[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3050":3,"related-3050":87},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":71,"slug":74,"view_count":75,"doi":8,"paper":76,"created_at":86},3050,"面向再生农业与气候韧性食物系统的可解释数字孪生集成框架","https:\u002F\u002Fwww.mdpi.com\u002F2071-1050\u002F18\u002F18\u002F9645","研究提出集成全球农业基础表征模型（GAFRM）、自演化可解释数字孪生（SEDT）、自演化进化基础优化器（SEEFO）与增强型绿色再生农业可持续性指数（GRASI）的统一计算框架，显式将作物微量营养素密度纳入农业决策架构并建模其与覆盖作物、生物炭施用、免耕等再生实践的关系。框架使用多源全球数据集评估全球约60个代表性国家6大洲15个气候带2000-2026年数据，SEDT达到RMSE 3.18\u002FMAE 2.29\u002FR² 0.972\u002FNSE 0.968；SEEFO获得最高Hypervolume 0.956与最低GD 0.028；通过XAI特征归因建立全透明、可解释决策支持环境。",null,"MDPI Sustainability 18(18):9645","2026-09-20T00:00:00Z","论文",10,false,80,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,13,9,1,"方法新颖、数据规模大且指标可靠，属农业人工智能与气候智慧农业前沿成果，值得进入每日精选。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","可解释AI","数字孪生","气候韧性","再生农业",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"H8","sustainable-agriculture","可持续与保护性农业","\u002Ftopic\u002Fenvironment\u002Fsustainable-agriculture","H",[],{"status":38,"locked":13,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,49,54,61,66],{"code":44,"score":18,"supported":45,"title":46,"abstract":47,"tags":48},"I1",true,[27],[27],[27,25],{"code":31,"score":50,"supported":45,"title":51,"abstract":52,"tags":53},12,[29],[29],[29],{"code":55,"score":56,"supported":45,"title":57,"abstract":58,"tags":60},"J3",3,[],[59],"全球农业",[],{"code":62,"score":20,"supported":13,"title":63,"abstract":64,"tags":65},"H7",[],[],[28],{"code":67,"score":20,"supported":13,"title":68,"abstract":69,"tags":70},"I2",[],[],[26],[72,73],"GAFRM 数字孪生 再生农业","GRASI 气候韧性","GAFRM数字孪生再生农业-3050",2,{"doi":8,"openalex_id":8,"authors":77,"venue":8,"cited_by_count":78,"oa_url":8,"card":79,"direction":83,"ingested_from":85},[],0,{"tldr":80,"method":81,"finding":82,"direction":83,"opportunity":84},"提出集成数字孪生与进化优化的可解释框架，将微量营养素密度纳入再生农业决策。","全球60国2000-2026多源数据，GAFRM+SEDT+SEEFO+GRAS","SEDT预测精度高（R²0.972），SEEFO优化性能最优，实现透明可解释决策支持。","农业人工智能与决策模型","可探索将微量营养素密度与再生实践耦合的实时数字孪生，并验证跨气候带可迁移性。","agent","2026-09-21T00:04:39.490071Z",{"total":88,"page":20,"page_size":88,"items":89},6,[90,199,261,345,450,538],{"id":91,"title":92,"url":93,"summary":94,"summary_zh":95,"content":8,"source_name":96,"source_url":93,"published_at":97,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":98,"score_detail":99,"sources":104,"tags":106,"primary_topic":110,"secondary_topics":111,"classification":117,"search_phrases":180,"slug":183,"view_count":20,"doi":184,"paper":185,"created_at":198},4528,"Integrating indigenous knowledge systems into regenerative agriculture for sustainable crop production in southern Africa","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43621-026-04926-8","Abstract Agricultural production in Southern Africa is increasingly constrained by climate variability, declining soil fertility, water scarcity, biodiversity loss, and rising pest pressures, particularly within rain-fed smallholder farming systems. Indigenous Knowledge Systems (IKS), developed through generations of interaction between communities and local agroecosystems, offer context-specific approaches that align closely with the principles of regenerative agriculture. This review synthesizes evidence from 37 publications examining the contribution of IKS to sustainable crop production across Southern Africa. Particular attention is given to soil health, soil biological activity, water-use efficiency, ecological pest regulation, crop productivity, and climate resilience. The synthesis demonstrates that indigenous regenerative practices, including organic soil amendments, residue retention, crop diversification, intercropping, agroforestry, water harvesting, and botanical pest management, improve soil organic carbon, enhance microbial activity, increase water retention, and stabilize yields under climatic stress. Evidence further indicates that indigenous pest management strategies frequently maintain pest populations below economic injury thresholds, thereby reducing dependence on synthetic pesticides while supporting ecosystem services. The review highlights the convergence between IKS, agroecology, integrated pest management, conservation agriculture, and regenerative agriculture, and proposes pathways for integrating indigenous ecological indicators into decision-support systems, crop models, and precision agriculture technologies. Despite growing recognition of indigenous knowledge within sustainability and climate adaptation agendas, significant gaps remain in quantitative validation, longitudinal assessment, and integration into formal agricultural research and policy frameworks. The findings demonstrate that Indigenous Knowledge Systems constitute a scientifically credible and economically viable foundation for regenerative agriculture and contribute directly to Sustainable Development Goals 2 (Zero Hunger), 12 (Responsible Consumption and Production), 13 (Climate Action), and 15 (Life on Land). Strengthening the integration of indigenous and scientific knowledge systems will be essential for building resilient, productive, and sustainable agricultural systems across Southern Africa and the broader Global South.","摘要 南部非洲的农业生产日益受到气候变异性、土壤肥力下降、水资源短缺、生物多样性丧失和病虫害压力上升的制约，这在雨养小农耕作系统中尤为突出。本土知识体系（Indigenous Knowledge Systems, IKS）通过社区与地方农业生态系统数代互动而发展形成，提供了与再生农业原则高度契合的情境化方法。本综述综合了37篇文献的证据，考察了IKS在南部非洲可持续作物生产中的贡献。研究特别关注土壤健康、土壤生物活性、水分利用效率、生态病虫害调控、作物生产力及气候韧性。综合结果表明，本土再生实践——包括有机土壤改良、残茬保留、作物多样化、间作、农林业、集水和植物源病虫害管理——能够提高土壤有机碳、增强微生物活性、增加持水量并在气候胁迫下稳定产量。证据进一步表明，本土病虫害管理策略常能将病虫害种群维持在经济危害阈值以下，从而减少对合成农药的依赖，同时支持生态系统服务。本综述强调了IKS与农业生态学、病虫害综合治理、保护性农业和再生农业之间的趋同性，并提出了将本土生态指标纳入决策支持系统、作物模型和精准农业技术的路径。尽管本土知识在可持续发展和气候适应议程中日益受到认可，但在定量验证、长期评估以及纳入正式农业研究和政策框架方面仍存在显著空白。研究结果表明，本土知识体系构成了再生农业的科学可信且经济可行的基础，并直接有助于实现可持续发展目标2（零饥饿）、12（负责任消费和生产）、13（气候行动）和15（陆地生物）。加强本土知识与科学知识体系的整合，对于在南部非洲及更广泛的全球南方构建韧性、高产和可持续的农业系统至关重要。","Discover Sustainability","2026-10-08T00:00:00Z",75,{"impact":100,"substance":101,"depth":16,"authority":18,"freshness":102,"relevant":20,"comment":103},15,21,8,"综述整合37篇文献，论证土著知识对再生农业与气候韧性的科学价值，具区域政策参考意义。",[105],{"name":96,"url":93},[107,28,108,29,109],"小农户","土壤健康","土著知识",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[112],{"code":113,"slug":114,"name":115,"path":116,"parent_code":35},"H6","biodiversity","生态保护与生物多样性","\u002Ftopic\u002Fenvironment\u002Fbiodiversity",{"status":38,"locked":13,"version":39,"method":40,"evidence":118},{"candidates":119,"agricultural_evidence":45},[120,126,134,142,148,155,161,168,174],{"code":31,"score":16,"supported":45,"title":121,"abstract":123,"tags":125},[122],"regenerative agriculture",[29,124,122],"conservation agriculture",[29],{"code":113,"score":19,"supported":45,"title":127,"abstract":128,"tags":133},[],[129,130,131,114,132],"生物多样性","农业生态","生态系统服务","agroecology",[],{"code":135,"score":136,"supported":45,"title":137,"abstract":138,"tags":141},"H2",7,[],[139,140],"土壤","soil",[108],{"code":62,"score":136,"supported":45,"title":143,"abstract":144,"tags":147},[],[145,146],"气候适应","climate resilience",[28],{"code":149,"score":88,"supported":45,"title":150,"abstract":151,"tags":154},"A7",[],[152,153],"间作","intercropping",[],{"code":44,"score":88,"supported":45,"title":156,"abstract":157,"tags":160},[],[158,159],"精准农业","precision agriculture",[],{"code":162,"score":163,"supported":45,"title":164,"abstract":165,"tags":167},"G2",4,[],[166],"smallholder",[107],{"code":169,"score":56,"supported":45,"title":170,"abstract":171,"tags":173},"F4",[],[172],"农药",[],{"code":175,"score":56,"supported":45,"title":176,"abstract":177,"tags":179},"H3",[],[178],"水资源",[],[181,182],"南部非洲 再生农业 土著知识","土著知识 土壤健康 小农户","南部非洲再生农业土著知识-4528","10.1007\u002Fs43621-026-04926-8",{"doi":184,"openalex_id":186,"authors":187,"venue":96,"cited_by_count":78,"oa_url":93,"card":191,"direction":83,"ingested_from":197},"W7220943031",[188],{"name":189,"orcid":190},"Albert Thembinkosi Modi","https:\u002F\u002Forcid.org\u002F0000-0002-6887-1721",{"tldr":192,"method":193,"finding":194,"direction":195,"opportunity":196},"综述37篇文献，论证南部非洲本土知识可支撑再生农业与可持续作物生产。","系统综述37篇文献，聚焦土壤、水分、病虫害与气候韧性。","本土再生实践能提升土壤碳、微生物活性与水分保持，稳定产量并减少农药依赖。","农业绿色发展与碳","可将本土生态指标量化并嵌入作物模型与精准农业决策系统，填补长期验证空白。","openalex","2026-10-09T23:30:52.261674Z",{"id":200,"title":201,"url":202,"summary":203,"summary_zh":8,"content":8,"source_name":204,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":205,"score_detail":206,"sources":210,"tags":212,"primary_topic":216,"secondary_topics":217,"classification":222,"search_phrases":248,"slug":251,"view_count":56,"doi":8,"paper":252,"created_at":260},3243,"Integrating Climate Resilience and Digital Traceability in Regenerative Agri-Food Systems: A Scenario-Based Framework for Verifiable Sustainability Claims（再生农业食品系统整合气候韧性与数字溯源：可验证可持续性声明的情景框架）","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F18\u002F2024","MDPI Agriculture 16(18) 2024 发表研究：面对再生农业食品系统的可持续性声明常缺乏可验证、系统性证据的问题，构建整合情景分析、SWOT评估和案例研究的三方法框架。三种前瞻性情景——乐观、常规、悲观——基于现有气候韧性和政策文献构建；SWOT分析综合区块链、物联网和AI赋能的溯源机制影响因素；案例研究以先前记录的再生农业食品计划为基础，分析气候韧性叙事、数字验证工具和消费者信任线索的交互作用。结果表明，再生声明常与可验证数据流脱节，数字溯源采用面临结构性、成本相关障碍，消费者信任更依赖于情感和本土化线索而非正式认证；该框架为政策制定者、认证机构和农产品生产者将气候韧性战略与数字可验证可持续性声明相结合提供可复制、低资源方法。（罗马尼亚布加勒斯特国家科学技术大学Politehnica）","MDPI Agriculture",70,{"impact":50,"substance":207,"depth":208,"authority":18,"freshness":102,"relevant":20,"comment":209},20,17,"论文提出情景分析、SWOT与案例研究三方法框架，指出再生农业可持续性声明与可验证数据流脱节，对农业数字化溯源有参考价值，但属学术探讨、产业落地影响有限。",[211],{"name":204,"url":202},[213,214,28,215,29],"农业人工智能","区块链","数字溯源",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[218],{"code":62,"slug":219,"name":220,"path":221,"parent_code":35},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate",{"status":38,"locked":13,"version":39,"method":40,"evidence":223},{"candidates":224,"agricultural_evidence":45},[225,229,233,239,244],{"code":31,"score":50,"supported":45,"title":226,"abstract":227,"tags":228},[29],[29],[29],{"code":62,"score":19,"supported":45,"title":230,"abstract":231,"tags":232},[146],[],[28],{"code":234,"score":56,"supported":45,"title":235,"abstract":236,"tags":238},"I5",[],[237],"物联网",[],{"code":240,"score":20,"supported":13,"title":241,"abstract":242,"tags":243},"E4",[],[],[215],{"code":67,"score":20,"supported":13,"title":245,"abstract":246,"tags":247},[],[],[213],[249,250],"布加勒斯特 Politehnica 再生农业","MDPI Agriculture 数字溯源","布加勒斯特Politehnica再生农业-3243",{"doi":8,"openalex_id":8,"authors":253,"venue":8,"cited_by_count":78,"oa_url":8,"card":254,"direction":258,"ingested_from":85},[],{"tldr":255,"method":256,"finding":257,"direction":258,"opportunity":259},"构建情景分析、SWOT与案例研究框架，整合再生农业的气候韧性与数字溯源以验证可持续性声明。","情景分析、SWOT评估与案例研究三方法框架，结合区块链、物联网和AI溯源文献。","再生声明常与可验证数据脱节，数字溯源有成本障碍，消费者信任更依赖情感与本土线索。","数字乡村与农业信息化","可探索低成本数字溯源与本土化信任线索结合的可验证声明机制，尤其在小农户场景。","2026-09-23T00:04:32.924354Z",{"id":262,"title":263,"url":264,"summary":265,"summary_zh":266,"content":8,"source_name":267,"source_url":264,"published_at":268,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":269,"score_detail":270,"sources":273,"tags":275,"primary_topic":278,"secondary_topics":283,"classification":285,"search_phrases":320,"slug":323,"view_count":75,"doi":324,"paper":325,"created_at":344},2537,"A Counterfactual-Enabled Agricultural Decision Support Framework for Sustainability-Aware Groundnut Yield Prediction Using Bayesian-Optimized XGBoost","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fai7090364","Sustainable agricultural planning requires predictive frameworks that can capture spatiotemporal variability, sustainability dynamics, and the potential outcomes of alternative management scenarios. The research proposes TSAFI-DT, a retrospectively validated, data-driven Digital Twin prototype integrating spatiotemporal data reconstruction, sustainability-state representation, hierarchical yield forecasting, counterfactual analysis, and scenario simulation. The framework operates on historical district-level APY observations and therefore represents a retrospective approximation of Digital Twin operation rather than a continuously synchronized cyber-physical agricultural Digital Twin. The Extended Regenerative Agriculture Index (eRAI) combines crop diversity, productivity–stability, land-use efficiency, and yield-trend information to characterize district-level sustainability states. A Bayesian-optimized XGBoost model is employed for one-step-ahead yield forecasting under temporal validation, while fixed-effects and synthetic-control analyses provide complementary associational and intervention-associated evidence. Evaluation using district-level groundnut data from India during 1997–2023 demonstrates that the proposed predictor achieves an RMSE of 0.171 t\u002Fha and R2=0.92, outperforming the evaluated baselines with statistically significant differences (p\u003C0.05). The fully adjusted fixed-effects model identifies a positive association between higher sustainability states and yield, while retrospective Digital Twin replay demonstrates close temporal agreement between predicted and observed outcomes. Model-based scenario simulations indicate predicted yield increases of up to 12.4% under the evaluated sustainability-state perturbations; these estimates represent counterfactual sensitivity rather than guaranteed causal effects. TSAFI-DT provides a reproducible framework for sustainability-aware agricultural forecasting, comparative scenario exploration, and data-driven decision support.","可持续农业规划需要能够捕捉时空变异性、可持续性动态以及替代管理情景潜在结果的预测框架。本研究提出TSAFI-DT，一个经回溯验证的数据驱动数字孪生（Digital Twin）原型，集成了时空数据重建、可持续性状态表征、分层产量预测、反事实分析和情景模拟。该框架基于历史地区级APY观测数据运行，因此代表的是数字孪生运行的回溯近似，而非持续同步的网络-物理农业数字孪生。扩展再生农业指数（Extended Regenerative Agriculture Index, eRAI）综合了作物多样性、生产力-稳定性、土地利用效率和产量趋势信息，以刻画地区级可持续性状态。采用贝叶斯优化的XGBoost模型在时间验证下进行一步超前产量预测，同时固定效应和合成控制分析提供互补的关联性证据和干预关联性证据。利用印度1997—2023年地区级花生数据进行评估，结果表明所提出的预测器实现了0.171 t\u002Fha的RMSE和R²=0.92，优于所评估的基线模型且差异具有统计学显著性（p\u003C0.05）。完全调整的固定效应模型识别出较高可持续性状态与产量之间的正相关关系，而回溯性数字孪生重放表明预测结果与观测结果在时间上高度一致。基于模型的情景模拟显示，在所评估的可持续性状态扰动下，预测产量增幅最高可达12.4%；这些估计代表的是反事实敏感性而非保证的因果效应。TSAFI-DT为可持续性感知的农业预测、比较情景探索和数据驱动决策支持提供了一个可复现的框架。","AI","2026-09-14T00:00:00Z",76,{"impact":271,"substance":17,"depth":16,"authority":50,"freshness":102,"relevant":20,"comment":272},16,"提出融合数字孪生、反事实分析与贝叶斯优化XGBoost的花生产量预测框架，方法新颖、数据跨度长且验证充分，对可持续农业决策支持有参考价值。",[274],{"name":267,"url":264},[25,213,276,27,277],"产量预测","花生种植",{"code":67,"slug":279,"name":280,"path":281,"parent_code":282},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[284],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":286},{"candidates":287,"agricultural_evidence":45},[288,293,298,303,309,315],{"code":67,"score":50,"supported":45,"title":289,"abstract":291,"tags":292},[290],"decision support",[290],[213],{"code":31,"score":19,"supported":45,"title":294,"abstract":295,"tags":297},[],[296,29,122],"可持续农业",[],{"code":44,"score":102,"supported":45,"title":299,"abstract":300,"tags":302},[],[27,301],"digital twin",[27,25],{"code":304,"score":163,"supported":45,"title":305,"abstract":306,"tags":308},"A4",[],[307],"花生",[277],{"code":310,"score":56,"supported":45,"title":311,"abstract":312,"tags":314},"J1",[],[313],"农业规划",[],{"code":316,"score":20,"supported":13,"title":317,"abstract":318,"tags":319},"I3",[],[],[276],[321,322],"农业人工智能 产量预测 数字孪生 智慧农业","农业人工智能 产量预测","农业人工智能产量预测数字孪生智慧农业-2537","10.3390\u002Fai7090364",{"doi":324,"openalex_id":326,"authors":327,"venue":267,"cited_by_count":78,"oa_url":264,"card":339,"direction":258,"ingested_from":197},"W7212812029",[328,331,334,336],{"name":329,"orcid":330},"Rekha R Nair","https:\u002F\u002Forcid.org\u002F0000-0002-7207-2877",{"name":332,"orcid":333},"Tina Babu","https:\u002F\u002Forcid.org\u002F0000-0001-7846-3679",{"name":335,"orcid":8},"Sumendra Yogarayan",{"name":337,"orcid":338},"Abdul Razak","https:\u002F\u002Forcid.org\u002F0000-0002-6108-3183",{"tldr":340,"method":341,"finding":342,"direction":83,"opportunity":343},"提出TSAFI-DT数字孪生框架，用贝叶斯优化XGBoost预测印度花生产量并做反事实情景分析。","基于1997-2023年印度县级花生产量数据，构建eRAI可持续性指数，采用贝叶","模型RMSE为0.171 t\u002Fha、R²=0.92，高可持续状态与产量正相关，情景模拟产量最高提升1","可延伸至实时物联网数据驱动的数字孪生，并验证反事实情景的因果效应与跨作物泛化能力。","2026-09-15T23:30:26.594281Z",{"id":346,"title":347,"url":348,"summary":349,"summary_zh":350,"content":8,"source_name":351,"source_url":348,"published_at":268,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":269,"score_detail":352,"sources":354,"tags":356,"primary_topic":357,"secondary_topics":358,"classification":364,"search_phrases":434,"slug":436,"view_count":75,"doi":437,"paper":438,"created_at":449},2518,"AI-Driven Transformation in Sustainable Agriculture: A Systematic Review","https:\u002F\u002Fdoi.org\u002F10.18805\u002Fijare.a-6627","The agriculture sector is facing unprecedented pressure from a rapidly growing global population, erratic weather conditions and declining water availability. Traditional farming methods are increasingly proving insufficient in meeting the rising food demand, necessitating a shift towards technology-driven solutions. This paper provides a critical and systematic review of the application of Artificial Intelligence (AI) in agriculture, analysing its impact on productivity and sustainability, while identifying potential barriers hindering adoption. Employing a Systematic Literature Review approach, this study synthesizes recent research organized around the core domains of agricultural production - crop, soil and nutrient, water and irrigation and crop-protection (pest, disease and weed) management, alongside yield forecasting - examining how data-driven tools such as machine learning, the Internet of Things, robotics and computer vision are applied within each and prioritizing studies that reported agronomically meaningful outcomes such as yield gains and resource-use efficiency. The strongest gains identified across the review fall within three agricultural areas - crop and soil monitoring, yield forecasting and robotic field operations such as targeted detection, weeding and harvesting. The technologies enabling them, chiefly machine-learning models such as convolutional neural networks combined with field and remote sensors, have delivered high in-field precision, with reported object-detection precision of up to 95.78% in field conditions. In practical terms, this translates into more efficient use of water, fertilizer and other inputs and into improved yield and crop quality. The review concludes that prioritizing Explainable AI and interoperable farm systems is central to building farmer trust and safeguarding food security under a changing climate.","农业部门正面临着来自全球人口快速增长、天气条件不稳定以及水资源日益减少的前所未有的压力。传统耕作方法在满足不断增长的粮食需求方面日益显得力不从心，因此有必要转向技术驱动的解决方案。本文对人工智能（Artificial Intelligence, AI）在农业中的应用进行了批判性和系统性的综述，分析了其对生产力和可持续性的影响，同时识别了阻碍其采用的潜在障碍。本研究采用系统性文献综述方法，围绕农业生产的核心领域——作物、土壤与养分、水资源与灌溉、作物保护（病虫害和杂草）管理以及产量预测——对近期研究进行了综合梳理，考察了机器学习、物联网、机器人技术和计算机视觉等数据驱动工具在各领域中的应用方式，并优先关注报告了具有农学意义成果（如产量提升和资源利用效率）的研究。综述中发现的最显著收益集中在三个农业领域——作物与土壤监测、产量预测以及机器人田间作业（如靶向检测、除草和收获）。实现这些收益的技术，主要是卷积神经网络等机器学习模型与田间及遥感传感器的结合，已在田间条件下实现了高精度，所报告的目标检测精度在田间条件下高达95.78%。在实际应用中，这意味着水、肥料及其他投入品的更高效利用，以及产量和作物品质的提升。综述得出结论：优先发展可解释人工智能（Explainable AI）和可互操作的农场系统，对于在气候变化背景下建立农民信任和保障粮食安全至关重要。","Indian Journal of Agricultural Research",{"impact":16,"substance":207,"depth":208,"authority":18,"freshness":102,"relevant":20,"comment":353},"系统综述梳理AI在作物土壤监测、产量预测与机器人田间作业中的应用成效与推广障碍，结论扎实，对智慧农业方向有参考价值。",[355],{"name":351,"url":348},[25,213,276,26,158],{"code":67,"slug":279,"name":280,"path":281,"parent_code":282},[359,363],{"code":175,"slug":360,"name":361,"path":362,"parent_code":35},"irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":365},{"candidates":366,"agricultural_evidence":45},[367,378,383,388,395,402,406,411,416,420,425,430],{"code":67,"score":368,"supported":45,"title":369,"abstract":370,"tags":377},11,[],[371,372,373,374,375,376],"目标检测","机器学习","计算机视觉","machine learning","artificial intelligence","computer vision",[213,26],{"code":175,"score":19,"supported":45,"title":379,"abstract":380,"tags":382},[],[381,178,360],"灌溉",[],{"code":31,"score":102,"supported":45,"title":384,"abstract":386,"tags":387},[385],"sustainable agriculture",[],[],{"code":389,"score":88,"supported":45,"title":390,"abstract":391,"tags":394},"A8",[],[392,393],"粮食安全","food security",[],{"code":396,"score":88,"supported":45,"title":397,"abstract":398,"tags":401},"F3",[],[399,400],"肥料","fertilizer",[],{"code":135,"score":88,"supported":45,"title":403,"abstract":404,"tags":405},[],[139,140],[],{"code":234,"score":88,"supported":45,"title":407,"abstract":408,"tags":410},[],[237,409],"internet of things",[],{"code":316,"score":163,"supported":45,"title":412,"abstract":413,"tags":415},[],[414],"遥感",[276],{"code":149,"score":56,"supported":45,"title":417,"abstract":418,"tags":419},[],[152],[],{"code":169,"score":56,"supported":45,"title":421,"abstract":422,"tags":424},[],[423],"除草",[],{"code":62,"score":56,"supported":45,"title":426,"abstract":427,"tags":429},[],[428],"气候变化",[],{"code":44,"score":75,"supported":13,"title":431,"abstract":432,"tags":433},[],[],[25,158],[435,322],"农业人工智能 产量预测 智慧农业 精准农业","农业人工智能产量预测智慧农业精准农业-2518","10.18805\u002Fijare.a-6627",{"doi":437,"openalex_id":439,"authors":440,"venue":351,"cited_by_count":78,"oa_url":348,"card":443,"direction":448,"ingested_from":197},"W7212616413",[441],{"name":442,"orcid":8},"Manish Maan",{"tldr":444,"method":445,"finding":446,"direction":83,"opportunity":447},"系统综述AI在可持续农业中的应用，分析生产力与可持续性影响及推广障碍。","系统文献综述，围绕作物、土壤、水、植保和产量预测梳理ML、IoT、机器人、计算机","作物与土壤监测、产量预测和机器人田间作业收益最大，检测精度达95.78%，需可解释AI与互操作系统。","可解释AI与互操作农场系统在农户信任和气候适应中的作用尚缺实证，是值得深入的研究空白。","智慧农业 \u002F 农业物联网","2026-09-15T23:30:13.705421Z",{"id":451,"title":452,"url":453,"summary":454,"summary_zh":455,"content":8,"source_name":456,"source_url":453,"published_at":457,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":458,"sources":461,"tags":463,"primary_topic":466,"secondary_topics":470,"classification":475,"search_phrases":520,"slug":523,"view_count":20,"doi":524,"paper":525,"created_at":537},4073,"Intelligent soil monitoring system for sustainable agriculture using TinyML and ultra-low power wireless sensor networks","https:\u002F\u002Fdoi.org\u002F10.35784\u002Fiapgos.9467","Precision agriculture demands continuous, energy-autonomous soil monitoring capable of detecting critical conditions such as rapid moisture loss or nutrient depletion approaching crop-threatening thresholds. Conventional wireless sensor networks face a fundamental trade-off between multi-year battery life and sub-second response latency, as duty-cycled polling wastes energy on idle queries while always-on communication remains infeasible for battery-powered field deployments spanning hundreds of acres. This work presents a novel integration of TinyML-based edge inference with a custom-designed 40 nm CMOS ultra-low power wake-up receiver (WuRX), enabling event-driven, asynchronous soil condition monitoring without reliance on periodic polling schedules. The proposed three-tier edge-fog-cloud architecture employs sensor nodes measuring moisture, temperature, pH, nitrogen, phosphorus, and potassium, with quantized neural networks trained and validated on 64,800 labelled samples collected from instrumented corn and soybean field deployments over 180 days, achieving a classification accuracy of 91.3% and F1-score of 93.0% at an inference energy cost of 0.87 mJ per cycle. Circuit-level simulations of the 40 nm CMOS WuRX confirm an input return loss of -15.8 dB, transmission gain of +18.2 dB, and power-added efficiency of 45.3% at -60 dBm sensitivity, with continuous standby consumption of 45–53 µW. System-level power budget analysis validates battery lifetimes of 200–300 days using 240 mAh lithium cells augmented by a 5 cm² monocrystalline solar harvester. Key limitations include the restriction of field validation to two crop types and dependence on adequate solar irradiance for energy-neutral operation. The proposed architecture reduces communication overhead by 80–90% relative to threshold-based systems, providing a practical framework for scalable, resource-constrained precision agriculture deployments.","精准农业需要能够持续、能源自主地监测土壤，以检测诸如水分快速流失或养分耗竭接近威胁作物阈值等关键状况。传统无线传感器网络面临多年电池寿命与亚秒级响应延迟之间的根本性权衡，因为占空比轮询会在空闲查询上浪费能量，而始终在线的通信对于覆盖数百英亩的电池供电田间部署而言仍不可行。本研究提出了一种新颖的集成方案，将基于TinyML的边缘推理与定制设计的40 nm CMOS超低功耗唤醒接收器（WuRX）相结合，实现事件驱动的异步土壤状况监测，而无需依赖周期性轮询调度。所提出的三层边缘-雾-云架构采用测量水分、温度、pH、氮、磷和钾的传感器节点，其量化神经网络在180天内从仪器化玉米和大豆田间部署中采集的64,800个标记样本上进行训练和验证，在每次推理周期能耗为0.87 mJ的情况下，实现了91.3%的分类准确率和93.0%的F1分数。对40 nm CMOS WuRX的电路级仿真证实，在-60 dBm灵敏度下，输入回波损耗为-15.8 dB，传输增益为+18.2 dB，功率附加效率为45.3%，连续待机功耗为45–53 µW。系统级功率预算分析验证了使用240 mAh锂电池并辅以5 cm²单晶硅太阳能收集器时，电池寿命可达200–300天。主要局限性包括田间验证仅限于两种作物类型，以及能量中性运行依赖充足的太阳辐照度。与基于阈值的系统相比，所提出的架构将通信开销降低了80–90%，为可扩展、资源受限的精准农业部署提供了实用框架。","Informatyka Automatyka Pomiary w Gospodarce i Ochronie Środowiska","2026-09-30T00:00:00Z",{"impact":16,"substance":17,"depth":459,"authority":18,"freshness":102,"relevant":20,"comment":460},19,"将TinyML边缘推理与40nm CMOS超低功耗唤醒接收机结合，实现事件驱动型土壤监测，实测数据扎实、能耗指标明确，对精准农业物联网部署有参考价值。",[462],{"name":456,"url":453},[25,213,158,464,465],"无线传感器网络","土壤监测",{"code":234,"slug":467,"name":468,"path":469,"parent_code":282},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[471,474],{"code":135,"slug":140,"name":472,"path":473,"parent_code":35},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":476},{"candidates":477,"agricultural_evidence":45},[478,484,489,493,497,504,510,516],{"code":234,"score":100,"supported":45,"title":479,"abstract":481,"tags":483},[480],"wireless sensor",[482,480],"无线传感",[464],{"code":135,"score":485,"supported":45,"title":486,"abstract":487,"tags":488},14,[140],[139,140],[],{"code":31,"score":102,"supported":45,"title":490,"abstract":491,"tags":492},[385],[],[],{"code":44,"score":102,"supported":45,"title":494,"abstract":495,"tags":496},[],[158,159],[25,158],{"code":498,"score":88,"supported":45,"title":499,"abstract":500,"tags":503},"A3",[],[501,502],"玉米","corn",[],{"code":304,"score":88,"supported":45,"title":505,"abstract":506,"tags":509},[],[507,508],"大豆","soybean",[],{"code":511,"score":56,"supported":45,"title":512,"abstract":513,"tags":515},"F5",[],[514],"harvester",[],{"code":67,"score":20,"supported":13,"title":517,"abstract":518,"tags":519},[],[],[213],[521,522],"TinyML 土壤监测","超低功耗 唤醒接收机 精准农业","TinyML土壤监测-4073","10.35784\u002Fiapgos.9467",{"doi":524,"openalex_id":526,"authors":527,"venue":456,"cited_by_count":78,"oa_url":531,"card":532,"direction":448,"ingested_from":197},"W7214927134",[528],{"name":529,"orcid":530},"Muhammad Ovais Akhter","https:\u002F\u002Forcid.org\u002F0000-0002-8928-4489","https:\u002F\u002Fph.pollub.pl\u002Findex.php\u002Fiapgos\u002Farticle\u002Fdownload\u002F9467\u002F5631",{"tldr":533,"method":534,"finding":535,"direction":448,"opportunity":536},"提出TinyML边缘推理与超低功耗唤醒接收机集成的土壤监测系统，实现事件驱动异步监测。","TinyML量化神经网络、40nm CMOS唤醒接收机、三层边缘-雾-云架构，6","分类准确率91.3%，通信开销降低80-90%，电池寿命200-300天。","可探索多作物多土壤类型泛化、无光照或弱光下能量收集与事件触发协同优化。","2026-10-03T23:30:17.793958Z",{"id":539,"title":540,"url":541,"summary":542,"summary_zh":543,"content":8,"source_name":544,"source_url":541,"published_at":545,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":546,"sources":548,"tags":550,"primary_topic":555,"secondary_topics":560,"classification":567,"search_phrases":621,"slug":624,"view_count":56,"doi":625,"paper":626,"created_at":681},3759,"Synergistic interaction effects of precision phosphorus fertigation and residue management on productivity, profitability, and resource-use efficiency of wheat under conservation agriculture","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1944629","Phosphorus (P) management under conventional surface-broadcast application in calcareous soils of the Indo-Gangetic Plains (IGP) suffers from severe fixation losses, limiting phosphorus-use efficiency (PUE) to 10–25% and contributing to yield gaps in wheat, a globally important food security crops. A two-year (2023–24 and 2024–25) split-plot field experiment was conducted within a mid-term conservation agriculture (CA)-based maize-wheat-greengram system to evaluate nine phosphorus fertigation levels and split application schedules through subsurface drip fertigation (SSDF), combined with two residue management practices (retention: R+, no-retention: R-), on growth, yield, water productivity, economics, and resource-use efficiency and post-harvest available phosphorus of wheat (cv. HD 2967). Treatments included no-P (control), SSDF of P as DAP at 50, 75, and 100% of the recommended dose (RDP; 60 kg P 2 O 5 ha −1 ) applied either fully as basal (10 DAS) or split (10 and 25 DAS), along with a nano-DAP foliar spray, compared against conventional CA with flood irrigation and basal broadcast P (CA-FI-100% RDP-B). SSDF treatments consumed only 178–275 mm of total water input against 437–452 mm under flood irrigation. Among SSDF treatments, 100% RDP applied in two splits (100% RDP-2S) consistently recorded the highest growth attributes, grain yield (6.23 and 6.31 t ha −1 ), and economic returns (BCR: 1.8–2) across both years, improving grain yield by 10.6–11.5% and net returns by 13.7% over CA-FI-100% RDP-B. Notably, 75% RDP-2S was statistically comparable to 100% RDP-2S for yield and profitability, demonstrating that a 25% reduction in P dose under precision SSDF does not compromise productivity. Total and irrigation water productivity improved by 127.7 and 156.7%, respectively, under 100% RDP-2S over CA-FI-100% RDP-B. Residue retention further enhanced productivity, increasing grain yield by 14.0–15.0% and net returns by 26.4–27.5%. Post-harvest soil available P was 18.0 and 43.3% higher under SSDF than under CA-FI-100% RDP-B at 0–15 and 15–30 cm, respectively. The interaction of split P fertigation and residue retention was consistently superior for grain yield and water productivity. These findings establish 75–100% RDP delivered through split SSDF, combined with residue retention, as an agronomically superior, water-efficient, economically viable strategy for sustainable wheat intensification in the semi-arid IGPs.","在印度河-恒河平原（IGP）石灰性土壤上，常规地表撒施条件下的磷（P）管理面临严重的固定损失，导致磷利用效率（PUE）仅为10–25%，并造成小麦——一种全球重要的粮食安全作物——的产量差距。在中期保护性农业（CA）为基础的玉米-小麦-绿豆轮作体系中，开展了一项为期两年（2023–24和2024–25）的裂区田间试验，评估九种磷肥滴灌水平和分次施用方案通过地下滴灌施肥（SSDF）对小麦（品种HD 2967）生长、产量、水分生产力、经济效益、资源利用效率及收获后土壤有效磷的影响，并结合两种秸秆管理方式（还田：R+，不还田：R-）。处理包括：无磷（对照）、以DAP形式通过SSDF施用推荐施磷量（RDP；60 kg P₂O₅ ha⁻¹）的50%、75%和100%，分别以全部基施（播种后10天）或分次施用（播种后10天和25天），同时配合纳米DAP叶面喷施，并与常规保护性农业配合漫灌和基施撒施磷（CA-FI-100% RDP-B）进行比较。SSDF处理的总水分投入仅为178–275 mm，而漫灌条件下为437–452 mm。在SSDF处理中，100% RDP分两次施用（100% RDP-2S）在两年中均持续表现出最高的生长指标、籽粒产量（6.23和6.31 t ha⁻¹）和经济效益（BCR：1.8–2），较CA-FI-100% RDP-B分别提高籽粒产量10.6–11.5%和净收益13.7%。值得注意的是，75% RDP-2S在产量和盈利能力上与100% RDP-2S无统计学差异，表明在精准SSDF下减少25%的磷用量不会影响生产力。与CA-FI-100% RDP-B相比，100% RDP-2S处理下总水分生产力和灌溉水分生产力分别提高了127.7%和156.7%。秸秆还田进一步提高了生产力，使籽粒产量增加14.0–15.0%，净收益增加26.4–27.5%。收获后土壤有效磷在0–15 cm和15–30 cm土层中，SSDF较CA-FI-100% RDP-B分别高出18.0%和43.3%。分次磷肥滴灌与秸秆还田的交互作用在籽粒产量和水分生产力方面始终表现最优。这些研究结果表明，通过分次SSDF施用75–100% RDP并结合秸秆还田，是一种农艺上优越、水分高效、经济可行的策略，可用于半干旱印度河-恒河平原小麦的可持续集约化生产。","Frontiers in Sustainable Food Systems","2026-09-28T00:00:00Z",{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":547},"两年田间试验证实分次地下滴灌施磷配合秸秆还田可减磷25%并显著提升小麦产量与水肥利用效率，数据扎实、结论可靠，对半干旱地区精准水肥管理有直接参考价值。",[549],{"name":544,"url":541},[25,551,552,553,554],"精准施肥","小麦","保护性耕作","水肥一体化",{"code":556,"slug":557,"name":552,"path":558,"parent_code":559},"A2","wheat","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[561,566],{"code":396,"slug":562,"name":563,"path":564,"parent_code":565},"fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":568},{"candidates":569,"agricultural_evidence":45},[570,576,580,584,589,593,597,601,606,612,617],{"code":396,"score":271,"supported":45,"title":571,"abstract":573,"tags":575},[572],"fertigation",[574,572],"施肥",[554,551],{"code":556,"score":100,"supported":45,"title":577,"abstract":578,"tags":579},[557],[552,557],[552],{"code":31,"score":50,"supported":45,"title":581,"abstract":582,"tags":583},[124],[124],[553],{"code":498,"score":88,"supported":45,"title":585,"abstract":586,"tags":588},[],[501,587],"maize",[],{"code":389,"score":88,"supported":45,"title":590,"abstract":591,"tags":592},[],[392,393],[],{"code":135,"score":88,"supported":45,"title":594,"abstract":595,"tags":596},[],[139,140],[],{"code":175,"score":88,"supported":45,"title":598,"abstract":599,"tags":600},[],[381,360],[],{"code":149,"score":56,"supported":45,"title":602,"abstract":603,"tags":605},[],[604],"轮作",[],{"code":607,"score":56,"supported":45,"title":608,"abstract":609,"tags":611},"H5",[],[610],"秸秆还田",[],{"code":62,"score":56,"supported":45,"title":613,"abstract":614,"tags":616},[],[615],"干旱",[],{"code":44,"score":20,"supported":13,"title":618,"abstract":619,"tags":620},[],[],[25],[622,623],"地下滴灌 磷肥 小麦","保护性耕作 秸秆还田 小麦","地下滴灌磷肥小麦-3759","10.3389\u002Ffsufs.2026.1944629",{"doi":625,"openalex_id":627,"authors":628,"venue":544,"cited_by_count":78,"oa_url":541,"card":676,"direction":448,"ingested_from":197},"W7214579192",[629,631,634,636,638,640,642,645,647,649,651,653,655,658,660,662,665,668,671,674],{"name":630,"orcid":8},"Kadagonda Nithinkumar",{"name":632,"orcid":633},"Anchal Dass","https:\u002F\u002Forcid.org\u002F0000-0003-3909-1803",{"name":635,"orcid":8},"Devika A. R.",{"name":637,"orcid":8},"Arjun Singh",{"name":639,"orcid":8},"Susama Sudhishri",{"name":641,"orcid":8},"Vinod Kumar Singh",{"name":643,"orcid":644},"Sanjay Singh Rathore","https:\u002F\u002Forcid.org\u002F0000-0001-6725-1478",{"name":646,"orcid":8},"Sarvendra Kumar",{"name":648,"orcid":8},"Teekam Singh",{"name":650,"orcid":8},"Jitendra Rajput",{"name":652,"orcid":8},"Pravin Kumar Upadhyaya",{"name":654,"orcid":8},"R. N. Sahoo",{"name":656,"orcid":657},"ARPULA SAIRAM","https:\u002F\u002Forcid.org\u002F0009-0009-9034-6032",{"name":659,"orcid":8},"Aye Aye San",{"name":661,"orcid":8},"K. S. Sachin",{"name":663,"orcid":664},"Mummasani Asritha","https:\u002F\u002Forcid.org\u002F0009-0002-4619-9943",{"name":666,"orcid":667},"Ramanjit Kaur","https:\u002F\u002Forcid.org\u002F0000-0001-5117-050X",{"name":669,"orcid":670},"Mona Nagargade","https:\u002F\u002Forcid.org\u002F0000-0003-1062-512X",{"name":672,"orcid":673},"Vishal Tyagi","https:\u002F\u002Forcid.org\u002F0000-0001-5593-3076",{"name":675,"orcid":8},"Subhash Babu",{"tldr":677,"method":678,"finding":679,"direction":448,"opportunity":680},"研究保护性农业下精准磷肥滴灌与秸秆还田对小麦产量、收益和资源效率的协同效应。","两年裂区田间试验，地下滴灌分次施磷与秸秆还田处理，测产量、水生产力与经济指标。","75–100%推荐磷量分次滴灌配秸秆还田可增产10%以上、节水超一倍且不减产。","可探索基于土壤磷素实时监测的变量施磷决策模型，并与秸秆还田互作机制结合优化。","2026-09-29T23:30:06.859116Z"]