under occlusion, illumination variation, and scale differences in field environments [[23](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B23-sensors-26-04994)]. Sensor-based time-series data are also important for greenhouse control, soil moisture monitoring, and crop growth trend analysis, where continuous environmental variables need to be modeled dynamically [[24](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B24-sensors-26-04994)]. Long short term memory (LSTM), gated recurrent unit (GRU), and Transformer models have been adopted to capture long-term dependencies among meteorological variables, soil variables, and growth indicators [[25](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B25-sensors-26-04994)]. Remote sensing methods are more commonly used for regional growth estimation, drought monitoring, and yield assessment through spectral features, vegetation indices, and spatial textures [[26](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B26-sensors-26-04994)]. Despite these advances, most existing studies remain centered on a single modality or a single task [[27](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B27-sensors-26-04994)]. Image models usually focus on disease categories, fruit numbers, or phenotypic traits; sensor models are mainly used for environmental trend prediction or soil state estimation; and remote sensing models emphasize regional crop growth variation [[28](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B28-sensors-26-04994)]. Such fragmented strategies are effective for specific tasks, but they are insufficient for describing the coupled relationships among crops, environments, soils, and management behaviors [[29](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B29-sensors-26-04994)]. For agricultural input–profit optimization, crop growth status or environmental risk alone is not enough; it is also necessary to understand how these states influence fertilization, irrigation, and pesticide application, and how such behaviors are ultimately reflected in yield, cost, and net profit [[30](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B30-sensors-26-04994)]. Accordingly, limitations remain in cross-modal spatiotemporal alignment, unified state representation, and feature fusion oriented toward economic decision-making [[31](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B31-sensors-26-04994),[32](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B32-sensors-26-04994)].\n\n### 2.2. Agricultural Yield Prediction and Input Modeling Methods\n\nAgricultural yield prediction and input modeling aim to estimate crop production by modeling the relationships among environmental conditions, soil properties, management practices, and historical crop growth states [[33](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B33-sensors-26-04994)]. Early studies mainly relied on statistical regression, crop growth models, and production function models to quantify the effects of climate, soil, irrigation, and fertilization on yield [[34](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B34-sensors-26-04994),[35](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B35-sensors-26-04994)]. Although these methods are interpretable, they have limited ability to capture the nonlinear and dynamic interactions among meteorological conditions, soil characteristics, crop varieties, pests, and management practices that jointly determine agricultural production [[36](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B36-sensors-26-04994)]. Recent studies have introduced machine learning and deep learning methods to improve yield modeling [[37](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B37-sensors-26-04994)]. Tree-based models such as Random Forest and XGBoost, together with support vector machines, have demonstrated robust performance on structured agricultural data [[38](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B38-sensors-26-04994)], while sequential models including LSTM, GRU, and Transformer further improve the modeling of temporal dependencies and long-term environmental effects from multi-source observations [[39](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B39-sensors-26-04994),[40](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B40-sensors-26-04994)]. These advances have substantially improved prediction accuracy for agricultural production. However, existing studies remain primarily prediction-oriented. Most methods optimize yield without explicitly considering production costs or economic returns, despite the fact that maximizing yield does not necessarily maximize profit [[41](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B41-sensors-26-04994),[42](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B42-sensors-26-04994)]. In addition, current models generally learn statistical correlations between agricultural inputs and outputs rather than identifying the underlying causal relationships, making them vulnerable to confounding factors such as weather, soil conditions, and management differences [[43](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B43-sensors-26-04994)]. Consequently, they provide limited support for reliable input optimization [[44](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B44-sensors-26-04994)]. To address these limitations, the proposed causal-aware input–profit modeling module treats fertilization, irrigation, and pesticide application as intervenable variables, jointly estimating their effects on yield, cost, and profit from multimodal agricultural state representations, thereby extending agricultural modeling from prediction toward interpretable decision-oriented optimization [[45](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B45-sensors-26-04994)].\n\n### 2.3. Agricultural Economic Optimization and Intelligent Decision-Making Methods\n\nAgricultural economic optimization aims to allocate land, water, fertilizer, pesticides, labor, and other production resources to balance yield, quality, cost, and profit under resource constraints [[46](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B46-sensors-26-04994)]. Traditional approaches mainly rely on production functions, cost–benefit analysis, and input–output efficiency evaluation to quantify the economic effects of agricultural inputs and support production planning [[47](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B47-sensors-26-04994),[48](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B48-sensors-26-04994)]. Although these methods provide clear economic interpretations, they generally assume relatively stable environmental conditions and fixed input–output relationships, making them difficult to apply to real agricultural systems where weather, market conditions, and crop responses vary continuously across growth stages [[49](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B49-sensors-26-04994)]. Consequently, agricultural input optimization is increasingly regarded as a dynamic sequential decision-making problem rather than a static optimization task [[50](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B50-sensors-26-04994)]. Reinforcement learning (RL) provides an effective framework for learning long-term agricultural management strategies by optimizing cumulative rewards through continuous interactions with the environment [[51](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B51-sensors-26-04994),[52](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B52-sensors-26-04994)]. Existing studies formulate crop status, soil conditions, meteorological observations, and historical management records as states [[53](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B53-sensors-26-04994)], while irrigation, fertilization, and pesticide application are treated as actions, enabling optimization of long-term objectives such as yield, quality, resource consumption, and economic return [[54](https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F15\u002F4994#B54-sensors-26-04994)]. Compared with prediction-based approaches, RL is better suited to sta","Sensors 2026-08-06","2026-08-06T00:00:00Z","论文",false,{"impact":416,"substance":508,"depth":361,"authority":416,"freshness":408,"relevant":455,"comment":583},"论文提出多模态时空对齐与因果利润建模的农业投入优化方法，具有创新性，但影响范围限于学术研究，时效性一般。",[585],{"name":578,"url":575},[587,588,589,590,591],"智慧农业","中国农业大学","多模态","强化学习","Sensors",{"code":144,"slug":145,"name":146,"path":147,"parent_code":128},[],{"status":595,"locked":581,"version":4,"method":596,"evidence":597},"classified","rules",{"candidates":598,"agricultural_evidence":600},[599,604,610],{"code":16,"score":400,"supported":600,"title":601,"abstract":602,"tags":603},true,[],[587],[587],{"code":144,"score":605,"supported":600,"title":606,"abstract":607,"tags":609},3,[],[608],"土壤",[],{"code":24,"score":69,"supported":581,"title":611,"abstract":612,"tags":613},[],[],[589,590],[615,616],"中国农业大学 强化学习 智慧农业 多模态","中国农业大学 强化学习","中国农业大学强化学习智慧农业多模态-373","2026-08-10T23:54:46.189166Z",{"technologies":620,"keywords":660},[621,623,625,627,630,633,635,638,640,642,644,646,648,650,652,654,655,656,658],{"name":622,"count":477},"农业人工智能",{"name":624,"count":141},"遥感",{"name":626,"count":516},"精准农业",{"name":628,"count":629},"遥感监测",24,{"name":631,"count":632},"机器学习",16,{"name":634,"count":524},"农业遥感",{"name":636,"count":637},"物联网",7,{"name":639,"count":400},"GIS",{"name":641,"count":605},"农业传感器",{"name":643,"count":69},"深度学习",{"name":645,"count":455},"人工智能",{"name":647,"count":455},"传感器",{"name":649,"count":455},"农业机器人",{"name":651,"count":455},"卫星遥感",{"name":653,"count":455},"图像分割",{"name":589,"count":455},{"name":590,"count":455},{"name":657,"count":455},"无人机遥感",{"name":659,"count":455},"高光谱",[661,663,665,667,669,671,673,675,677,678,680,682],{"name":587,"count":662},74,{"name":664,"count":361},"盐碱地治理",{"name":666,"count":632},"土壤健康",{"name":668,"count":416},"土壤墒情",{"name":670,"count":416},"生物炭",{"name":672,"count":416},"种业振兴",{"name":674,"count":173},"可持续农业",{"name":676,"count":173},"土壤改良",{"name":226,"count":173},{"name":679,"count":637},"根际微生物",{"name":681,"count":637},"粮食安全",{"name":683,"count":684},"农业微生物",6]