[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2020":3,"related-2020":103},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":44,"search_phrases":75,"slug":78,"view_count":79,"doi":80,"paper":81,"created_at":102},2020,"Decision support in recirculating aquaculture systems (RAS): A case study of a human–AI interface in prawn hatchery operation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102554","The need for sustainable and responsible production in aquaculture calls for innovative implementation of recirculating aquaculture systems (RAS), which are extraordinarily complex, requiring the integration of various fields of science and technology to reach the desired productivity. In this case study, we report a four-month observation using a large language model (LLM) that – collaboratively with human expertise – analyzed and resolved complex challenges in a Macrobrachium rosenbergii RAS hatchery. Unacceptable larval and post-larval mortality prompted the integration into hatchery management of an AI decision-support system as a strategic management partner, enabling exploration across chemical, biological, physical, engineering, and behavioral domains. Key interventions suggested by the AI agent included mineral balance recalibration, microbial load diagnostics, behavioral pattern decoding, and lighting and flow engineering. Outcomes were evaluated in terms of a reduction in larval mortality and improved rates of larval metamorphosis to post larvae. Central to the process was the presence of a guiding human entity, steering AI's analytical power through deliberate questioning and contextual framing. This case study suggests that AI has the potential to improve intensive aquaculture systems. However, the tendency of AI agents to oversimplify complex systems requires the direction and guidance of a human expert to lead AI-human conversations. The adoption of LLMs in RAS-based aquaculture, bridging the gaps between raw data and actionable insights, has the potential to drive both the efficiency and the long-term sustainability of the aquaculture industry.","水产养殖可持续和负责任生产的需要，要求创新性地实施循环水养殖系统（RAS），该系统极为复杂，需要整合各种科学和技术领域以实现理想的生产力。在本案例研究中，我们报告了一项为期四个月的观察，使用大型语言模型（LLM）与人类专业知识协作，分析和解决了罗氏沼虾（Macrobrachium rosenbergii）RAS孵化场中的复杂挑战。不可接受的幼体和后期幼体死亡率促使将AI决策支持系统作为战略管理伙伴纳入孵化场管理，从而能够在化学、生物、物理、工程和行为领域进行探索。AI代理建议的关键干预措施包括矿物质平衡重新校准、微生物负荷诊断、行为模式解码以及光照和水流工程。结果通过幼体死亡率的降低和幼体变态为后期幼体的比率提高来评估。该过程的核心是有一个指导性的人类实体，通过有意的提问和情境构建来引导AI的分析能力。本案例研究表明，AI有潜力改善集约化水产养殖系统。然而，AI代理倾向于过度简化复杂系统，需要人类专家的指导和引导来主导AI与人类的对话。在基于RAS的水产养殖中采用LLM，弥合原始数据与可操作见解之间的差距，有潜力推动水产养殖行业的效率和长期可持续性。",null,"Smart Agricultural Technology","2026-09-07T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,21,13,8,1,"核心期刊发表的LLM辅助RAS对虾育苗决策案例，方法新颖、结论有实证支撑，对智慧水产养殖具参考价值，值得进入每日精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","大语言模型","水产养殖","循环水养殖",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"D1","pond-factory-aquaculture","池塘与工厂化养殖","\u002Ftopic\u002Faquaculture\u002Fpond-factory-aquaculture","D",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":45,"locked":14,"version":46,"method":47,"evidence":48},"classified","2026-10-22.2","rules",{"candidates":49,"agricultural_evidence":52},[50,58,64,70],{"code":36,"score":51,"supported":52,"title":53,"abstract":55,"tags":57},15,true,[54],"aquaculture",[56,54],"水产",[29],{"code":32,"score":59,"supported":52,"title":60,"abstract":62,"tags":63},14,[61],"recirculating aquaculture",[30,61],[],{"code":39,"score":19,"supported":52,"title":65,"abstract":67,"tags":69},[66],"decision support",[68],"large language model",[27,28],{"code":71,"score":21,"supported":14,"title":72,"abstract":73,"tags":74},"I1",[],[],[26],[76,77],"农业人工智能 大语言模型 循环水养殖 智慧农业","农业人工智能 大语言模型","农业人工智能大语言模型循环水养殖智慧农业-2020",4,"10.1016\u002Fj.atech.2026.102554",{"doi":80,"openalex_id":82,"authors":83,"venue":10,"cited_by_count":92,"oa_url":93,"card":94,"direction":100,"ingested_from":101},"W7167492172",[84,87,89],{"name":85,"orcid":86},"Shai Avraham Shaked","https:\u002F\u002Forcid.org\u002F0000-0003-1995-6419",{"name":88,"orcid":9},"Assaf Shechter",{"name":90,"orcid":91},"Amir Sagi","https:\u002F\u002Forcid.org\u002F0000-0002-4229-1059",0,"https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2772375526007793\u002Fpdf",{"tldr":95,"method":96,"finding":97,"direction":98,"opportunity":99},"用大语言模型辅助人类专家，解决罗氏沼虾RAS育苗中幼体高死亡率问题。","四个月案例观察，LLM与人类专家协作分析化学、生物、工程等多域数据。","AI建议的矿物质平衡、微生物诊断等干预降低了幼体死亡率并提高变态率。","农业人工智能与决策模型","可研究LLM在RAS多参数耦合决策中的可解释性与人机协同机制，避免过度简化。","智慧农业 \u002F 农业物联网","openalex","2026-09-10T23:30:03.364805Z",{"total":104,"page":21,"page_size":104,"items":105},6,[106,178,262,325,406,470],{"id":107,"title":108,"url":109,"summary":110,"summary_zh":111,"content":9,"source_name":112,"source_url":109,"published_at":113,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":114,"score_detail":115,"sources":120,"tags":122,"primary_topic":125,"secondary_topics":130,"classification":132,"search_phrases":152,"slug":155,"view_count":92,"doi":156,"paper":157,"created_at":177},5376,"Agri-Synergy: A Hardware–Software Co-Designed Hybrid IoT System for Sensor Interface Standardization and LLM-Driven Interactive Decision Support","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriengineering8100446","This paper presents Agri-Synergy, a hybrid Internet of Things (IoT) system featuring a hardware–software co-design to tackle sensor data heterogeneity and the barriers to effective AI-driven decision support in smart agriculture. Unlike software-based data harmonization, we propose a universal sensor printed circuit board (PCB) with RS485\u002FModbus interface for hardware unification, complemented by on-node edge processing that ensures standardized data from source. To lower the entry barrier for farmers, the system integrates the DeepSeek large language model (LLM) API, combining static agricultural knowledge with real-time sensor data, for context-aware, natural language-based decision support, functioning without local model deployment. Field deployment showed reference-verified sensor accuracy predominantly within manufacturer specifications, stable 4G connectivity during the 4-h benchmark but intermittent dropouts during the 20-day deployment, and remote-control success rates of 96% (normal) and 80% (weak signal at 300 m). Multi-node concurrent transmission resulted in average latency of 238.0 ± 27.1 ms and packet loss below 0.5%. The system achieves a 3–5× cost reduction compared to commercial platforms. These results demonstrate that addressing data heterogeneity from source through hardware unification and software edge processing, while leveraging AI to lower the barrier to system adoption, provides a more reliable foundation for data synchronization and accessible AI-driven analytics.","本文提出Agri-Synergy，一种采用软硬件协同设计的混合物联网（IoT）系统，旨在解决智慧农业中传感器数据异构性问题以及有效AI驱动决策支持的障碍。与基于软件的数据协调方式不同，我们提出了一种带有RS485\u002FModbus接口的通用传感器印刷电路板（PCB）以实现硬件统一，并辅以节点端边缘处理，确保从源头获得标准化数据。为降低农民的使用门槛，该系统集成了DeepSeek大语言模型（LLM）API，将静态农业知识与实时传感器数据相结合，提供上下文感知的、基于自然语言的决策支持，且无需本地部署模型即可运行。现场部署表明，经参考验证的传感器精度基本处于制造商规格范围内；在4小时基准测试期间4G连接稳定，但在20天部署期间出现间歇性断连；远程控制成功率分别为96%（正常信号）和80%（300 m处弱信号）。多节点并发传输的平均延迟为238.0 ± 27.1 ms，丢包率低于0.5%。与商业平台相比，该系统实现了3–5倍的成本降低。这些结果表明，通过硬件统一和软件边缘处理从源头解决数据异构性问题，同时利用AI降低系统采用门槛，可为数据同步和可及的AI驱动分析提供更可靠的基础。","AgriEngineering","2026-10-19T00:00:00Z",76,{"impact":116,"substance":18,"depth":17,"authority":117,"freshness":118,"relevant":21,"comment":119},16,12,9,"硬件统一接口与边缘处理结合大模型决策支持的农业物联网系统论文，方法新颖、有实地部署数据，但属细分技术进展，公共影响有限。",[121],{"name":112,"url":109},[26,27,123,28,124],"农业物联网","传感器标准化",{"code":126,"slug":127,"name":128,"path":129,"parent_code":43},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[131],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":133},{"candidates":134,"agricultural_evidence":52},[135,142,146],{"code":126,"score":17,"supported":52,"title":136,"abstract":138,"tags":141},[137],"IoT",[139,140,137],"物联网","internet of things",[123],{"code":39,"score":116,"supported":52,"title":143,"abstract":144,"tags":145},[66],[68,66],[27,28],{"code":71,"score":147,"supported":52,"title":148,"abstract":149,"tags":151},7,[],[26,150],"smart agriculture",[26],[153,154],"Agri-Synergy 物联网 传感器","DeepSeek 决策支持","Agri-Synergy物联网传感器-5376","10.3390\u002Fagriengineering8100446",{"doi":156,"openalex_id":158,"authors":159,"venue":112,"cited_by_count":92,"oa_url":109,"card":172,"direction":100,"ingested_from":101},"W7222920424",[160,162,164,166,168,170],{"name":161,"orcid":9},"Leqi Lai",{"name":163,"orcid":9},"Langtao Duan",{"name":165,"orcid":9},"Yuhao Chen",{"name":167,"orcid":9},"Yuhang Zheng",{"name":169,"orcid":9},"Jinyu Yang",{"name":171,"orcid":9},"Mingyao Wen",{"tldr":173,"method":174,"finding":175,"direction":100,"opportunity":176},"提出软硬件协同的混合物联网系统，统一传感器接口并用大模型提供交互式决策支持。","通用RS485\u002FModbus传感器PCB、节点边缘处理、DeepSeek大模型A","传感器精度达标，多节点延迟238ms、丢包低于0.5%，成本降低3-5倍。","可研究弱信号下通信可靠性提升与边缘-云端LLM协同的长期田间鲁棒性。","2026-10-20T23:30:08.319698Z",{"id":179,"title":180,"url":181,"summary":182,"summary_zh":183,"content":9,"source_name":184,"source_url":181,"published_at":185,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":186,"score_detail":187,"sources":190,"tags":192,"primary_topic":195,"secondary_topics":196,"classification":197,"search_phrases":245,"slug":248,"view_count":92,"doi":249,"paper":250,"created_at":261},5232,"Current applications of artificial intelligence for advancing agriculture, sustainability and climate mitigation","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02540-1","Artificial intelligence (AI) is reshaping agriculture by enabling data-driven decision-making across crop production systems and supporting the transition toward more sustainable, resilient, and climate-smart farming. This review critically synthesizes advances in AI applications spanning precision irrigation, nutrient and soil management, yield prediction, pest and disease monitoring, computer vision, autonomous agricultural robotics, and large language model (LLM)-based decision support systems. Beyond summarizing technological developments, the review evaluates their practical deployment, emphasizing that successful agricultural AI depends not only on predictive accuracy but also on model generalizability, explainability, economic feasibility, interoperability, and integration with existing agronomic knowledge. Emerging technologies including Vision Transformers, foundation models, Digital Twins, multimodal AI, Retrieval-Augmented Generation, and federated and continual learning—are discussed as important directions for overcoming limitations related to data scarcity, environmental variability, and scalable field implementation. The review highlights that responsible AI adoption requires transparent governance frameworks addressing data ownership, privacy, algorithmic fairness, cybersecurity, and equitable access, particularly for smallholder farming systems. Although numerous AI models report outstanding performance, widespread agricultural adoption remains constrained by cross-region validation, fragmented datasets, infrastructure requirements, and insufficient real-world deployment. Future progress will depend on multidisciplinary collaboration integrating advances in artificial intelligence, sensing technologies, robotics, crop science, and agricultural engineering to develop robust, trustworthy, and farmer-centered decision-support systems. By critically evaluating technological innovations and implementation challenges, this review provides a framework for understanding the current state of AI in agriculture while identifying research priorities that will shape the next generation of sustainable and climate-resilient agricultural systems.","人工智能（AI）正在重塑农业，通过在作物生产系统中实现数据驱动的决策，并支持向更可持续、更具韧性和气候智能型农业转型。本综述批判性地综合了AI应用的进展，涵盖精准灌溉、养分与土壤管理、产量预测、病虫害监测、计算机视觉、自主农业机器人以及基于大语言模型（LLM）的决策支持系统。除总结技术发展外，本综述还评估了其实际部署情况，强调农业AI的成功不仅取决于预测准确性，还取决于模型泛化能力、可解释性、经济可行性、互操作性以及与现有农学知识的整合。文中讨论了包括视觉Transformer、基础模型、数字孪生、多模态AI、检索增强生成以及联邦学习和持续学习在内的新兴技术，将其视为克服数据稀缺、环境变异性和田间可扩展实施等局限的重要方向。本综述强调，负责任的AI采用需要透明的治理框架，以解决数据所有权、隐私、算法公平性、网络安全和公平获取等问题，尤其是对小农耕作系统而言。尽管众多AI模型报告了卓越的性能，但农业领域的广泛采用仍受限于跨区域验证、碎片化数据集、基础设施要求以及现实世界部署不足。未来的进展将取决于多学科协作，整合人工智能、传感技术、机器人技术、作物科学和农业工程领域的进展，以开发稳健、可信且以农民为中心的决策支持系统。通过批判性评估技术创新和实施挑战，本综述提供了一个理解AI在农业中现状的框架，同时确定了将塑造下一代可持续和气候韧性农业系统的研究优先事项。","Discover Artificial Intelligence","2026-10-17T00:00:00Z",83,{"impact":188,"substance":188,"depth":17,"authority":117,"freshness":118,"relevant":21,"comment":189},22,"该综述系统梳理了AI在农业中的应用与落地瓶颈，覆盖精准灌溉、机器人、大模型决策支持等方向，信息密度高，但属综述类论文，产业级突破性有限，可入精选。",[191],{"name":184,"url":181},[26,27,28,193,194],"数字孪生","气候智慧农业",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":198},{"candidates":199,"agricultural_evidence":52},[200,208,215,222,227,234,240],{"code":39,"score":201,"supported":52,"title":202,"abstract":204,"tags":207},19,[203],"artificial intelligence",[205,203,206,68,66],"计算机视觉","computer vision",[27,28],{"code":209,"score":104,"supported":52,"title":210,"abstract":211,"tags":214},"H2",[],[212,213],"土壤","soil",[],{"code":216,"score":104,"supported":52,"title":217,"abstract":218,"tags":221},"H3",[],[219,220],"灌溉","irrigation",[],{"code":71,"score":223,"supported":52,"title":224,"abstract":225,"tags":226},5,[],[193],[193,26],{"code":228,"score":229,"supported":52,"title":230,"abstract":231,"tags":233},"F6",3,[],[232],"农业机器人",[],{"code":235,"score":229,"supported":52,"title":236,"abstract":237,"tags":239},"G2",[],[238],"smallholder",[],{"code":241,"score":21,"supported":14,"title":242,"abstract":243,"tags":244},"H7",[],[],[194],[246,247],"气候智慧农业 AI","农业人工智能 气候智慧农业 大语言模型 数字孪生","气候智慧农业AI-5232","10.1007\u002Fs44163-026-02540-1",{"doi":249,"openalex_id":251,"authors":252,"venue":184,"cited_by_count":92,"oa_url":181,"card":256,"direction":100,"ingested_from":101},"W7222823256",[253],{"name":254,"orcid":255},"Mostafa Farajpour","https:\u002F\u002Forcid.org\u002F0000-0003-4223-502X",{"tldr":257,"method":258,"finding":259,"direction":98,"opportunity":260},"综述农业人工智能在精准灌溉、产量预测、病虫害监测等应用及落地挑战。","文献综述，覆盖视觉Transformer、基础模型、数字孪生、多模态AI与联邦学","农业AI落地受限于跨区域验证、数据碎片化与基础设施，需兼顾可解释性与公平治理。","可研究小农户场景下跨区域可泛化、可解释且低成本的农业大模型与联邦学习部署。","2026-10-18T23:30:07.666127Z",{"id":263,"title":264,"url":265,"summary":266,"summary_zh":267,"content":9,"source_name":268,"source_url":265,"published_at":269,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":270,"score_detail":271,"sources":275,"tags":277,"primary_topic":280,"secondary_topics":281,"classification":282,"search_phrases":299,"slug":302,"view_count":229,"doi":303,"paper":304,"created_at":324},2913,"A quantum-inspired multi-objective learning framework for real-time sustainable aquaculture water quality prediction","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1827991","Management of sustainable aquaculture necessitates accurate prediction of water quality parameters, since environmental variability is an important factor in determining aquatic productivity and ecological stability. Traditional machine learning systems are usually limited by inefficient parameter optimization, feature overlap, and limited adaptability to non-linear and time-varying environmental trends. To address these issues, a new concept is proposed, which is called Quantum-Inspired Aquaculture Optimization Network (Q-AQUAOptNet). To improve the process of feature selection, hyperparameter optimization, and model stability before temporal prediction, the proposed architecture combines sustainability index modeling and quantum-inspired multi-objective evolutionary optimization. The optimization approach balances exploration and exploitation, enhancing the learning ability of the prediction model. Implementation of the framework was done through Python-based simulation tools in preprocessing, optimization, and performance evaluation. The created system had a Root Mean Square Error of 0.24, a Mean Absolute Error of 0.21, and an R 2 of 0.97, which means that it has effective predictive power and a great ability to explain the variance. Integrating evolutionary optimization and temporal learning improves generalization performance and reduces prediction uncertainty. The findings demonstrate that Q-AQUAOptNet provides effective predictive performance within a simulation-based framework and shows potential as a sustainability-oriented intelligent water-quality monitoring and decision support system for aquaculture applications.","可持续水产养殖管理需要准确预测水质参数，因为环境变异性是决定水生生产力和生态稳定性的重要因素。传统机器学习系统通常受限于参数优化效率低、特征重叠以及对非线性和时变环境趋势的适应能力有限。为解决这些问题，提出了一种新概念，称为量子启发水产养殖优化网络（Quantum-Inspired Aquaculture Optimization Network，Q-AQUAOptNet）。为在时间预测之前改进特征选择、超参数优化和模型稳定性，所提出的架构结合了可持续性指数建模和量子启发多目标进化优化。该优化方法平衡了探索与利用，增强了预测模型的学习能力。该框架的实现通过基于Python的仿真工具完成，涵盖预处理、优化和性能评估。所构建系统的均方根误差为0.24，平均绝对误差为0.21，R²为0.97，这意味着其具有有效的预测能力和较强的方差解释能力。将进化优化与时间学习相结合，提高了泛化性能并降低了预测不确定性。研究结果表明，Q-AQUAOptNet在基于仿真的框架内提供了有效的预测性能，并显示出作为面向可持续性的智能水质监测与决策支持系统应用于水产养殖的潜力。","Frontiers in Sustainable Food Systems","2026-09-18T00:00:00Z",71,{"impact":117,"substance":272,"depth":273,"authority":19,"freshness":118,"relevant":21,"comment":274},20,17,"提出量子启发多目标优化网络用于水产养殖水质预测，仿真指标较优，属智慧渔业细分领域的方法学进展，但尚处仿真阶段、缺乏真实场景验证。",[276],{"name":268,"url":265},[26,27,29,278,279],"多目标优化","水质预测",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":283},{"candidates":284,"agricultural_evidence":52},[285,289,295],{"code":36,"score":51,"supported":52,"title":286,"abstract":287,"tags":288},[54],[56,54],[29],{"code":39,"score":13,"supported":52,"title":290,"abstract":291,"tags":294},[],[292,293,66],"机器学习","machine learning",[27],{"code":71,"score":21,"supported":14,"title":296,"abstract":297,"tags":298},[],[],[26],[300,301],"Q-AQUAOptNet 水产养殖 水质预测","农业人工智能 多目标优化 智慧农业 水产养殖","Q-AQUAOptNet水产养殖水质预测-2913","10.3389\u002Ffsufs.2026.1827991",{"doi":303,"openalex_id":305,"authors":306,"venue":268,"cited_by_count":92,"oa_url":265,"card":319,"direction":100,"ingested_from":101},"W7213532503",[307,310,313,315,317],{"name":308,"orcid":309},"Abdel‐Haleem Abdel‐Aty","https:\u002F\u002Forcid.org\u002F0000-0002-6763-2569",{"name":311,"orcid":312},"Ali Jaber Almalki","https:\u002F\u002Forcid.org\u002F0009-0004-1359-2612",{"name":314,"orcid":9},"Sara A. Ghorashi",{"name":316,"orcid":9},"Betty Wan Niu Voon",{"name":318,"orcid":9},"Mohamed Hafez",{"tldr":320,"method":321,"finding":322,"direction":100,"opportunity":323},"提出量子启发多目标优化网络Q-AQUAOptNet，实现水产养殖水质实时预测。","量子启发多目标进化优化结合时间预测与可持续指数建模，Python仿真。","RMSE 0.24、MAE 0.21、R² 0.97，预测精度高且泛化好。","可探索真实养殖场部署与多源传感器融合，验证量子启发优化在边缘端的实时性。","2026-09-19T23:30:07.985707Z",{"id":326,"title":327,"url":328,"summary":329,"summary_zh":9,"content":9,"source_name":330,"source_url":9,"published_at":331,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":332,"score_detail":333,"sources":335,"tags":337,"primary_topic":341,"secondary_topics":347,"classification":355,"search_phrases":392,"slug":395,"view_count":396,"doi":9,"paper":397,"created_at":405},2494,"露地白萝卜定植收获农机农艺垂直大模型调优方法研究(NRA-LoRA, Qwen3-4B LLM-Metric 84.32)","http:\u002F\u002Fwww.qikanvip.com\u002Fqkml\u002F166270.html","山东农业大学机械与电子工程学院李扬、褚化星、李天华、赵维松、潘浩晨、王善平,山东省设施园艺智慧生产技术装备重点实验室,农业农村部南京农业机械化研究所,山东省果树研究所联合发表。针对通用大语言模型在露地白萝卜定植与收获场景中专业性不足、农机农艺协同能力弱等问题,提出融合农机农艺知识垂直大模型调优方法。构建包含农机、农艺、农机农艺关联和定植收获关联 4 类知识专用数据集,共 14524 条数据;提出非均匀 Rank 分配的 NRA-LoRA 微调方法。Qwen3-4B(NRA-LoRA)表现最优,LLM-Metric 达 84.32,BLEU-4\u002FROUGE-1\u002F2\u002FL 分别 30.95\u002F52.68\u002F23.84\u002F41.96。","农机化研究 2026(11) 2026-09-10","2026-09-09T16:00:00Z",75,{"impact":51,"substance":188,"depth":17,"authority":59,"freshness":104,"relevant":21,"comment":334},"面向露地白萝卜定植收获的农机农艺垂直大模型微调研究，方法新颖、数据规模可观，属细分领域实质性技术进展，但应用面较窄，适合作为主题聚合素材而非头条精选。",[336],{"name":330,"url":328},[26,27,338,28,339,340],"智能农机","农机农艺融合","白萝卜",{"code":342,"slug":343,"name":344,"path":345,"parent_code":346},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[348,354],{"code":349,"slug":350,"name":351,"path":352,"parent_code":353},"F5","machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","F",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":356},{"candidates":357,"agricultural_evidence":52},[358,365,370,376,382,388],{"code":349,"score":201,"supported":52,"title":359,"abstract":361,"tags":364},[360],"农机",[360,362,363],"农业机械","机械化",[339,338],{"code":39,"score":19,"supported":52,"title":366,"abstract":368,"tags":369},[367],"大模型",[367],[27,28],{"code":342,"score":371,"supported":52,"title":372,"abstract":374,"tags":375},11,[373],"萝卜",[373],[],{"code":377,"score":229,"supported":52,"title":378,"abstract":379,"tags":381},"B2",[],[380],"果树",[],{"code":383,"score":229,"supported":52,"title":384,"abstract":385,"tags":387},"B7",[],[386],"设施园艺",[],{"code":71,"score":21,"supported":14,"title":389,"abstract":390,"tags":391},[],[],[26],[393,394],"农业人工智能 农机农艺融合 大语言模型 智慧农业","农业人工智能 农机农艺融合","农业人工智能农机农艺融合大语言模型智慧农业-2494",2,{"doi":9,"openalex_id":9,"authors":398,"venue":9,"cited_by_count":92,"oa_url":9,"card":399,"direction":98,"ingested_from":404},[],{"tldr":400,"method":401,"finding":402,"direction":98,"opportunity":403},"提出NRA-LoRA微调方法，构建农机农艺知识数据集，提升白萝卜定植收获垂直大模型性能。","构建14524条农机农艺知识数据集，采用非均匀Rank分配的NRA-LoRA微调","Qwen3-4B(NRA-LoRA)最优，LLM-Metric达84.32，BLEU-4\u002FROUGE","可探索非均匀Rank分配在更多作物农机农艺场景的泛化，及知识图谱增强的垂直大模型。","agent","2026-09-15T00:04:27.326828Z",{"id":407,"title":408,"url":409,"summary":410,"summary_zh":411,"content":9,"source_name":412,"source_url":409,"published_at":413,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":414,"sources":416,"tags":418,"primary_topic":421,"secondary_topics":422,"classification":423,"search_phrases":438,"slug":441,"view_count":79,"doi":442,"paper":443,"created_at":469},2281,"Artificial intelligence-enabled aquacultural engineering systems: A design-oriented review of sensing, modelling, and deployment architectures","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112353","Artificial intelligence-enabled aquacultural engineering systems: A design-oriented review of sensing, modelling, and deployment architectures。Computers and Electronics in Agriculture","人工智能赋能的水产养殖工程系统：面向设计的传感、建模与部署架构综述。农业中的计算机与电子学","Computers and Electronics in Agriculture","2026-09-11T00:00:00Z",{"impact":17,"substance":272,"depth":17,"authority":59,"freshness":20,"relevant":21,"comment":415},"核心期刊发表的水产养殖AI工程系统设计综述，涵盖感知、建模与部署架构，对智慧渔业技术路线有参考价值，但属综述类论文，产业落地影响有限。",[417],{"name":412,"url":409},[26,27,29,419,420],"智能传感","数字渔业",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":424},{"candidates":425,"agricultural_evidence":52},[426,430,434],{"code":39,"score":117,"supported":52,"title":427,"abstract":428,"tags":429},[203],[203],[27],{"code":36,"score":79,"supported":52,"title":431,"abstract":432,"tags":433},[],[56],[29],{"code":71,"score":21,"supported":14,"title":435,"abstract":436,"tags":437},[],[],[26],[439,440],"农业人工智能 数字渔业 智慧农业 智能传感","农业人工智能 数字渔业","农业人工智能数字渔业智慧农业智能传感-2281","10.1016\u002Fj.compag.2026.112353",{"doi":442,"openalex_id":444,"authors":445,"venue":412,"cited_by_count":92,"oa_url":409,"card":464,"direction":100,"ingested_from":101},"W7212232512",[446,449,452,455,458,461],{"name":447,"orcid":448},"V. Ravi Sankar","https:\u002F\u002Forcid.org\u002F0000-0002-8580-2920",{"name":450,"orcid":451},"Alzayat Saleh","https:\u002F\u002Forcid.org\u002F0000-0001-6973-019X",{"name":453,"orcid":454},"Armin Ehrampoosh","https:\u002F\u002Forcid.org\u002F0000-0002-5482-3454",{"name":456,"orcid":457},"Phoebe Arbon","https:\u002F\u002Forcid.org\u002F0000-0003-0171-6302",{"name":459,"orcid":460},"Dean R. Jerry","https:\u002F\u002Forcid.org\u002F0000-0003-3735-1798",{"name":462,"orcid":463},"Mostafa Rahimi Azghadi","https:\u002F\u002Forcid.org\u002F0000-0001-7975-3985",{"tldr":465,"method":466,"finding":467,"direction":100,"opportunity":468},"综述AI赋能水产养殖工程系统，从感知、建模到部署架构的设计视角。","设计导向综述，梳理传感器、AI建模与部署架构。","提出面向水产养殖的AI工程系统设计框架与架构分类。","可针对水产养殖场景的轻量化边缘AI与多模态传感融合部署开展实证研究。","2026-09-13T23:30:01.790828Z",{"id":471,"title":472,"url":473,"summary":474,"summary_zh":475,"content":9,"source_name":476,"source_url":473,"published_at":477,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":478,"score_detail":479,"sources":481,"tags":483,"primary_topic":487,"secondary_topics":492,"classification":494,"search_phrases":509,"slug":512,"view_count":92,"doi":513,"paper":514,"created_at":528},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",69,{"impact":20,"substance":18,"depth":17,"authority":117,"freshness":13,"relevant":21,"comment":480},"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[482],{"name":476,"url":473},[26,27,484,485,486],"小农户","植物病害识别","可解释性",{"code":235,"slug":488,"name":489,"path":490,"parent_code":491},"farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[493],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":495},{"candidates":496,"agricultural_evidence":52},[497,501,505],{"code":235,"score":117,"supported":52,"title":498,"abstract":499,"tags":500},[238],[238],[484],{"code":39,"score":13,"supported":52,"title":502,"abstract":503,"tags":504},[206],[],[27,485],{"code":71,"score":21,"supported":14,"title":506,"abstract":507,"tags":508},[],[],[26],[510,511],"农业人工智能 植物病害识别 可解释性 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":513,"openalex_id":515,"authors":516,"venue":476,"cited_by_count":92,"oa_url":473,"card":523,"direction":98,"ingested_from":101},"W7223137323",[517,519,521],{"name":518,"orcid":9},"Akshay Ramgoolam",{"name":520,"orcid":9},"Priya Bundhoo Appadoo",{"name":522,"orcid":9},"Jean-Noël LEspérance",{"tldr":524,"method":525,"finding":526,"direction":98,"opportunity":527},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z"]