[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3665":3,"related-3665":52},{"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,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":51},3665,"ASAS-NANP SYMPOSIUM: MATHEMATICAL MODELING IN ANIMAL NUTRITION: The Evolution of Large Language Models and Their Impact on Animal Sciences","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fjas\u002Fskag306","The rapid rise of large language models (LLM) is reshaping the scientific landscape, transitioning from early statistical language models to advanced transformer-based architectures capable of synthesizing knowledge across disciplines. While their predictive capacity and scalability have opened new avenues in data analysis, hypothesis generation, and decision support, concerns remain regarding bias, hallucination, reproducibility, and ethical governance. In animal sciences, LLM are gradually applied to challenges in nutrition modeling, animal health, genetic selection, and sustainability. Precision nutrition has benefited from LLM-driven synthesis of feed and metabolic data, enabling individualized feeding strategies and improved resource efficiency. In animal health, domain-specific systems have demonstrated applications in diagnostics and epidemiological monitoring. LLM is augmenting genomic analyses to accelerate marker discovery and breeding optimization, while sustainability efforts employ them to model greenhouse gas emissions, feed additives, and adaptation to climatic stressors. Notably, decision-support platforms demonstrate how domain-specialized LLM can bridge mechanistic knowledge with predictive analytics, enhancing knowledge transfer and empowering livestock producers. However, risks associated with overreliance, recursive reuse of LLM outputs in model development, and pseudo-expertise underscore the critical importance of human oversight. Unlike mechanistic models, which embed biological causality, LLM are entirely data-driven and may confidently propagate errors if trained on ill-conditioned datasets. Responsible use requires transparent reporting, validation, and bias auditing, with domain-specific fine-tuning. Open-source models can enhance reproducibility and trust, but they also raise financial and security concerns. LLM must be guided by transparency, accountability, and fairness to ensure they complement, rather than replace, human expertise. By advancing inquiry and livestock management, LLM hold the potential to support sustainable food production systems if deployed responsibly. Rather than full training, most applications will rely on fine-tuning and augmentation, which are more sustainable and adaptable strategies. This review intends to promote critical literacy and responsible adoption of LLM in research, education, and livestock decision-support systems for animal scientists, nutrition modelers, and extension professionals.","大语言模型（LLM）的迅速崛起正在重塑科学格局，从早期的统计语言模型过渡到能够跨学科综合知识的先进基于Transformer的架构。尽管其预测能力和可扩展性在数据分析、假设生成和决策支持方面开辟了新途径，但围绕偏见、幻觉、可重复性和伦理治理的担忧依然存在。在动物科学领域，LLM正逐步应用于营养建模、动物健康、遗传选择和可持续性等方面的挑战。精准营养已受益于LLM驱动的饲料与代谢数据综合，从而实现个体化饲喂策略并提高资源效率。在动物健康方面，领域专用系统已在诊断和流行病学监测中展现出应用价值。LLM正在增强基因组分析，以加速标记发现和育种优化，而可持续性工作则利用其建模温室气体排放、饲料添加剂及对气候胁迫的适应性。值得注意的是，决策支持平台展示了领域专用LLM如何将机制性知识与预测分析相衔接，促进知识转化并赋能畜牧生产者。然而，过度依赖、在模型开发中递归复用LLM输出以及伪专业知识等风险，凸显了人类监督的至关重要性。与嵌入生物学因果关系的机制性模型不同，LLM完全由数据驱动，若在病态数据集上训练，可能自信地传播错误。负责任的使用需要透明报告、验证和偏见审计，并进行领域专用微调。开源模型可以增强可重复性和信任，但也引发财务和安全方面的担忧。LLM必须以透明性、问责制和公平性为指引，以确保其补充而非取代人类专业知识。通过在研究和畜牧管理中推动探究，LLM在负责任部署的前提下具有支持可持续食品生产系统的潜力。大多数应用将依赖微调和增强，而非完整训练，这是更具可持续性和适应性的策略。本综述旨在促进动物科学家、营养建模人员和推广专业人员在研究、教育和畜牧决策支持系统中对LLM的批判性素养和负责任采用。",null,"Journal of Animal Science","2026-09-25T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,20,14,8,1,"核心期刊综述，系统梳理大语言模型在动物营养、健康与育种中的应用与风险，专业深度高但属综述性论文，产业级影响有限。",[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","精准营养","动物科学",[32,33],"大语言模型 动物科学","LLM 精准营养","大语言模型动物科学-3665",0,"10.1093\u002Fjas\u002Fskag306",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":42,"card":43,"direction":49,"ingested_from":50},"W7214347972",[40],{"name":41,"orcid":9},"Luis O Tedeschi","https:\u002F\u002Facademic.oup.com\u002Fjas\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fjas\u002Fskag306\u002F71398322\u002Fskag306.pdf",{"tldr":44,"method":45,"finding":46,"direction":47,"opportunity":48},"综述大语言模型在动物科学中的应用、风险与负责任使用路径。","文献综述，梳理LLM在营养、健康、遗传和可持续性中的应用。","LLM可辅助精准营养与决策支持，但需人类监督、验证和领域微调。","农业人工智能与决策模型","可探索面向畜牧生产的领域专用LLM微调与可验证决策支持系统，并建立偏差审计与可复现评估框架。","智慧农业 \u002F 农业物联网","openalex","2026-09-28T23:30:12.831387Z",{"total":53,"page":21,"page_size":53,"items":54},6,[55,86,109,148,178,200],{"id":56,"title":57,"url":58,"summary":59,"summary_zh":9,"content":9,"source_name":60,"source_url":9,"published_at":61,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":62,"score_detail":63,"sources":67,"tags":69,"search_phrases":73,"slug":76,"view_count":21,"doi":9,"paper":77,"created_at":85},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":64,"substance":65,"depth":17,"authority":19,"freshness":53,"relevant":21,"comment":66},15,22,"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。",[68],{"name":60,"url":58},[26,27,70,28,71,72],"智能农机","农机农艺融合","白萝卜",[74,75],"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",{"doi":9,"openalex_id":9,"authors":78,"venue":9,"cited_by_count":35,"oa_url":9,"card":79,"direction":47,"ingested_from":84},[],{"tldr":80,"method":81,"finding":82,"direction":47,"opportunity":83},"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":87,"title":88,"url":89,"summary":90,"summary_zh":9,"content":9,"source_name":91,"source_url":9,"published_at":92,"category":93,"cover_url":9,"hotness":13,"is_selected":14,"score":94,"score_detail":95,"sources":99,"tags":101,"search_phrases":104,"slug":107,"view_count":35,"doi":9,"paper":9,"created_at":108},2228,"棉花所联合西部农业研究中心发布全球首个棉花领域专属大语言模型\"棉芯1.0\"","https:\u002F\u002Fdy.163.com\u002Farticle\u002FL6HM1VUQ05199FC8.html","中国农业科学院棉花研究所联合西部农业研究中心8月下旬发布全球首个棉花领域专属知识大语言模型\"CottonMind1.0\",覆盖棉花种质资源、品种性状、栽培管理、加工利用等全产业链数据,标志着农业AI从通用模型向行业垂直深耕转向。","中国农业科学院 布瑞克农业数据","2026-09-10T16:00:00Z","报道",85,{"impact":96,"substance":65,"depth":97,"authority":19,"freshness":53,"relevant":21,"comment":98},26,17,"全球首个棉花领域专属大语言模型，覆盖全产业链数据，标志农业AI向垂直深耕转型，产业级突破值得入选。",[100],{"name":91,"url":89},[26,27,102,28,103],"种业振兴","棉花",[105,106],"农业人工智能 大语言模型 智慧农业 种业振兴","农业人工智能 大语言模型","农业人工智能大语言模型智慧农业种业振兴-2228","2026-09-13T00:04:00.640632Z",{"id":110,"title":111,"url":112,"summary":113,"summary_zh":114,"content":9,"source_name":115,"source_url":112,"published_at":116,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":117,"sources":121,"tags":123,"search_phrases":126,"slug":128,"view_count":35,"doi":129,"paper":130,"created_at":147},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。","Smart Agricultural Technology","2026-09-07T00:00:00Z",{"impact":17,"substance":118,"depth":17,"authority":119,"freshness":20,"relevant":21,"comment":120},21,13,"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。",[122],{"name":115,"url":112},[26,27,28,124,125],"水产养殖","循环水养殖",[127,106],"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循环水养殖智慧农业-2020","10.1016\u002Fj.atech.2026.102554",{"doi":129,"openalex_id":131,"authors":132,"venue":115,"cited_by_count":35,"oa_url":141,"card":142,"direction":49,"ingested_from":50},"W7167492172",[133,136,138],{"name":134,"orcid":135},"Shai Avraham Shaked","https:\u002F\u002Forcid.org\u002F0000-0003-1995-6419",{"name":137,"orcid":9},"Assaf Shechter",{"name":139,"orcid":140},"Amir Sagi","https:\u002F\u002Forcid.org\u002F0000-0002-4229-1059","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2772375526007793\u002Fpdf",{"tldr":143,"method":144,"finding":145,"direction":47,"opportunity":146},"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。","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。","2026-09-10T23:30:03.364805Z",{"id":149,"title":150,"url":151,"summary":152,"summary_zh":153,"content":9,"source_name":154,"source_url":151,"published_at":155,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":156,"score_detail":157,"sources":160,"tags":162,"search_phrases":165,"slug":167,"view_count":35,"doi":168,"paper":169,"created_at":177},1624,"AGRITWIN AI: A DIGITAL TWIN AND MULTIMODAL EXPLAINABLE AI FRAMEWORK FOR PRECISION AGRICULTURE USING SATELLITE IMAGERY, IOT SENSORS, WEATHER INTELLIGENCE, LARGE LANGUAGE MODELS, AND RETRIEVAL-AUGMENTED GENERATION","https:\u002F\u002Fdoi.org\u002F10.56726\u002Firjmets102032","Current digital precision agricultural systems suffer from a critical, structural operational data-cognition gap: modern cyber-physical sensing systems (e.g.IoT devices, remote sensing pipelines) operate as opaque numeric computation engines yielding multi-dimensional, high-frequency numeric matrices while agriculture specific Large Language Models (LLMs) remain locked into a non-numeric world that is conceptually divorced from physical realities on the ground.To bridge this data-cognition gap, this paper proposes AgriTwin AI: a holistic, end-to-end framework coupling a spatial-temporal Digital Twin engine to an autonomous, Multimodal Explainable AI (XAI) advisory pipeline.AgriTwin AI ingests heterogeneous input from 1D linear IoT sensor streams, text-based meteorological intelligence, and 2D multi-spectral satellite raster images; an asymmetric, cross-modal late-fusion architecture synchronizes these data types into a coherent, real-time virtual representation of the farm field.When the physics-driven equations of the Digital Twin engine identify an environmental threshold breach or anomaly, AgriTwin AI automatically triggers a bespoke Retrieval-Augmented Generation (RAG) cycle that is governed by an agronomic Domain Knowledge Processing Layer (DKPL).Linking fine-tuned vision-language parameters of Low-Rank Adaptation (LoRA) to text documents from regional agricultural handbooks stored in a local vector database, AgriTwin AI translates complex numerical anomalies into highly specific, traceable, and human-verifiable natural language diagnostic information.Based on preliminary simulation, AgriTwin AI reduces biological hallucinations below 0.4% and achieves a 95.2% safety constraint validation accuracy, establishing a reliable system for data-driven, explainable, and secure agricultural decision making.","当前的数字精准农业系统面临着一个关键的结构性运营数据认知鸿沟：现代网络物理感知系统（如物联网设备、遥感处理管道）作为不透明的数值计算引擎运行，产生多维、高频的数值矩阵，而农业专用的大语言模型（LLMs）仍局限于非数值世界，在概念上与地面物理现实脱节。为弥合这一数据认知鸿沟，本文提出AgriTwin AI：一个将时空数字孪生引擎与自主多模态可解释人工智能（XAI）咨询管道相结合的整体端到端框架。AgriTwin AI接收来自一维线性物联网传感器流、基于文本的气象情报以及二维多光谱卫星栅格图像的异构输入；一种非对称的跨模态后期融合架构将这些数据类型同步为连贯、实时的农田虚拟表示。当数字孪生引擎的物理驱动方程识别出环境阈值突破或异常时，AgriTwin AI自动触发由农学领域知识处理层（DKPL）管理的定制检索增强生成（RAG）循环。通过将低秩适应（LoRA）的微调视觉-语言参数与存储在本地向量数据库中的区域农业手册文本文档相连接，AgriTwin AI将复杂的数值异常转化为高度具体、可追溯且可由人工验证的自然语言诊断信息。基于初步模拟，AgriTwin AI将生物幻觉率降至0.4%以下，并达到95.2%的安全约束验证准确率，为数据驱动、可解释且安全的农业决策建立了可靠系统。","International Research Journal of Modernization in Engineering Technology and Science","2026-09-03T00:00:00Z",73,{"impact":17,"substance":65,"depth":17,"authority":20,"freshness":158,"relevant":21,"comment":159},7,"提出整合数字孪生与多模态可解释AI的农业框架，方法新颖，但尚处模拟阶段，信源为普通期刊。",[161],{"name":154,"url":151},[26,27,28,163,164],"数字孪生","遥感",[166,106],"农业人工智能 大语言模型 数字孪生 智慧农业","农业人工智能大语言模型数字孪生智慧农业-1624","10.56726\u002Firjmets102032",{"doi":168,"openalex_id":170,"authors":171,"venue":154,"cited_by_count":35,"oa_url":151,"card":172,"direction":49,"ingested_from":50},"W7207853514",[],{"tldr":173,"method":174,"finding":175,"direction":47,"opportunity":176},"提出 AgriTwin AI 框架，融合数字孪生与多模态可解释 AI，弥合农业数据与认知鸿沟。","结合数字孪生、跨模态融合、LoRA微调视觉语言模型及RAG，利用卫星、IoT和气","将数值异常转为可验证的自然语言诊断，幻觉率低于0.4%，安全验证准确率95.2%。","可探索多模态融合在作物病害早期诊断中的应用，或开发轻量化边缘部署方案以适配田间实时决策。","2026-09-04T23:30:11.566549Z",{"id":179,"title":180,"url":181,"summary":182,"summary_zh":9,"content":9,"source_name":183,"source_url":9,"published_at":184,"category":93,"cover_url":9,"hotness":13,"is_selected":185,"score":186,"score_detail":187,"sources":192,"tags":194,"search_phrases":196,"slug":198,"view_count":190,"doi":9,"paper":9,"created_at":199},1162,"中国农业科学院棉花研究所发布全球首个棉花专属大语言模型棉芯1.0 中英文维吾尔语乌兹别克语四语服务","https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F8\u002F570344.shtm","8月24日,中国农业科学院棉花研究所联合中国农业科学院西部农业研究中心正式发布全球首个棉花领域专属知识大语言模型棉芯1.0(CottonMind1.0),标志着我国棉花产业迈入AI+科研+生产深度融合新阶段。棉芯1.0以网页端+小程序端双端设计,网页端为科研人员打造云端智研工作台集成AI智能检索、文献加速阅读、知识图谱可视化等功能;小程序端为棉农打造随身农技专家,提供AI问答、拍照诊断、专家在线咨询等服务。已整合全球41680篇中外文科研文献、2000余项专利与国家标准、559部专业著作、1806条审定品种信息。采用混合检索增强生成与多智能体协同问答方案,有效破解通用AI大模型在农业场景中专业知识不足、幻觉频出等短板。","科学网\u002F中国科学报 2026-08-24","2026-08-24T08:00:00Z",true,87,{"impact":188,"substance":189,"depth":17,"authority":19,"freshness":190,"relevant":21,"comment":191},28,24,3,"全球首个棉花专属大模型，四语服务，整合海量数据，标志棉花产业AI深度融合，影响深远。",[193],{"name":183,"url":181},[26,27,28,195],"棉花产业",[197,106],"农业人工智能 大语言模型 智慧农业 棉花产业","农业人工智能大语言模型智慧农业棉花产业-1162","2026-09-01T00:03:36.434610Z",{"id":201,"title":202,"url":203,"summary":204,"summary_zh":9,"content":205,"source_name":206,"source_url":9,"published_at":207,"category":93,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":208,"sources":211,"tags":213,"search_phrases":218,"slug":221,"view_count":35,"doi":9,"paper":9,"created_at":222},3751,"设施技术国产化让每公斤番茄综合生产成本降至5元","https:\u002F\u002Fnync.yn.gov.cn\u002Fhtml\u002F2026\u002Fyunnongkuanxun-new_0923\u002F1428950.html","云南首个AI+农业全链路示范基地位于昆明市宜良县匡远街道温泉社区。嘉措（云南）农业科技有限公司联合云南指月科技有限公司打造国产化AI种植模式，通过核心算法本地化适配与全链条国产化硬件深度协同，基地里每公斤番茄综合生产成本降至5元，仅为海外高端温室模式的三分之一。","位于昆明市宜良县匡远街道温泉社区的番茄示范基地即将在国庆假期进入采收期。记者近日来到该基地，探访这座云南首个“AI+农业全链路”示范基地。\n\n清晨，基地里一串串番茄在简易薄膜温室内泛着诱人的青红光泽。没有泥泞的土地，没有汗流浃背的弯腰劳作，眼前这座“番茄工厂”安静得只听见蜜蜂授粉时的嗡鸣声和水肥滴灌的微响。\n\n上午8时，有工人陆续进场，偌大的基地只需三五位工人就能打理完毕。物联网感知终端静静矗立，实时采集光照强度、空气温湿度、水肥浓度和作物长势。种苗定植、枝蔓生长、开花坐果到成熟采收，每一个环节都有“数字管家”全程值守。嘉措（云南）农业科技有限公司农场场长李良坐在棚外，掏出手机轻点屏幕，棚内温湿度曲线、土壤含水量、水肥配比参数一目了然。指尖滑动间，灌溉阀自动开启，水肥顺着滴灌带精准送达番茄根部。\n\n“过去种番茄靠经验，现在靠算法。”云南指月科技有限公司项目经理尹文鑫指着棚内的国产化智慧灌溉设备说。这套系统由嘉措（云南）农业科技有限公司联合云南指月科技有限公司打造，创新构建“全域监测+AI算法+智慧灌溉”三位一体的数字化种植模式。\n\n“基地里的全套设备都是国产的。”尹文鑫提高音量信心十足地介绍。长期以来，国内高端设施农业赛道被海外技术路线主导。参照国外植物工厂及高端玻璃温室模式，依托全套进口水肥设备与闭环控制系统虽能实现稳定高产，但每公斤番茄综合生产成本高达13元至15元，加之进口设备造价高、配件周期长、操作门槛高等痛点，技术落地难度极大。而该基地探索的国产化AI种植模式，正在彻底改写这一成本结构。\n\n国产化的意义，最终落在基地每一颗番茄的身价上。通过核心算法本地化适配与全链条国产化硬件深度协同，基地里每公斤番茄综合生产成本降至5元，仅为海外高端温室模式的三分之一。同时，国产化硬件的使用，进一步压缩了采购、部署与运维成本，凸显整套方案规模化落地的性价比。\n\n“云”上管棚，“数”里种田。从传感器、灌溉阀到核心控制系统，基地核心硬件已实现全部国产配套；从数据采集、模型训练到智能决策输出，AI技术真正扎根田间。对种植户而言，AI不再是遥远的科技概念，而是手机里能调水肥、棚里能提产量、年底能多增收的实用“新农具”。（记者：王淑娟）","云南省农业农村厅","2026-09-23T12:00:00Z",{"impact":65,"substance":65,"depth":97,"authority":209,"freshness":53,"relevant":21,"comment":210},11,"云南首个AI+农业全链路示范基地，以国产化硬件与算法将番茄综合成本从13-15元\u002F公斤降至5元，数据具体、多方信源，具备行业示范价值。",[212],{"name":206,"url":203},[26,27,214,215,216,217],"设施农业","云南","番茄","国产化替代",[219,220],"云南 宜良 AI番茄 示范基地","嘉措农业 指月科技 智慧灌溉","云南宜良AI番茄示范基地-3751","2026-09-29T00:08:25.735852Z"]