[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2929":3,"related-2929":94},{"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":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":74,"slug":77,"view_count":78,"doi":79,"paper":80,"created_at":93},2929,"A REAL-TİME AI-DRİVEN AGRİCULTURAL ROVER INTEGRATİNG PLANT DİSEASE DETECTİON AND GEO-REFERENCED SOİL MOİSTURE ANALYSİS","https:\u002F\u002Fdoi.org\u002F10.30546\u002Femnaa.2026.02.28.123","This paper presents an autonomous agricultural ground robot for real-time monitoring of plant health and soil moisture in large-scale crop fields.The proposed system integrates a deep learning-based perception subsystem with autonomous navigation and a custom ground control station (GCS) to enable continuous and geo-referenced field analysis.Visual data are acquired using an onboard camera and processed in real time on a Raspberry Pi using an object detection model (ODM) to identify disease-related visual symptoms such as discoloration, deformation and leaf degradation.Each detected instance is associated with a confidence score and accurately geo-tagged using GPS data.In parallel, a contact-based soil moisture sensor performs localized measurements at fixed spatial intervals along a grid-based coverage trajectory.All perception outputs are synchronized with navigation data and transmitted via a telemetry link to the GCS where live video with detection overlays, rover trajectory, mission status and sensor telemetry are visualized and logged for postmission analysis.Field experiments conducted under real operating conditions demonstrate stable autonomous operation and achieve an overall plant disease detection accuracy of 85-90%, confirming the effectiveness of the proposed system for precision agriculture applications.","本文提出了一种用于大规模农田植物健康和土壤湿度实时监测的自主农业地面机器人。该系统将基于深度学习的感知子系统与自主导航及自定义地面控制站（GCS）相结合，实现连续且带地理参考的田间分析。视觉数据通过机载相机采集，并利用目标检测模型（ODM）在树莓派上实时处理，以识别与病害相关的视觉症状，如变色、变形和叶片退化。每个检测到的实例均关联置信度分数，并通过GPS数据精确标注地理位置。与此同时，基于接触式的土壤湿度传感器沿网格化覆盖轨迹以固定空间间隔进行局部测量。所有感知输出与导航数据同步，并通过遥测链路传输至地面控制站，在此可视化并记录带有检测叠加层的实时视频、漫游车轨迹、任务状态和传感器遥测数据，以供任务后分析。在实际运行条件下进行的田间实验证明了稳定的自主运行能力，并实现了85-90%的植物病害整体检测准确率，验证了所提系统在精准农业应用中的有效性。",null,"Scientific Journal","2026-09-18T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,21,17,13,8,1,"集成深度学习病害识别与地理参考土壤墒情监测的自主农业机器人论文，田间实测准确率85-90%，方法新颖且数据可靠，对精准农业有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","农业机器人","植物病害检测","土壤墒情监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":46},[45,53,61,69],{"code":33,"score":13,"supported":46,"title":47,"abstract":48,"tags":52},true,[],[49,50,51],"目标检测","深度学习","deep learning",[28],{"code":54,"score":55,"supported":46,"title":56,"abstract":57,"tags":60},"I1",7,[],[58,59],"精准农业","precision agriculture",[27],{"code":62,"score":63,"supported":46,"title":64,"abstract":65,"tags":68},"H2",6,[],[66,67],"土壤","soil",[],{"code":70,"score":22,"supported":14,"title":71,"abstract":72,"tags":73},"F6",[],[],[29],[75,76],"农业机器人 病害检测 土壤墒情","Raspberry Pi 植物病害识别","农业机器人病害检测土壤墒情-2929",4,"10.30546\u002Femnaa.2026.02.28.123",{"doi":79,"openalex_id":81,"authors":82,"venue":10,"cited_by_count":85,"oa_url":6,"card":86,"direction":90,"ingested_from":92},"W7213559917",[83],{"name":84,"orcid":9},"Gasimov V.A., Dadashov F.H., Hasanov H.B., Huseynov N.E",0,{"tldr":87,"method":88,"finding":89,"direction":90,"opportunity":91},"开发实时AI农业机器人，集成植物病害检测与地理参考土壤湿度分析。","Raspberry Pi上部署目标检测模型，结合GPS和接触式土壤湿度传感器。","田间试验实现85-90%的植物病害检测准确率，并稳定自主运行。","智慧农业 \u002F 农业物联网","可探索多模态传感器融合与边缘计算优化，提升复杂田间环境下的实时检测鲁棒性。","openalex","2026-09-19T23:30:11.232025Z",{"total":63,"page":22,"page_size":63,"items":95},[96,162,225,317,386,442],{"id":97,"title":98,"url":99,"summary":100,"summary_zh":101,"content":9,"source_name":102,"source_url":99,"published_at":103,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":104,"score_detail":105,"sources":109,"tags":111,"primary_topic":112,"secondary_topics":113,"classification":114,"search_phrases":143,"slug":146,"view_count":147,"doi":148,"paper":149,"created_at":161},4912,"Deep Learning Approaches for Plant Disease Detection: A Review of Convolutional Neural Networks and Emerging Techniques","https:\u002F\u002Fdoi.org\u002F10.56201\u002Fijcsmt.vol.11.no12.2025.pg220.231","Plant diseases pose a significant threat to global food security, crop yield, and agricultural sustainability. Traditional disease diagnosis methods, relying on expert visual inspection and laboratory analyses, are often time-consuming, labor-intensive, and costly, limiting their scalability. Recent advances in artificial intelligence, particularly deep learning, offer automated and accurate solutions for plant disease detection. This review synthesizes current research on deep learning–based approaches, focusing on convolutional neural networks (CNNs), hybrid CNN-transformer models, attention mechanisms, and generative data augmentation techniques. CNNs have demonstrated strong capabilities in extracting hierarchical features from leaf images, capturing complex patterns such as lesion shapes, color variations, and textures, thereby outperforming conventional machine learning and rule-based methods. Hybrid architectures and transformer-based models enhance feature extraction, particularly for subtle or visually similar disease symptoms. Data augmentation strategies, including generative adversarial networks (GANs), help address class imbalance and improve model generalization. Despite high reported accuracies, challenges remain, including limited dataset diversity, environmental variability, overfitting, lack of explainable AI, and computational constraints for mobile deployment. Future research should prioritize explainable models, multi-crop and multi-disease detection, lightweight architectures suitable for field applications, and integration with precision agriculture systems. Overall, deep learning–based plant disease detection presents a transformative approach for early diagnosis, timely intervention, and sustainable agricultural practices, offering the potential to reduce crop losses, enhance productivity, and contribute to global food security.","植物病害对全球粮食安全、作物产量和农业可持续性构成重大威胁。传统的病害诊断方法依赖专家视觉检查和实验室分析，往往耗时、费力且成本高昂，限制了其可扩展性。人工智能，特别是深度学习的最新进展，为植物病害检测提供了自动化且准确的解决方案。本文综述了基于深度学习方法的最新研究，重点关注卷积神经网络（CNN）、CNN-Transformer混合模型、注意力机制和生成式数据增强技术。CNN在从叶片图像中提取层次化特征方面展现出强大能力，能够捕捉病变形状、颜色变化和纹理等复杂模式，从而优于传统机器学习和基于规则的方法。混合架构和基于Transformer的模型增强了特征提取能力，尤其针对细微或视觉上相似的病害症状。数据增强策略，包括生成对抗网络（GAN），有助于解决类别不平衡问题并提高模型泛化能力。尽管已有研究报告了较高的准确率，但仍存在诸多挑战，包括数据集多样性有限、环境变异性、过拟合、缺乏可解释的人工智能以及移动端部署的计算约束。未来研究应优先关注可解释模型、多作物和多病害检测、适用于田间应用的轻量级架构以及与精准农业系统的集成。总体而言，基于深度学习的植物病害检测为早期诊断、及时干预和可持续农业实践提供了一种变革性方法，具有减少作物损失、提高生产力并促进全球粮食安全的潜力。","INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN","2026-10-12T00:00:00Z",75,{"impact":17,"substance":106,"depth":19,"authority":107,"freshness":21,"relevant":22,"comment":108},20,12,"系统综述深度学习植物病害检测的方法进展与挑战，学术价值较高但偏理论，对产业落地有参考意义。",[110],{"name":102,"url":99},[27,28,50,58,30],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":115},{"candidates":116,"agricultural_evidence":46},[117,125,129,136],{"code":33,"score":118,"supported":46,"title":119,"abstract":120,"tags":124},19,[51],[50,121,122,51,123],"机器学习","machine learning","artificial intelligence",[28,50],{"code":54,"score":21,"supported":46,"title":126,"abstract":127,"tags":128},[],[58,59],[27,58],{"code":130,"score":63,"supported":46,"title":131,"abstract":132,"tags":135},"A8",[],[133,134],"粮食安全","food security",[],{"code":137,"score":138,"supported":46,"title":139,"abstract":140,"tags":142},"H8",3,[],[141],"可持续农业",[],[144,145],"植物病害检测 深度学习","卷积神经网络 作物病害识别","植物病害检测深度学习-4912",2,"10.56201\u002Fijcsmt.vol.11.no12.2025.pg220.231",{"doi":148,"openalex_id":150,"authors":151,"venue":102,"cited_by_count":85,"oa_url":154,"card":155,"direction":159,"ingested_from":92},"W7221637766",[152],{"name":153,"orcid":9},"NUHU ABDULLAHI","https:\u002F\u002Fiiardjournals.org\u002Fget\u002FIJCSMT\u002FVOL. 11 NO. 12 2025\u002FDeep Learning Approaches for Plant 220-231.pdf",{"tldr":156,"method":157,"finding":158,"direction":159,"opportunity":160},"综述深度学习在植物病害检测中的应用，涵盖CNN、混合Transformer、注意力机制与生成式数据增","综述CNN、CNN-Transformer混合模型、注意力机制及GAN数据增强在","深度学习检测精度高，但仍受数据集多样性、环境变异、可解释性和移动部署算力限制。","农业人工智能与决策模型","可探索轻量化可解释模型、多作物多病害检测及与精准农业系统集成，解决田间部署难题。","2026-10-14T23:30:54.687367Z",{"id":163,"title":164,"url":165,"summary":166,"summary_zh":167,"content":9,"source_name":168,"source_url":165,"published_at":169,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":170,"score_detail":171,"sources":174,"tags":176,"primary_topic":179,"secondary_topics":180,"classification":181,"search_phrases":207,"slug":210,"view_count":211,"doi":212,"paper":213,"created_at":224},4798,"Adaptability of Lightweight AI Models for Embedded Deployment: A Case Study of an Agricultural Monitoring Robot","https:\u002F\u002Fdoi.org\u002F10.54254\u002F2755-2721\u002F2026.ld37676","Many artificial intelligence programs require powerful computing hardware, whereas agricultural robots, drones, and smart cameras rely on small embedded devices with limited computing power, battery capacity, and heat dissipation. Lightweight models reduce parameters and computational costs while maintaining acceptable accuracy, enabling AI deployment on resource-constraint network devices. This paper reviews key lightweighting methods, including compact network architectures, model pruning, model quantization, and knowledge distillation. It compares common platforms such as Jetson, Raspberry Pi, and microcontrollers. Using an agricultural monitoring robot as an example, this study proposes a system combining a camera, a lightweight YOLO model, Jetson, and a microcontroller for real-time crop monitoring. Experiments are designed to evaluate accuracy, speed, power consumption, temperature, and battery life. Rather than pursuing maximum model complexity, this paper focuses on explaining how to select a model that is truly suitable for the actual device. For agricultural robots, effective deployment requires sufficient accuracy, real-time performance, and low energy consumption.","许多人工智能程序需要强大的计算硬件，而农业机器人、无人机和智能摄像头则依赖于计算能力、电池容量和散热能力均有限的小型嵌入式设备。轻量级模型在保持可接受精度的同时减少参数和计算成本，使人工智能能够部署在资源受限的网络设备上。本文综述了关键的轻量化方法，包括紧凑网络架构、模型剪枝、模型量化和知识蒸馏。本文比较了Jetson、树莓派和微控制器等常见平台。以农业监测机器人为例，本研究提出了一种结合摄像头、轻量级YOLO模型、Jetson和微控制器的系统，用于实时作物监测。实验旨在评估精度、速度、功耗、温度和电池寿命。本文并非追求最大化的模型复杂度，而是着重解释如何选择真正适合实际设备的模型。对于农业机器人而言，有效部署需要足够的精度、实时性能和低能耗。","Applied and Computational Engineering","2026-10-13T00:00:00Z",69,{"impact":107,"substance":17,"depth":172,"authority":20,"freshness":13,"relevant":22,"comment":173},16,"系统梳理轻量化模型在农业嵌入式设备上的部署路径，并以监测机器人案例给出可复现方案，对智慧农业工程落地有参考价值。",[175],{"name":168,"url":165},[27,28,29,177,178],"边缘计算","作物监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":182},{"candidates":183,"agricultural_evidence":46},[184,189,193,197,202],{"code":33,"score":55,"supported":46,"title":185,"abstract":186,"tags":188},[],[123,187],"YOLO",[28],{"code":70,"score":78,"supported":46,"title":190,"abstract":191,"tags":192},[],[29],[29],{"code":54,"score":22,"supported":14,"title":194,"abstract":195,"tags":196},[],[],[27],{"code":198,"score":22,"supported":14,"title":199,"abstract":200,"tags":201},"I3",[],[],[178],{"code":203,"score":22,"supported":14,"title":204,"abstract":205,"tags":206},"I5",[],[],[177],[208,209],"农业监测机器人 轻量YOLO Jetson","嵌入式AI 模型轻量化","农业监测机器人轻量YOLOJetson-4798",5,"10.54254\u002F2755-2721\u002F2026.ld37676",{"doi":212,"openalex_id":214,"authors":215,"venue":168,"cited_by_count":85,"oa_url":218,"card":219,"direction":90,"ingested_from":92},"W7221561538",[216],{"name":217,"orcid":9},"Jingen Zhou","https:\u002F\u002Face.ewapub.com\u002Farticle\u002Fview\u002F37676.pdf",{"tldr":220,"method":221,"finding":222,"direction":90,"opportunity":223},"综述轻量化AI方法，并以农业监测机器人为例，提出相机+轻量YOLO+Jetson+单片机的嵌入式部署","综述网络压缩、剪枝、量化、蒸馏，对比Jetson、树莓派、单片机，设计农业机器人","农业机器人部署需兼顾足够精度、实时性与低能耗，而非追求最大模型复杂度。","可研究面向田间多变环境的轻量化模型自适应选择与能效-精度联合优化部署策略。","2026-10-13T23:30:08.379081Z",{"id":226,"title":227,"url":228,"summary":229,"summary_zh":230,"content":9,"source_name":231,"source_url":228,"published_at":232,"category":12,"cover_url":9,"hotness":233,"is_selected":14,"score":234,"score_detail":235,"sources":238,"tags":243,"primary_topic":246,"secondary_topics":247,"classification":258,"search_phrases":301,"slug":304,"view_count":22,"doi":305,"paper":306,"created_at":316},4573,"APPLICATION OF ARTIFICIAL INTELLIGENCE AND AUTOMATION TECHNOLOGIES IN MODERN AGRICULTURAL MACHINERY","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23255982","The rapid development of artificial intelligence (AI), robotics, computer vision, Internet of Things (IoT), satellite navigation, remote sensing, and autonomous control systems is transforming the design and operation of modern agricultural machinery. Agricultural machinery is increasingly evolving from conventional mechanical equipment into intelligent cyber-physical systems capable of sensing field conditions, processing large volumes of data, making operational decisions, and executing agricultural tasks with limited human intervention. This article examines the application of artificial intelligence and automation technologies in tractors, harvesters, sprayers, robotic platforms, unmanned aerial vehicles, and other agricultural machinery. The study is based on a systematic analysis of scientific publications, international institutional reports, and documented agricultural technology adoption data. Particular attention is given to autonomous navigation, machine vision, precision spraying, variable-rate application, crop monitoring, yield prediction, robotic weeding, harvesting, and safety systems. Evidence from the United States demonstrates substantial growth in precision-agriculture adoption: automated guidance systems were used on more than half of the acreage planted to several major crops, while in 2023 guidance autosteering was used by 52 percent of midsize farms and 70 percent of large-scale crop-producing farms. Scientific literature also demonstrates the growing role of machine learning in yield estimation, nitrogen management, disease detection, and robotic perception. However, high acquisition costs, inadequate rural connectivity, data governance issues, cybersecurity, technical complexity, and safety risks remain significant barriers. The study concludes that AI-enabled agricultural machinery can contribute to higher operational efficiency, more precise input application, reduced operator fatigue, improved resource management, and greater agricultural sustainability, provided that technological development is accompanied by appropriate infrastructure, human-capacity development, interoperability standards, and safety regulation.","人工智能（AI）、机器人技术、计算机视觉、物联网（IoT）、卫星导航、遥感及自主控制系统的快速发展，正在深刻改变现代农业机械的设计与运行方式。农业机械正日益从传统机械设备演变为智能信息物理系统，能够感知田间条件、处理海量数据、做出作业决策，并在有限人工干预下执行农业任务。本文探讨了人工智能与自动化技术在拖拉机、联合收割机、喷雾机、机器人平台、无人机及其他农业机械中的应用。研究基于对科学文献、国际机构报告及已记录的农业技术采用数据的系统分析。重点关注自主导航、机器视觉、精准喷雾、变量施用、作物监测、产量预测、机器人除草、收获及安全系统。来自美国的证据表明，精准农业的采用率大幅增长：自动导航系统已应用于多种主要作物一半以上的种植面积，而2023年，52%的中型农场和70%的大型作物生产农场使用了导航自动转向技术。科学文献也表明，机器学习在产量估算、氮素管理、病害检测和机器人感知中的作用日益增强。然而，高昂的购置成本、农村网络连接不足、数据治理问题、网络安全、技术复杂性及安全风险仍是重要障碍。研究结论认为，在技术发展的同时配套适当的基础设施、人力能力建设、互操作性标准和安全监管，人工智能赋能的农业机械能够有助于提高作业效率、实现更精准的投入施用、减轻操作人员疲劳、改善资源管理并增强农业可持续性。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-09T00:00:00Z",25,81,{"impact":236,"substance":106,"depth":17,"authority":20,"freshness":21,"relevant":22,"comment":237},22,"系统梳理AI与自动化在农机领域应用的综述性论文，含美国精准农业采纳率等实证数据，对智慧农业主题聚合有较高参考价值。",[239,240],{"name":231,"url":228},{"name":241,"url":242},"International Bulletin of Engineering and Technology","https:\u002F\u002Finternationalbulletins.com\u002Fintjour\u002Findex.php\u002Fibet\u002Farticle\u002Fview\u002F2468",[27,28,29,244,58,245],"农业物联网","自动驾驶农机",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[248,254],{"code":249,"slug":250,"name":251,"path":252,"parent_code":253},"F5","machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","F",{"code":203,"slug":255,"name":256,"path":257,"parent_code":37},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":40,"locked":14,"version":41,"method":42,"evidence":259},{"candidates":260,"agricultural_evidence":46},[261,267,274,281,287,291,297],{"code":33,"score":17,"supported":46,"title":262,"abstract":263,"tags":266},[123],[121,264,122,123,265],"计算机视觉","computer vision",[28],{"code":249,"score":19,"supported":46,"title":268,"abstract":270,"tags":273},[269],"agricultural machinery",[271,272,269],"农业机械","收割机",[],{"code":203,"score":13,"supported":46,"title":275,"abstract":276,"tags":280},[],[277,278,279],"物联网","internet of things","IoT",[244],{"code":198,"score":63,"supported":46,"title":282,"abstract":283,"tags":286},[],[284,285],"遥感","remote sensing",[],{"code":54,"score":211,"supported":46,"title":288,"abstract":289,"tags":290},[],[58],[27,58],{"code":292,"score":138,"supported":46,"title":293,"abstract":294,"tags":296},"F4",[],[295],"除草",[],{"code":70,"score":22,"supported":14,"title":298,"abstract":299,"tags":300},[],[],[29],[302,303],"农业机械 人工智能 自动化","精准农业 自动驾驶 农机","农业机械人工智能自动化-4573","10.5281\u002Fzenodo.23255982",{"doi":305,"openalex_id":307,"authors":308,"venue":231,"cited_by_count":85,"oa_url":228,"card":311,"direction":90,"ingested_from":92},"W7221138004",[309],{"name":310,"orcid":9},"Rahimjonov Shoxrux Shuhratjon o'g'li",{"tldr":312,"method":313,"finding":314,"direction":90,"opportunity":315},"系统综述AI与自动化技术在现代农机中的应用现状、效益与障碍。","系统分析科学文献、国际机构报告及美国精准农业采用数据。","AI农机可提升效率与可持续性，但成本、连接性、数据治理与安全仍是主要障碍。","可研究低成本AI农机方案、农村连接与数据治理标准，及人机协同安全监管框架。","2026-10-10T23:30:13.826410Z",{"id":318,"title":319,"url":320,"summary":321,"summary_zh":322,"content":9,"source_name":323,"source_url":320,"published_at":324,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":325,"score_detail":326,"sources":328,"tags":330,"primary_topic":332,"secondary_topics":333,"classification":334,"search_phrases":359,"slug":362,"view_count":138,"doi":363,"paper":364,"created_at":385},4177,"The Changing Landscape of Plant Disease Detection: The Role of Artificial Intelligence","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fjsrr\u002F2026\u002Fv32i104569","Plant diseases constrain agricultural productivity and food security, while conventional diagnosis depends heavily on visible symptoms and specialist expertise, limiting rapid and scalable assessment across heterogeneous agricultural environments. Artificial intelligence (AI), particularly machine learning, deep learning, and computer vision, offers complementary approaches for automated and non-invasive disease detection. This review examines AI-based methods for image classification, object detection, image segmentation, severity assessment, and early or pre-symptomatic disease detection. It also considers the integration of AI with hyperspectral, multispectral, and thermal imaging and unmanned aerial vehicles for crop-scale monitoring and precision management. Reported studies demonstrate high performance under many experimental conditions; however, reliable field deployment remains constrained by limited or imbalanced datasets, symptom similarity, environmental variability, domain shift, computational requirements, and insufficient independent validation. The review further considers explainable artificial intelligence, edge-based computing, multimodal sensing, foundation models, vision-language models, and federated learning as emerging directions. These approaches may improve robustness, interpretability, accessibility, and scalability, but their value depends on representative field data, biological validity, rigorous external validation, and integration with plant-pathology expertise across diverse crops, cultivars, locations, seasons, and imaging conditions. AI should therefore be regarded as a complementary decision-support tool whose practical contribution depends on combining computational methods with biological knowledge and real-world agricultural observations.","植物病害制约农业生产力和粮食安全，而传统诊断高度依赖可见症状和专家经验，限制了在异质性农业环境中进行快速、可扩展的评估。人工智能（AI），特别是机器学习、深度学习和计算机视觉，为自动化、非侵入式病害检测提供了互补性方法。本文综述了基于AI的图像分类、目标检测、图像分割、严重度评估以及早期或症状前病害检测方法，并探讨了AI与高光谱、多光谱和热成像及无人机相结合用于作物尺度监测和精准管理的集成应用。已报道的研究在许多实验条件下表现出高性能；然而，可靠的田间部署仍受限于数据集有限或不平衡、症状相似性、环境变异性、域偏移、计算需求以及独立验证不足等问题。本文进一步探讨了可解释人工智能、边缘计算、多模态传感、基础模型、视觉语言模型和联邦学习等新兴方向。这些方法有望提升鲁棒性、可解释性、可及性和可扩展性，但其价值取决于具有代表性的田间数据、生物学有效性、严格的外部验证，以及与植物病理学专业知识在多样化作物、品种、地点、季节和成像条件下的整合。因此，AI应被视为一种互补性决策支持工具，其实际贡献取决于将计算方法与生物学知识和真实农业观测相结合。","Journal of Scientific Research and Reports","2026-10-03T00:00:00Z",78,{"impact":17,"substance":18,"depth":17,"authority":20,"freshness":21,"relevant":22,"comment":327},"系统综述AI植物病害检测的方法、瓶颈与前沿方向，学术价值高但属综述性论文，产业落地影响有限。",[329],{"name":323,"url":320},[27,28,58,331,30],"遥感监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":335},{"candidates":336,"agricultural_evidence":46},[337,341,347,351,355],{"code":33,"score":17,"supported":46,"title":338,"abstract":339,"tags":340},[123],[49,50,121,264,122,51,123,265],[28],{"code":198,"score":55,"supported":46,"title":342,"abstract":343,"tags":346},[],[344,345],"multispectral","hyperspectral",[331],{"code":130,"score":63,"supported":46,"title":348,"abstract":349,"tags":350},[],[133,134],[],{"code":203,"score":138,"supported":46,"title":352,"abstract":353,"tags":354},[],[177],[],{"code":54,"score":147,"supported":14,"title":356,"abstract":357,"tags":358},[],[],[27,58],[360,361],"AI 植物病害检测","无人机 高光谱 作物监测","AI植物病害检测-4177","10.9734\u002Fjsrr\u002F2026\u002Fv32i104569",{"doi":363,"openalex_id":365,"authors":366,"venue":323,"cited_by_count":85,"oa_url":320,"card":380,"direction":159,"ingested_from":92},"W7218426608",[367,369,371,374,376,378],{"name":368,"orcid":9},"Aksa Anna Shajan",{"name":370,"orcid":9},"Sumiya K. V.",{"name":372,"orcid":373},"Sainamole Kurian P.","https:\u002F\u002Forcid.org\u002F0009-0004-1992-3582",{"name":375,"orcid":9},"Pooja Naduvalath",{"name":377,"orcid":9},"Athira Suresh",{"name":379,"orcid":9},"Aswathi P. R.",{"tldr":381,"method":382,"finding":383,"direction":159,"opportunity":384},"综述AI在植物病害检测中的应用，涵盖分类、检测、分割及早期诊断，并指出田间部署的瓶颈与新兴方向。","综述机器学习、深度学习、计算机视觉与高光谱\u002F多光谱\u002F热成像及无人机结合的研究。","AI实验表现优异，但受数据、环境变异和验证不足限制，田间可靠部署仍困难。","可探索多模态基础模型与联邦学习在跨域田间病害检测中的鲁棒性和可解释性验证。","2026-10-04T23:30:40.159648Z",{"id":387,"title":388,"url":389,"summary":390,"summary_zh":9,"content":9,"source_name":391,"source_url":9,"published_at":392,"category":393,"cover_url":9,"hotness":13,"is_selected":14,"score":394,"score_detail":395,"sources":399,"tags":401,"primary_topic":404,"secondary_topics":405,"classification":406,"search_phrases":437,"slug":440,"view_count":55,"doi":9,"paper":9,"created_at":441},4124,"农民日报《对话》栏目「用算法种好地 让AI扛农活」——杜志雄、李想、孔德栋三位专家谈农业AI落地","https:\u002F\u002Fwww.farmer.com.cn\u002F2026\u002F09\u002F30\u002F991030099.html","农民日报全媒体记者李克欣对话中国社科院杜志雄、中国农业大学李想、雄安集团孔德栋三位专家。专家指出当前我国智慧农业正从早期试点示范迈向规模化、体系化推广应用新阶段，人工智能赋能农业的关键技术包括机器学习与深度学习、计算机视觉与智能感知（如200万张高清图像训练的AI作物表型模型识别精度达95%以上）、农业大模型（如中化iMAP节约水肥10%~20%、增产8%~10%）和智能农机与农业机器人（如土壤高通量检测机器人实现42项指标检测误差控制在5%以内）。","中国农网（农民日报）·2026年9月30日","2026-09-30T00:00:00Z","报道",83,{"impact":396,"substance":236,"depth":17,"authority":397,"freshness":211,"relevant":22,"comment":398},24,14,"央媒多方专家对话，含AI作物表型、农业大模型、农业机器人等具体数据与结论，信息增量足，但发布已过一周，时效性略降。",[400],{"name":391,"url":389},[27,28,402,29,403],"农业大模型","智能农机",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":407},{"candidates":408,"agricultural_evidence":46},[409,415,420,424,428,432],{"code":33,"score":410,"supported":46,"title":411,"abstract":412,"tags":414},11,[],[413,50,121,264],"大模型",[28,402],{"code":249,"score":78,"supported":46,"title":416,"abstract":417,"tags":419},[],[418],"农机",[403],{"code":70,"score":78,"supported":46,"title":421,"abstract":422,"tags":423},[],[29],[29],{"code":54,"score":78,"supported":46,"title":425,"abstract":426,"tags":427},[],[27],[27],{"code":62,"score":138,"supported":46,"title":429,"abstract":430,"tags":431},[],[66],[],{"code":198,"score":138,"supported":46,"title":433,"abstract":434,"tags":436},[],[435],"作物表型",[],[438,439],"中化 iMAP 大模型","AI 作物表型 识别精度","中化iMAP大模型-4124","2026-10-04T00:09:05.162758Z",{"id":443,"title":444,"url":445,"summary":446,"summary_zh":447,"content":9,"source_name":448,"source_url":445,"published_at":449,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":450,"sources":452,"tags":454,"primary_topic":456,"secondary_topics":457,"classification":458,"search_phrases":486,"slug":489,"view_count":147,"doi":490,"paper":491,"created_at":505},4063,"An Intelligent LLM–Fuzzy Decision Support and Digital Twin Framework for Adaptive Agricultural Robotics Systems","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriengineering8100423","This study develops an integrated LLM–fuzzy decision-support and digital twin framework for adaptive agricultural robotics, combining semantic reasoning, fuzzy inference, multi-objective optimization, and feedback-driven state updating. Numerical sensor data, operational information, and textual field knowledge are transformed into validated decision rules and model-ready parameters, enabling coordinated decisions across economic, operational, crop-stress, and sustainability-related objectives. The framework is evaluated as a simulation-based proof of concept calibrated with real observations from a semi-smart tomato farm, while controlled digital twin scenarios are used to assess its behavior under environmental and operational disturbances. Compared with numerical optimization alone, the complete LLM–fuzzy framework reduces operational cost by 3.35% and crop stress by 7.98%, while improving operational performance by 4.45%. Ablation, repeated-run, scenario, sensitivity, and dynamic-adaptation analyses further demonstrate consistent computational performance under the evaluated conditions. Sustainability is assessed through a model-based measure integrating water use, energy consumption, and soil-compaction-related impacts. These findings demonstrate the potential of combining semantic reasoning, uncertainty processing, optimization, and digital-twin feedback for adaptive agricultural decision support. However, the results represent a calibrated simulation-based proof of concept rather than validation through a full-scale autonomous field deployment; broader multi-season and field-scale validation is therefore required before generalizing the reported operational and sustainability benefits.","本研究开发了一个面向自适应农业机器人（adaptive agricultural robotics）的集成式LLM-模糊决策支持与数字孪生框架，融合了语义推理、模糊推理、多目标优化和反馈驱动的状态更新。数值传感器数据、运营信息和文本田间知识被转化为经过验证的决策规则和模型就绪参数，从而支持在经济、运营、作物胁迫和可持续性相关目标之间进行协调决策。该框架以基于仿真的概念验证形式进行评估，并利用半智能番茄农场的真实观测数据进行校准，同时使用受控数字孪生场景评估其在环境和运营扰动下的行为表现。与仅使用数值优化相比，完整的LLM-模糊框架将运营成本降低了3.35%，作物胁迫降低了7.98%，同时将运营性能提升了4.45%。消融实验、重复运行、场景、敏感性和动态自适应分析进一步表明，在所评估条件下该框架具有一致的计算性能。可持续性通过一个基于模型的度量进行评估，该度量综合了用水量、能源消耗和土壤压实相关影响。这些发现表明，将语义推理、不确定性处理、优化和数字孪生反馈相结合用于自适应农业决策支持具有潜力。然而，这些结果代表的是一种经过校准的基于仿真的概念验证，而非通过全尺度自主田间部署所进行的验证；因此，在将所报告的运营和可持续性效益加以推广之前，仍需开展更广泛的多季节和田间尺度验证。","AgriEngineering","2026-10-02T00:00:00Z",{"impact":172,"substance":236,"depth":17,"authority":20,"freshness":21,"relevant":22,"comment":451},"方法新颖、结论有量化支撑，但仅为仿真验证的概念验证，尚未田间落地，属细分领域前沿进展。",[453],{"name":448,"url":445},[27,28,29,455,58],"数字孪生",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":459},{"candidates":460,"agricultural_evidence":46},[461,466,471,478,482],{"code":54,"score":19,"supported":46,"title":462,"abstract":464,"tags":465},[463],"digital twin",[455,463],[455,27,58],{"code":33,"score":107,"supported":46,"title":467,"abstract":469,"tags":470},[468],"decision support",[468],[28],{"code":472,"score":63,"supported":46,"title":473,"abstract":474,"tags":477},"B1",[],[475,476],"番茄","tomato",[],{"code":62,"score":63,"supported":46,"title":479,"abstract":480,"tags":481},[],[66,67],[],{"code":70,"score":78,"supported":46,"title":483,"abstract":484,"tags":485},[],[29],[29],[487,488],"LLM 模糊决策 农业机器人","数字孪生 番茄农场","LLM模糊决策农业机器人-4063","10.3390\u002Fagriengineering8100423",{"doi":490,"openalex_id":492,"authors":493,"venue":448,"cited_by_count":85,"oa_url":445,"card":500,"direction":90,"ingested_from":92},"W7216447671",[494,497],{"name":495,"orcid":496},"Hamed Nozari","https:\u002F\u002Forcid.org\u002F0000-0002-6500-6708",{"name":498,"orcid":499},"Zornitsa B. Yordanova","https:\u002F\u002Forcid.org\u002F0000-0002-6056-8445",{"tldr":501,"method":502,"finding":503,"direction":159,"opportunity":504},"提出LLM-模糊决策与数字孪生框架，用于自适应农业机器人协同决策。","LLM语义推理、模糊推理、多目标优化与数字孪生仿真，基于半智能番茄农场数据。","相比纯数值优化，运营成本降3.35%、作物胁迫降7.98%、运营性能升4.45%。","可开展多季节田间规模化验证，并融合实时物联网数据提升数字孪生自适应能力。","2026-10-03T23:30:10.334001Z"]