[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-710":3,"related-710":60},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"primary_topic":26,"secondary_topics":32,"classification":33,"search_phrases":54,"slug":57,"view_count":58,"doi":8,"paper":8,"created_at":59},710,"UltraIR:从分子到复杂样品的红外光谱化学感知与分析仿真到现实迁移学习 [预印本]","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.13341","中国作者团队发布1 亿参数红外光谱基础模型 UltraIR,基于约 6,000 万模拟光谱预训练并融合谱图重建、分子指纹对齐与官能团预测;在官能团预测、混合物定量、细菌分类、药材产地鉴别、微塑料分类及土壤属性预测等任务上均超越传统机器学习与任务专用深度学习,少样本与跨实验室零样本迁移能力显著,为农业土壤属性检测、药材溯源与农产品品质化学感知提供数据高效新路径。[预印本,未经同行评审]",null,"Authors:[Yusen Tan](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Tan,+Y), [Yixuan Chen](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Chen,+Y), [Zheng Fang](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Fang,+Z), [Pan Liu](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Liu,+P), [Yifan Li](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Li,+Y), [Qinyu Guo](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Guo,+Q), [Zhedong Lin](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Lin,+Z), [Yuqiang Li](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Li,+Y), [Xiangxiang Zeng](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Zeng,+X), [Tong Wang](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Wang,+T), [Jun Xia](https:\u002F\u002Farxiv.org\u002Fsearch\u002Fcs?searchtype=author&query=Xia,+J)\n\n[View PDF](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2608.13341)[HTML (experimental)](https:\u002F\u002Farxiv.org\u002Fhtml\u002F2608.13341v2)\n\n> Abstract:Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-intensive, relies on prior knowledge and reference spectra, and is difficult to scale, whereas most machine-learning methods are tailored to individual tasks or datasets, require large labeled training sets, and transfer poorly across analytical objectives and experimental datasets. Here we introduce UltraIR, a foundation model for IR spectroscopy with more than 100 million parameters that enables simulation-to-real transfer learning for chemical sensing and analysis from molecules to complex samples. UltraIR is pretrained on approximately 60 million simulated IR spectra using spectral reconstruction, molecular fingerprint similarity alignment, and functional-group prediction, then adapted to downstream objectives with task-specific labels or targets. Across functional-group prediction, molecular structure elucidation, physicochemical property prediction, mixture-component identification and quantification, bacterial classification, medicinal-herb geographic origin traceability and constituent quantification, microplastics classification, and soil property prediction, UltraIR outperforms conventional machine-learning and task-specific deep-learning baselines. It performs strongly with limited labeled experimental spectra and in zero-shot inference for the same analytical task across Fourier-transform infrared spectrometers and laboratories, providing a route to adaptable, data-efficient chemical sensing from complex real-world samples.\n\nSubjects:Machine Learning (cs.LG); Artificial Intelligence (cs.AI)\nCite as:[arXiv:2608.13341](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.13341) [cs.LG]\n(or [arXiv:2608.13341v2](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.13341v2) [cs.LG] for this version)\n[https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2608.13341](https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2608.13341)\n\narXiv-issued DOI via DataCite\n\n## Submission history\n\nFrom: Yusen Tan [[view email](https:\u002F\u002Farxiv.org\u002Fshow-email\u002F2fb6ad01\u002F2608.13341)] \n\n**[[v1]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.13341v1)** Thu, 13 Aug 2026 15:11:50 UTC (7,895 KB)\n\n**[v2]** Fri, 14 Aug 2026 03:01:37 UTC (7,895 KB)","arXiv:2608.13341 [cs.LG] 2026-08-14","2026-08-14T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该论文主题为红外光谱化学感知与分析，属于化学与机器学习交叉领域，与农业信息化、智慧农业等主题无直接关联，不满足相关性门槛。",[19],{"name":10,"url":6},[21,22,23,24,25],"农业人工智能","预印本","大模型","红外光谱","土壤检测",{"code":27,"slug":28,"name":29,"path":30,"parent_code":31},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"classified","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":41},[39,47],{"code":27,"score":40,"supported":41,"title":42,"abstract":43,"tags":46},8,true,[],[44,45],"深度学习","机器学习",[21,23],{"code":48,"score":49,"supported":41,"title":50,"abstract":51,"tags":53},"H2",4,[],[52],"土壤",[25],[55,56],"农业人工智能 土壤检测 红外光谱 大模型","农业人工智能 土壤检测","农业人工智能土壤检测红外光谱大模型-710",3,"2026-08-18T23:59:19.229607Z",{"total":61,"page":62,"page_size":61,"items":63},6,1,[64,145,200,250,309,360],{"id":65,"title":66,"url":67,"summary":68,"summary_zh":69,"content":8,"source_name":70,"source_url":67,"published_at":71,"category":12,"cover_url":8,"hotness":13,"is_selected":41,"score":72,"score_detail":73,"sources":79,"tags":81,"primary_topic":85,"secondary_topics":86,"classification":87,"search_phrases":103,"slug":106,"view_count":49,"doi":107,"paper":108,"created_at":144},3864,"A Knowledge‐Augmented Wearable System for Interpretable Plant Health Monitoring","https:\u002F\u002Fdoi.org\u002F10.1002\u002Ffle2.70020","ABSTRACT In precision agriculture, modern sensing technologies can autonomously collect and process vast plant data using statistical or machine‐learning models. However, an “interpretability gap” persists: these outputs often remain black‐box correlations rather than interpretable physiological insights, which means users cannot validate their credibility, trace causal links to plant physiology, or translate them into actionable decisions. To bridge this gap, we propose a knowledge‐augmented wearable system for interpretable plant health monitoring (K‐Wear). By coupling a soft wearable sensing platform with a knowledge‐guided reasoning framework, K‐Wear leverages a large language model to transform raw sensing signals into mechanistic diagnoses and recommendations for proactive management. In simulated evaluations, the system achieved 99% diagnostic accuracy and first correctly detected plant stress on day 4.95 on average. In a real 14‐day potassium‐deficiency monitoring experiment, K‐Wear successfully identified early stress signals on day 4 and generated targeted intervention recommendations, enabling timely treatment and recovery of plant health.","在精准农业中，现代传感技术能够利用统计或机器学习模型自主采集并处理海量植物数据。然而，“可解释性鸿沟”依然存在：这些输出往往仍是黑箱式的相关性结果，而非可解释的生理学洞见，这意味着用户无法验证其可信度、追溯其与植物生理的因果联系，或将其转化为可操作的决策。为弥合这一鸿沟，我们提出了一种用于可解释植物健康监测的知识增强可穿戴系统（K‐Wear）。通过将柔性可穿戴传感平台与知识引导的推理框架相结合，K‐Wear利用大语言模型将原始传感信号转化为机理诊断和主动管理建议。在模拟评估中，该系统达到了99%的诊断准确率，并最早在平均第4.95天正确检测到植物胁迫。在一项为期14天的真实缺钾监测实验中，K‐Wear成功在第4天识别出早期胁迫信号，并生成有针对性的干预建议，从而使植物健康得到及时治疗和恢复。","FlexTech","2026-09-29T00:00:00Z",84,{"impact":74,"substance":75,"depth":76,"authority":77,"freshness":40,"relevant":62,"comment":78},22,23,18,13,"将可穿戴传感与大模型知识推理结合，实现可解释的植物健康诊断，方法新颖、实验数据扎实，对智慧农业感知决策有参考价值。",[80],{"name":70,"url":67},[82,21,23,83,84],"智慧农业","可穿戴传感","植物健康监测",{"code":27,"slug":28,"name":29,"path":30,"parent_code":31},[],{"status":34,"locked":14,"version":35,"method":36,"evidence":88},{"candidates":89,"agricultural_evidence":41},[90,95],{"code":27,"score":40,"supported":41,"title":91,"abstract":92,"tags":94},[],[45,93],"large language model",[21,23],{"code":96,"score":97,"supported":41,"title":98,"abstract":99,"tags":102},"I1",7,[],[100,101],"精准农业","precision agriculture",[82],[104,105],"K-Wear 可穿戴 植物健康监测","大语言模型 植物胁迫 诊断","K-Wear可穿戴植物健康监测-3864","10.1002\u002Ffle2.70020",{"doi":107,"openalex_id":109,"authors":110,"venue":70,"cited_by_count":15,"oa_url":67,"card":136,"direction":142,"ingested_from":143},"W7214803187",[111,113,115,117,120,122,125,127,130,133],{"name":112,"orcid":8},"Xingxing Dong",{"name":114,"orcid":8},"Yihan Luo",{"name":116,"orcid":8},"Jiang Qin",{"name":118,"orcid":119},"Jie Ye","https:\u002F\u002Forcid.org\u002F0000-0001-7728-3588",{"name":121,"orcid":8},"Yihui Fan",{"name":123,"orcid":124},"Menghao Pu","https:\u002F\u002Forcid.org\u002F0009-0003-1421-6785",{"name":126,"orcid":8},"Zisheng Zong",{"name":128,"orcid":129},"Guoqiang Xu","https:\u002F\u002Forcid.org\u002F0009-0007-5481-1422",{"name":131,"orcid":132},"Han Ding","https:\u002F\u002Forcid.org\u002F0000-0003-2905-6369",{"name":134,"orcid":135},"Zhigang Wu","https:\u002F\u002Forcid.org\u002F0000-0002-3719-406X",{"tldr":137,"method":138,"finding":139,"direction":140,"opportunity":141},"提出知识增强可穿戴系统K-Wear，将植物传感信号转化为可解释诊断与建议。","软可穿戴传感平台+知识引导推理框架+大语言模型。","模拟诊断准确率99%，真实钾缺乏实验第4天检出早期胁迫并给出干预建议。","智慧农业 \u002F 农业物联网","可探索知识增强LLM推理在更多作物胁迫类型与田间长期监测中的泛化能力。","农业人工智能与决策模型","openalex","2026-09-30T23:30:55.022226Z",{"id":146,"title":147,"url":148,"summary":149,"summary_zh":8,"content":8,"source_name":150,"source_url":8,"published_at":151,"category":152,"cover_url":8,"hotness":13,"is_selected":14,"score":153,"score_detail":154,"sources":160,"tags":162,"primary_topic":166,"secondary_topics":167,"classification":168,"search_phrases":195,"slug":198,"view_count":58,"doi":8,"paper":8,"created_at":199},2815,"WAFI2026人工智能与农业论坛:中国方案助力农民种得好、种得起、种得稳、种得赚","https:\u002F\u002Fbaike.baidu.com\u002Fitem\u002F2026%E4%B8%96%E7%95%8C%E5%86%9C%E4%B8%9A%E7%A7%91%E6%8A%80%E5%88%9B%E6%96%B0%E5%A4%A7%E4%BC%9A\u002F68651190","9月16日WAFI2026举行\"人工智能与农业论坛\",中国农业大学全球食物经济与政策研究院院长樊胜根提出\"人工智能如何造福农民\"议题。论坛介绍神农大模型(2023年1.0版到2025年3.0版,3.0版为\"小麦育种智能助手\",可识别70类、600余种病虫害,已在非洲落地)、农业食物经济与政策AI模型、北大荒\"未来农场\"平台(覆盖111个农场、接入8.4万台智能装备、为60万种植户服务)、北京市\"智京园\"智慧设施管控技术体系等案例。","百度百科 \u002F 中国农业大学","2026-09-16T00:00:00Z","报道",86,{"impact":155,"substance":156,"depth":157,"authority":158,"freshness":40,"relevant":62,"comment":159},26,21,17,14,"国际论坛上集中展示神农大模型、北大荒未来农场等中国AI农业方案，案例数据具体、信源权威，时效性强，值得进入每日精选。",[161],{"name":150,"url":148},[82,21,163,164,23,165],"未来农场","智能育种","病虫害识别",{"code":27,"slug":28,"name":29,"path":30,"parent_code":31},[],{"status":34,"locked":14,"version":35,"method":36,"evidence":169},{"candidates":170,"agricultural_evidence":41},[171,175,181,186,191],{"code":27,"score":61,"supported":41,"title":172,"abstract":173,"tags":174},[],[23],[21,23,165],{"code":176,"score":58,"supported":41,"title":177,"abstract":178,"tags":180},"A2",[],[179],"小麦",[],{"code":182,"score":62,"supported":14,"title":183,"abstract":184,"tags":185},"F2",[],[],[164],{"code":187,"score":62,"supported":14,"title":188,"abstract":189,"tags":190},"F6",[],[],[163],{"code":96,"score":62,"supported":14,"title":192,"abstract":193,"tags":194},[],[],[82],[196,197],"农业人工智能 病虫害识别 智慧农业 智能育种","农业人工智能 病虫害识别","农业人工智能病虫害识别智慧农业智能育种-2815","2026-09-18T00:03:24.639818Z",{"id":201,"title":202,"url":203,"summary":204,"summary_zh":8,"content":8,"source_name":205,"source_url":8,"published_at":206,"category":152,"cover_url":8,"hotness":13,"is_selected":14,"score":207,"score_detail":208,"sources":214,"tags":216,"primary_topic":219,"secondary_topics":220,"classification":221,"search_phrases":244,"slug":247,"view_count":248,"doi":8,"paper":8,"created_at":249},2351,"'AI+'助力农林产业智变:2026服贸会集中展示智慧农业落地应用","https:\u002F\u002Fwww.farmer.com.cn\u002F2026\u002F09\u002F13\u002F991028309.html","2026年中国国际服务贸易交易会上，中粮集团展示玉米质量智能检验应用入选国资委首批央企人工智能战略性高价值场景；广西展示已在马来西亚榴莲主产区规模化落地的榴莲大模型；中国铁塔在北京西山试验林场构建空地一体林草防火监测体系，林上火情监控覆盖率提升至40%以上、重点林下区域达95%。","中国农网 | 2026-09-13","2026-09-13T00:00:00Z",82,{"impact":209,"substance":210,"depth":211,"authority":77,"freshness":212,"relevant":62,"comment":213},24,20,16,9,"服贸会集中展示AI在玉米质检、榴莲大模型、林草防火等场景的落地应用，案例具体、数据明确，具备产业级参考价值。",[215],{"name":205,"url":203},[82,21,217,23,218],"农业遥感","林草防火",{"code":27,"slug":28,"name":29,"path":30,"parent_code":31},[],{"status":34,"locked":14,"version":35,"method":36,"evidence":222},{"candidates":223,"agricultural_evidence":41},[224,228,233,239],{"code":96,"score":212,"supported":41,"title":225,"abstract":226,"tags":227},[82],[],[82],{"code":27,"score":229,"supported":41,"title":230,"abstract":231,"tags":232},5,[],[23],[21,23],{"code":234,"score":58,"supported":41,"title":235,"abstract":236,"tags":238},"A3",[],[237],"玉米",[],{"code":240,"score":62,"supported":14,"title":241,"abstract":242,"tags":243},"I3",[],[],[217],[245,246],"农业人工智能 农业遥感 智慧农业 林草防火","农业人工智能 农业遥感","农业人工智能农业遥感智慧农业林草防火-2351",2,"2026-09-14T00:06:25.997866Z",{"id":251,"title":252,"url":253,"summary":254,"summary_zh":255,"content":8,"source_name":256,"source_url":253,"published_at":257,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":258,"score_detail":259,"sources":263,"tags":265,"primary_topic":266,"secondary_topics":267,"classification":273,"search_phrases":290,"slug":292,"view_count":15,"doi":293,"paper":294,"created_at":308},2042,"An ensemble deep learning approach for soil pH classification leveraging GLCM-based texture features and neural networks","https:\u002F\u002Fdoi.org\u002F10.69598\u002Fsehs.20.26020002","Soil pH-level classification is a critical challenge in precision agriculture owing to data scarcity, high intra-class similarity, and subtle visual variations between pH levels. This research proposed an ensemble-feature deep learning framework that integrates convolutional neural networks with gray-level co-occurrence matrix (GLCM) texture descriptors to address fundamental limitations in pH-level classification. Through comprehensive experiments, we evaluated diverse architectures (i.e., InceptionV3, Inception ResNetV2, ResNet50, and VGG16) enhanced by GLCM features, demonstrating a substantial increase in classification accuracy, particularly under minimal visual distinctions between pH levels. The optimal Inception ResNetV2 w\u002FGLCM configuration achieved the best overall performance, with an F1-score of 82.10%, an accuracy of 82.22%, and a precision of 82.01%, outperforming the conventional machine learning and deep learning approaches evaluated in this study. The proposed method innovatively provides a synergistic integration of hierarchical deep learning features with statistical texture analysis, achieving robust discrimination of visually similar soil sample images capturing different pH levels. These findings advance automated soil analysis and contribute to precision agriculture by establishing a robust solution for image-based soil pH-level classification.","土壤pH值分级是精准农业中的一个关键挑战，其原因在于数据稀缺、类内相似度高以及不同pH值之间细微的视觉差异。本研究提出了一种集成特征深度学习框架，将卷积神经网络与灰度共生矩阵（GLCM）纹理描述符相结合，以解决pH值分级中的根本性局限。通过全面的实验，我们评估了多种经GLCM特征增强的架构（即InceptionV3、Inception ResNetV2、ResNet50和VGG16），结果表明分类准确率显著提升，尤其是在pH值之间视觉差异极小的情况下。最优的Inception ResNetV2结合GLCM配置取得了最佳整体性能，F1分数为82.10%，准确率为82.22%，精确率为82.01%，优于本研究中评估的传统机器学习和深度学习方法。所提出的方法创新性地将层次化深度学习特征与统计纹理分析协同集成，实现了对捕捉不同pH值的视觉相似土壤样本图像的稳健判别。这些发现推进了自动化土壤分析，并通过建立基于图像的土壤pH值分级的稳健解决方案，为精准农业做出了贡献。","Science, Engineering and Health Studies","2026-09-09T00:00:00Z",72,{"impact":260,"substance":210,"depth":157,"authority":261,"freshness":40,"relevant":62,"comment":262},15,12,"该研究提出融合GLCM纹理特征与CNN的集成深度学习框架，在土壤pH分级上取得82%以上准确率，方法新颖且对精准农业有实用价值，但属细分技术进展，影响范围有限。",[264],{"name":256,"url":253},[82,21,100,25],{"code":27,"slug":28,"name":29,"path":30,"parent_code":31},[268],{"code":48,"slug":269,"name":270,"path":271,"parent_code":272},"soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":34,"locked":14,"version":35,"method":36,"evidence":274},{"candidates":275,"agricultural_evidence":41},[276,282,286],{"code":27,"score":76,"supported":41,"title":277,"abstract":279,"tags":281},[278],"deep learning",[44,45,280,278],"machine learning",[21],{"code":48,"score":260,"supported":41,"title":283,"abstract":284,"tags":285},[269],[52,269],[25],{"code":96,"score":40,"supported":41,"title":287,"abstract":288,"tags":289},[],[100,101],[82,100],[291,56],"农业人工智能 土壤检测 智慧农业 精准农业","农业人工智能土壤检测智慧农业精准农业-2042","10.69598\u002Fsehs.20.26020002",{"doi":293,"openalex_id":295,"authors":296,"venue":256,"cited_by_count":15,"oa_url":301,"card":302,"direction":140,"ingested_from":143},"W7212037232",[297,299],{"name":298,"orcid":8},"Sujitranan Mungklachaiya",{"name":300,"orcid":8},"Anongporn Salaiwarakul","https:\u002F\u002Fli01.tci-thaijo.org\u002Findex.php\u002Fsehs\u002Farticle\u002Fdownload\u002F266062\u002F182682",{"tldr":303,"method":304,"finding":305,"direction":306,"opportunity":307},"提出融合GLCM纹理特征与CNN的集成深度学习框架，实现土壤pH等级图像分类。","用InceptionV3、ResNet50等CNN结合GLCM纹理特征，在土壤图","Inception ResNetV2+GLCM最优，F1达82.10%、准确率82.22%，优于常规","农业遥感与作物表型","可探索多源数据融合与轻量化模型，提升小样本下土壤属性分类泛化能力。","2026-09-10T23:30:09.461905Z",{"id":310,"title":311,"url":312,"summary":313,"summary_zh":8,"content":8,"source_name":314,"source_url":8,"published_at":315,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":316,"score_detail":317,"sources":319,"tags":321,"primary_topic":324,"secondary_topics":325,"classification":326,"search_phrases":347,"slug":350,"view_count":58,"doi":8,"paper":351,"created_at":359},1964,"农业大模型在田间地头的落地实践：伏羲大脑\"佳家农\"智慧农服平台案例研究","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7681667449858605587\u002F","佳木斯国家农高区依托中国科学院\"伏羲大脑\"农业大模型打造\"佳家农\"智慧农服平台，农户无需购置任何硬件设备，仅凭卫星遥感数据、手机交互、AI模型即可生成地块定制化的积温预报、选种指导与水肥管理方案。上线两年，\"佳家农\"已服务省内超5.6万农户，覆盖耕地700多万亩，实现每亩节本增收112元。从买农资、叫\"滴滴农机\"、到AI种地指导、溯源卖高价，再到贷款、上保险、学技术、查补贴，一个App全部搞定，相当于给农户配了一位随身的免费\"农艺师\"。","今日头条 中国新闻网 2026-09-04","2026-09-04T13:13:00Z",75,{"impact":210,"substance":74,"depth":76,"authority":13,"freshness":229,"relevant":62,"comment":318},"农业大模型落地案例，数据详实，服务规模大，具有行业示范意义。",[320],{"name":314,"url":312},[82,21,23,322,323],"遥感","农服平台",{"code":27,"slug":28,"name":29,"path":30,"parent_code":31},[],{"status":34,"locked":14,"version":35,"method":36,"evidence":327},{"candidates":328,"agricultural_evidence":41},[329,333,337,343],{"code":27,"score":77,"supported":41,"title":330,"abstract":331,"tags":332},[23],[23],[21,23],{"code":240,"score":49,"supported":41,"title":334,"abstract":335,"tags":336},[],[322],[322],{"code":338,"score":58,"supported":41,"title":339,"abstract":340,"tags":342},"F5",[],[341],"农机",[],{"code":96,"score":62,"supported":14,"title":344,"abstract":345,"tags":346},[],[],[82],[348,349],"农业人工智能 农服平台 智慧农业 大模型","农业人工智能 农服平台","农业人工智能农服平台智慧农业大模型-1964",{"doi":8,"openalex_id":8,"authors":352,"venue":8,"cited_by_count":15,"oa_url":8,"card":353,"direction":140,"ingested_from":358},[],{"tldr":354,"method":355,"finding":356,"direction":140,"opportunity":357},"介绍伏羲大脑农业大模型在佳木斯农高区的落地实践，通过手机和卫星数据提供农事指导，服务超5.6万农户。","基于农业大模型，结合卫星遥感、手机交互和AI算法，构建智慧农服平台。","平台服务5.6万农户，覆盖700多万亩，每亩节本增收112元，实现AI种地指导。","研究农业大模型在低硬件依赖下的服务模式，探索其可复制性及对农户决策行为的影响。","agent","2026-09-09T00:03:57.182443Z",{"id":361,"title":362,"url":363,"summary":364,"summary_zh":8,"content":8,"source_name":365,"source_url":8,"published_at":366,"category":152,"cover_url":8,"hotness":13,"is_selected":14,"score":367,"score_detail":368,"sources":371,"tags":373,"primary_topic":375,"secondary_topics":376,"classification":377,"search_phrases":400,"slug":402,"view_count":49,"doi":8,"paper":8,"created_at":403},1551,"神农大模型 4.0 路演落地湘湖实验室：病虫害识别拓展至 1016 种、准确率超 93%，覆盖全国 31 省超 500 万亩农田","https:\u002F\u002Fwww.xiaoshan.gov.cn\u002Fcol\u002Fcol1302903\u002Fart\u002F2026\u002Fart_51407f23df244519a64db25c4b0ea0b5.html","近日，\"神农大模型\"路演暨场景应用交流会在杭州市萧山区湘湖实验室举办。最新发布的神农大模型 4.0 病虫害识别种类拓展至 1016 种、识别准确率超 93%，可适配大田、设施农业、畜禽养殖等多元场景；同步推出的\"神农·农业世界模型 1.0\"能搭建数字孪生仿真田块，不用下地试种便可模拟预判施肥、温控等对作物长势的影响。这套农业\"超级大脑\"已覆盖全国 31 个省份超 500 万亩农田，惠及百万农户。","杭州市萧山区人民政府","2026-09-03T00:00:00Z",80,{"impact":369,"substance":74,"depth":260,"authority":13,"freshness":40,"relevant":62,"comment":370},25,"神农大模型4.0覆盖全国31省500万亩农田，病虫害识别准确率超93%，具有产业级影响，信息增量大，信源为地方政府官网，时效性佳。",[372],{"name":365,"url":363},[82,21,23,374,165],"数字孪生",{"code":27,"slug":28,"name":29,"path":30,"parent_code":31},[],{"status":34,"locked":14,"version":35,"method":36,"evidence":378},{"candidates":379,"agricultural_evidence":41},[380,384,388,394],{"code":27,"score":369,"supported":41,"title":381,"abstract":382,"tags":383},[23,165],[23,165],[21,23,165],{"code":96,"score":229,"supported":41,"title":385,"abstract":386,"tags":387},[],[374],[374,82],{"code":389,"score":58,"supported":41,"title":390,"abstract":391,"tags":393},"C",[],[392],"畜禽",[],{"code":395,"score":58,"supported":41,"title":396,"abstract":397,"tags":399},"F3",[],[398],"施肥",[],[401,197],"农业人工智能 病虫害识别 数字孪生 智慧农业","农业人工智能病虫害识别数字孪生智慧农业-1551","2026-09-04T00:05:30.291011Z"]