[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3961":3,"related-3961":76},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":8,"secondary_topics":30,"classification":31,"search_phrases":60,"slug":63,"view_count":64,"doi":8,"paper":65,"created_at":75},3961,"Weifang's AI Shields Crops with Privacy-Preserving Tech——四维混沌加密与Mamba-LSDet协同","https:\u002F\u002Fagritechinsights.com\u002Findex.php\u002F2026\u002F10\u002F01\u002Fweifangs-ai-shields-crops-with-privacy-preserving-tech","潍坊科技学院Hai Yu团队提出面向作物病害识别的隐私保护框架，集成四维混沌加密方案与轻量化Mamba-LSDet检测网络。加密方法利用混沌序列和DNA扩散对农业图像进行安全传输；Mamba-LSDet采用跨阶段门控模块和共享预测头降低参数。在测试中Mamba-LSDet优于轻量级YOLOv11n，mAP@0.5达0.841，mAP@0.50:0.95达0.505。可为带宽、算力受限的中小农场提供可信的实时病害监测方案。",null,"Agritech Insights·2026年10月01日（Frontiers in Plant Science）","2026-10-01T00:00:00Z","论文",10,false,76,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":20,"comment":21},15,21,17,13,1,"轻量检测网络与混沌加密结合的隐私保护病害识别方案，方法新颖、指标明确，对中小农场实时监测有参考价值。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","作物监测","病害识别","隐私保护",[],{"status":32,"locked":13,"version":33,"method":34,"evidence":35},"unclassified","2026-10-22.2","rules",{"candidates":36,"agricultural_evidence":58,"reason":59},[37,43,48,53],{"code":38,"score":39,"supported":13,"title":40,"abstract":41,"tags":42},"I2",2,[],[],[26,28],{"code":44,"score":20,"supported":13,"title":45,"abstract":46,"tags":47},"I1",[],[],[25],{"code":49,"score":20,"supported":13,"title":50,"abstract":51,"tags":52},"I3",[],[],[27],{"code":54,"score":20,"supported":13,"title":55,"abstract":56,"tags":57},"I6",[],[],[29],true,"缺少足够的主题证据",[61,62],"潍坊科技学院 Mamba-LSDet","四维混沌加密 作物病害识别","潍坊科技学院Mamba-LSDet-3961",3,{"doi":8,"openalex_id":8,"authors":66,"venue":8,"cited_by_count":67,"oa_url":8,"card":68,"direction":72,"ingested_from":74},[],0,{"tldr":69,"method":70,"finding":71,"direction":72,"opportunity":73},"提出四维混沌加密与Mamba-LSDet协同的作物病害隐私保护识别框架。","四维混沌序列与DNA扩散加密，结合轻量化Mamba-LSDet检测网络。","Mamba-LSDet优于YOLOv11n，mAP@0.5达0.841，适合资源受限农场。","农业人工智能与决策模型","可探索加密与检测联合优化，在边缘设备上实现隐私保护与实时性的平衡。","agent","2026-10-02T11:53:16.479845Z",{"total":77,"page":20,"page_size":77,"items":78},6,[79,146,221,284,343,416],{"id":80,"title":81,"url":82,"summary":83,"summary_zh":8,"content":8,"source_name":84,"source_url":8,"published_at":85,"category":11,"cover_url":8,"hotness":86,"is_selected":13,"score":87,"score_detail":88,"sources":92,"tags":97,"primary_topic":8,"secondary_topics":99,"classification":100,"search_phrases":115,"slug":118,"view_count":119,"doi":120,"paper":121,"created_at":145},2608,"Agricultural Visual Recognition: A Novel Privacy-Preserving Framework Based on 4D Chaos and Mamba Networks","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1939691\u002Ffull","Yu等发表。提出结合多图像加密和轻量级检测的安全作物病害识别集成框架。为识别任务的数据传输安全构建基于DNA全局扩散和多通道像素扰动的四维混沌系统；进一步开发轻量级Mamba-LSDet网络用于精确加密域病害识别。配备跨阶段门控模块和共享预测头，在资源有限的农业设备上实现准确和稳健的病害检测，在轻量级YOLOv11n上表现优异，mAP@50和mAP@50-95分别为0.841和0.505。","Frontiers in Plant Science 1939691","2026-09-15T01:00:00Z",25,78,{"impact":89,"substance":17,"depth":90,"authority":19,"freshness":12,"relevant":20,"comment":91},16,18,"提出4D混沌加密与轻量级Mamba网络结合的加密域病害识别框架，方法新颖、指标明确，对农业数据安全与边缘部署有参考价值。",[93,94],{"name":84,"url":82},{"name":95,"url":96},"Frontiers in Plant Science","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1939691",[25,26,98,28,29],"作物病害",[],{"status":32,"locked":13,"version":33,"method":34,"evidence":101},{"candidates":102,"agricultural_evidence":58,"reason":59},[103,107,111],{"code":38,"score":39,"supported":13,"title":104,"abstract":105,"tags":106},[],[],[26,28],{"code":44,"score":20,"supported":13,"title":108,"abstract":109,"tags":110},[],[],[25],{"code":54,"score":20,"supported":13,"title":112,"abstract":113,"tags":114},[],[],[29],[116,117],"农业人工智能 作物病害 智慧农业 病害识别","农业人工智能 作物病害","农业人工智能作物病害智慧农业病害识别-2608",4,"10.3389\u002Ffpls.2026.1939691\u002Ffull",{"doi":120,"openalex_id":122,"authors":123,"venue":95,"cited_by_count":67,"oa_url":96,"card":138,"direction":142,"ingested_from":144},"W7214909957",[124,126,128,130,133,135],{"name":125,"orcid":8},"Hai Yu",{"name":127,"orcid":8},"Yutao Xia",{"name":129,"orcid":8},"Yandong Ding",{"name":131,"orcid":132},"Xin Li","https:\u002F\u002Forcid.org\u002F0000-0002-4770-8968",{"name":134,"orcid":8},"Zhenqi Cheng",{"name":136,"orcid":137},"Han Jiao","https:\u002F\u002Forcid.org\u002F0000-0003-0750-9777",{"tldr":139,"method":140,"finding":141,"direction":142,"opportunity":143},"提出结合四维混沌加密与Mamba网络的隐私保护作物病害识别框架。","四维混沌系统、DNA扩散、多通道像素扰动及轻量级Mamba-LSDet网络。","在加密域实现准确病害检测，mAP@50达0.841，mAP@50-95达0.505。","智慧农业 \u002F 农业物联网","加密域视觉识别与轻量网络结合，可探索多模态数据安全共享与边缘部署。","openalex","2026-09-16T00:03:52.238664Z",{"id":147,"title":148,"url":149,"summary":150,"summary_zh":151,"content":8,"source_name":152,"source_url":149,"published_at":153,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":154,"score_detail":155,"sources":161,"tags":163,"primary_topic":166,"secondary_topics":171,"classification":172,"search_phrases":207,"slug":210,"view_count":20,"doi":211,"paper":212,"created_at":220},5311,"AI SMART AGRO SYSTEM: A WEB-BASED AI-ASSISTED DECISION SUPPORT PLATFORM FOR FARMERS","https:\u002F\u002Fdoi.org\u002F10.56726\u002Firjmets103514","Farmers often have to decide on disease control, crop selection, soil management and irrigation without timely expert advice, which leads to yield loss and wastage of water and fertiliser.This paper presents AI Smart Agro System, a web-based decision-support platform that brings five services into one dashboard: leaf disease detection from an uploaded photograph, crop recommendation, soil health analysis, irrigation advisory and weather-based farming advice.The system is built with PHP, MySQL and JavaScript, while disease detection and crop recommendation are handled by an external Python Flask AI service that is called through a secured REST API.Soil, irrigation and weather advice are generated by transparent rule-based logic using soil pH, N-P-K values, soil moisture, rainfall, temperature and humidity.Every result is stored in the user's history, and notifications and an administrator panel support monitoring.The prototype is designed to return the disease name, confidence, treatment and prevention tips for an uploaded leaf image, to recommend the three most suitable crops, and to give clear advice for soil and water management.Quantitative evaluation of the AI models is left for future work.","农民常常需要在没有及时专家建议的情况下决定病害防治、作物选择、土壤管理和灌溉，这会导致产量损失以及水和肥料的浪费。本文提出AI Smart Agro System，这是一个基于Web的决策支持平台，将五项服务整合到一个仪表板中：根据上传照片进行叶片病害检测、作物推荐、土壤健康分析、灌溉建议以及基于天气的农事建议。该系统使用PHP、MySQL和JavaScript构建，而病害检测和作物推荐由外部Python Flask AI服务处理，并通过安全的REST API调用。土壤、灌溉和天气建议由透明的基于规则的逻辑生成，使用土壤pH、N-P-K值、土壤湿度、降雨量、温度和湿度。每个结果都存储在用户历史记录中，通知和管理员面板支持监控。该原型旨在为上传的叶片图像返回病害名称、置信度、治疗和预防提示，推荐三种最合适的作物，并为土壤和水管理提供明确建议。AI模型的定量评估留待未来工作。","International Research Journal of Modernization in Engineering Technology and Science","2026-10-17T00:00:00Z",49,{"impact":156,"substance":157,"depth":158,"authority":77,"freshness":159,"relevant":20,"comment":160},8,14,12,9,"原型系统整合病害识别、作物推荐与灌溉建议，思路清晰但缺乏定量评估，属细分技术进展，公共影响有限。",[162],{"name":152,"url":149},[25,26,164,28,165],"决策支持系统","灌溉管理",{"code":38,"slug":167,"name":168,"path":169,"parent_code":170},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":173,"locked":13,"version":33,"method":34,"evidence":174},"classified",{"candidates":175,"agricultural_evidence":58},[176,182,190,197,203],{"code":38,"score":177,"supported":58,"title":178,"abstract":180,"tags":181},11,[179],"decision support",[],[26,164,28],{"code":183,"score":184,"supported":58,"title":185,"abstract":186,"tags":189},"H3",7,[],[187,188],"灌溉","irrigation",[165],{"code":191,"score":77,"supported":58,"title":192,"abstract":193,"tags":196},"H2",[],[194,195],"土壤","soil",[],{"code":198,"score":64,"supported":58,"title":199,"abstract":200,"tags":202},"F3",[],[201],"肥料",[],{"code":44,"score":20,"supported":13,"title":204,"abstract":205,"tags":206},[],[],[25],[208,209],"Web 农业决策支持平台","农业人工智能 决策支持系统 智慧农业 灌溉管理","Web农业决策支持平台-5311","10.56726\u002Firjmets103514",{"doi":211,"openalex_id":213,"authors":214,"venue":152,"cited_by_count":67,"oa_url":149,"card":215,"direction":142,"ingested_from":144},"W7222785888",[],{"tldr":216,"method":217,"finding":218,"direction":72,"opportunity":219},"构建一个面向农民的网页版AI决策支持平台，集成病害识别、选种、土壤、灌溉与天气建议。","PHP\u002FMySQL\u002FJS前端，Python Flask提供病害与选种AI服务，规","原型可输出病害名称、置信度与防治建议，推荐三种适宜作物并给出水土管理建议。","AI模型尚未定量评估，可补充精度验证与田间实测，并扩展多语言、离线与本地化作物模型。","2026-10-19T23:30:08.043132Z",{"id":222,"title":223,"url":224,"summary":225,"summary_zh":8,"content":8,"source_name":226,"source_url":8,"published_at":227,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":228,"score_detail":229,"sources":232,"tags":234,"primary_topic":237,"secondary_topics":243,"classification":244,"search_phrases":271,"slug":274,"view_count":64,"doi":275,"paper":276,"created_at":283},5301,"MambaSeed:基于Mamba的轻量级混合视觉网络用于番茄叶病识别(PLOS ONE)","https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle?id=10.1371\u002Fjournal.pone.0359350","PLOS ONE于2026-10-15发表论文MambaSeed,由Wang X, Zhang H, Chen Y, Li Y, Qin Y, Lv Z等团队提出基于MambaVisionMixer的轻量级混合视觉网络,配套局部连续分支注入(LCBI)机制;在番茄、玉米、马铃薯数据集上识别准确率分别达98.97%、98.06%和95.87%,模型仅1.13M参数、0.240G MACs,在RTX 4090上延迟3.39ms\u002F图像,为资源受限农田环境提供紧凑、高效、鲁棒的病害识别方案。","PLOS ONE(2026-10-15)","2026-10-15T00:00:00Z",79,{"impact":90,"substance":230,"depth":90,"authority":19,"freshness":156,"relevant":20,"comment":231},22,"方法新颖、指标扎实的轻量级病害识别论文，对资源受限农田场景有实用价值，值得进入每日精选。",[233],{"name":226,"url":224},[25,26,235,28,236],"番茄","轻量级模型",{"code":238,"slug":239,"name":240,"path":241,"parent_code":242},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":173,"locked":13,"version":33,"method":34,"evidence":245},{"candidates":246,"agricultural_evidence":58},[247,251,257,263,267],{"code":238,"score":158,"supported":58,"title":248,"abstract":249,"tags":250},[235],[235],[235],{"code":252,"score":64,"supported":58,"title":253,"abstract":254,"tags":256},"A3",[],[255],"玉米",[],{"code":258,"score":64,"supported":58,"title":259,"abstract":260,"tags":262},"A5",[],[261],"马铃薯",[],{"code":38,"score":39,"supported":13,"title":264,"abstract":265,"tags":266},[],[],[26,28],{"code":44,"score":20,"supported":13,"title":268,"abstract":269,"tags":270},[],[],[25],[272,273],"MambaSeed 番茄叶病","MambaVisionMixer 病害识别","MambaSeed番茄叶病-5301","10.1371\u002Fjournal.pone.0359350",{"doi":275,"openalex_id":8,"authors":277,"venue":8,"cited_by_count":67,"oa_url":8,"card":278,"direction":72,"ingested_from":74},[],{"tldr":279,"method":280,"finding":281,"direction":72,"opportunity":282},"提出轻量级混合视觉网络MambaSeed，实现番茄等作物叶病高效识别。","基于MambaVisionMixer与局部连续分支注入机制，在三种作物病害数据集","番茄、玉米、马铃薯识别准确率达98.97%、98.06%、95.87%，仅1.13M参数、3.39m","可探索该轻量模型在移动端与边缘设备的田间部署，及多作物跨域泛化与病害早期识别。","2026-10-19T00:07:48.589614Z",{"id":285,"title":286,"url":287,"summary":288,"summary_zh":8,"content":8,"source_name":289,"source_url":8,"published_at":227,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":290,"score_detail":291,"sources":294,"tags":296,"primary_topic":298,"secondary_topics":303,"classification":304,"search_phrases":331,"slug":334,"view_count":64,"doi":8,"paper":335,"created_at":342},5064,"Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.20544","Haimanot Bitew Alemayehu、Simachew Melaku Ayalew、Chilotie Desalew Mengesha、Ayisheshim Almaw Bogale、Anteneh Birhan Yenew、Abrham Tegegne Bogale在arXiv 2026-10-15上传的预印本,面向埃塞俄比亚粮食安全作物马铃薯,提出可部署于边缘设备的轻量卷积神经网络,完成健康、早疫病、晚疫病三类分类。模型在PlantVillage(2,215张图像)训练,测试准确率98.66%;在埃塞俄比亚Banja镇田间独立采集的247张图像测试中准确率为90.28%,体现独立田间验证相较受控基准更接近真实部署条件。模型仅含446,787个可训练参数、约1.70MB,训练周期较VGG16和MobileNetV2更短。【预印本未审稿;仅在埃塞俄比亚一地进行田间验证,跨地区泛化能力未测】","arXiv preprint 2026-10-15",71,{"impact":16,"substance":292,"depth":18,"authority":159,"freshness":12,"relevant":20,"comment":293},20,"预印本提出仅1.7MB的轻量CNN实现马铃薯早疫病、晚疫病识别，含独立田间验证，方法扎实但尚未审稿、泛化性待验证，属细分领域技术进展。",[295],{"name":289,"url":287},[25,26,261,297,28],"边缘计算",{"code":258,"slug":299,"name":300,"path":301,"parent_code":302},"tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",[],{"status":173,"locked":13,"version":33,"method":34,"evidence":305},{"candidates":306,"agricultural_evidence":58},[307,312,318,322,326],{"code":258,"score":158,"supported":58,"title":308,"abstract":310,"tags":311},[309],"potato",[261],[261],{"code":313,"score":64,"supported":58,"title":314,"abstract":315,"tags":317},"A8",[],[316],"粮食安全",[],{"code":38,"score":39,"supported":13,"title":319,"abstract":320,"tags":321},[],[],[26,28],{"code":44,"score":20,"supported":13,"title":323,"abstract":324,"tags":325},[],[],[25],{"code":327,"score":20,"supported":13,"title":328,"abstract":329,"tags":330},"I5",[],[],[297],[332,333],"埃塞俄比亚 马铃薯 晚疫病 检测","轻量CNN 马铃薯 叶片病害","埃塞俄比亚马铃薯晚疫病检测-5064",{"doi":8,"openalex_id":8,"authors":336,"venue":8,"cited_by_count":67,"oa_url":8,"card":337,"direction":72,"ingested_from":74},[],{"tldr":338,"method":339,"finding":340,"direction":72,"opportunity":341},"提出轻量CNN实现马铃薯早疫病与晚疫病三分类，并在埃塞俄比亚田间验证。","轻量卷积神经网络，PlantVillage 2215张训练，Banja镇247张","测试集准确率98.66%，独立田间测试降至90.28%，模型仅1.70MB。","可研究跨地区\u002F多作物泛化、田间复杂背景鲁棒性及边缘设备实时部署优化。","2026-10-16T00:14:01.369956Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":348,"content":8,"source_name":95,"source_url":346,"published_at":349,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":350,"score_detail":351,"sources":353,"tags":355,"primary_topic":358,"secondary_topics":363,"classification":365,"search_phrases":383,"slug":386,"view_count":20,"doi":387,"paper":388,"created_at":415},4806,"A study on the identification of wheat powdery mildew using chlorophyll fluorescence imaging","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1837843","Introduction Wheat powdery mildew poses a serious threat to global wheat production, and its accurate identification is key to smart agriculture. Methods This study combines chlorophyll fluorescence imaging with deep learning algorithms to investigate the temporal dynamics of key fluorescence parameters (such as maximum photochemical efficiency, QYmax) during the progression of powderymildew. A QYmax-based chlorophyll fluorescence image dataset for wheat powdery mildew was constructed. Building on this, the LCRNet model was proposed, which effectively processes fluorescence image data through a collaborative mechanism integrating the Large Selective Adaptive Fusion (LSAF) and Coordinated Attention (CA) modules. Results On an independent test set, the model achieved an accuracy of 94% and an F1 score of 94.1%, outperforming comparison models. Discussion This study proposes a method for classifying the severity of powdery mildew in wheat that reduces the computational cost of fluorescence data processing, providing important methodological support and technical insights for advancing the intelligent, precise, and green transformation of crop disease prevention and control systems.","引言 小麦白粉病对全球小麦生产构成严重威胁，其准确识别是实现智慧农业的关键。方法 本研究将叶绿素荧光成像与深度学习算法相结合，探究白粉病发展过程中关键荧光参数（如最大光化学效率QYmax）的时间动态变化，构建了基于QYmax的小麦白粉病叶绿素荧光图像数据集。在此基础上，提出了LCRNet模型，该模型通过融合大选择性自适应融合（LSAF）模块与协调注意力（CA）模块的协同机制，有效处理荧光图像数据。结果 在独立测试集上，该模型达到了94%的准确率和94.1%的F1分数，优于对比模型。讨论 本研究提出了一种小麦白粉病严重程度分类方法，降低了荧光数据处理的计算成本，为推动作物病害防控体系向智能化、精准化和绿色化转型提供了重要的方法学支撑和技术启示。","2026-10-12T00:00:00Z",81,{"impact":90,"substance":230,"depth":90,"authority":157,"freshness":159,"relevant":20,"comment":352},"将叶绿素荧光成像与深度学习结合用于小麦白粉病严重度识别，方法新颖、数据可靠，对智慧植保有实质参考价值。",[354],{"name":95,"url":346},[25,26,28,356,357],"叶绿素荧光","小麦白粉病",{"code":359,"slug":360,"name":361,"path":362,"parent_code":302},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat",[364],{"code":38,"slug":167,"name":168,"path":169,"parent_code":170},{"status":173,"locked":13,"version":33,"method":34,"evidence":366},{"candidates":367,"agricultural_evidence":58},[368,372,378],{"code":359,"score":157,"supported":58,"title":369,"abstract":370,"tags":371},[360],[361,360],[],{"code":38,"score":156,"supported":58,"title":373,"abstract":374,"tags":377},[],[375,376],"深度学习","deep learning",[26,28],{"code":44,"score":184,"supported":58,"title":379,"abstract":380,"tags":382},[],[25,381],"smart agriculture",[25],[384,385],"小麦白粉病 叶绿素荧光 深度学习","LCRNet 小麦病害识别","小麦白粉病叶绿素荧光深度学习-4806","10.3389\u002Ffpls.2026.1837843",{"doi":387,"openalex_id":389,"authors":390,"venue":95,"cited_by_count":67,"oa_url":409,"card":410,"direction":142,"ingested_from":144},"W7221549180",[391,393,396,399,401,403,405,407],{"name":392,"orcid":8},"Yijia Chen",{"name":394,"orcid":395},"Chengyuan Hao","https:\u002F\u002Forcid.org\u002F0000-0002-6002-3963",{"name":397,"orcid":398},"Zhiyu Li","https:\u002F\u002Forcid.org\u002F0000-0003-3771-0199",{"name":400,"orcid":8},"Xupeng An",{"name":402,"orcid":8},"Jingxiang Huang",{"name":404,"orcid":8},"Xinchang Chen",{"name":406,"orcid":8},"Shidong Wang",{"name":408,"orcid":8},"ZhiChao Chen","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1837843\u002Fpdf",{"tldr":411,"method":412,"finding":413,"direction":72,"opportunity":414},"该研究利用叶绿素荧光成像与深度学习识别小麦白粉病并分级。","构建QYmax荧光图像数据集，提出融合LSAF与CA模块的LCRNet模型。","模型在独立测试集上准确率达94%、F1为94.1%，优于对比模型。","可探索多病害、多作物荧光图像通用模型，并融合田间时序数据实现早期预警。","2026-10-13T23:30:09.060156Z",{"id":417,"title":418,"url":419,"summary":420,"summary_zh":421,"content":8,"source_name":422,"source_url":419,"published_at":349,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":423,"score_detail":424,"sources":426,"tags":428,"primary_topic":431,"secondary_topics":432,"classification":433,"search_phrases":451,"slug":454,"view_count":20,"doi":455,"paper":456,"created_at":474},4804,"Comparative Deep Learning and RISE-Based Explainable AI Framework for Orange Fruit Disease Detection","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1850038","Orange diseases significantly threaten fruit quality and agricultural productivity, resulting in substantial economic losses. Traditional diagnostic methods are limited by their labor-intensive nature, high costs, and reliance on subjective expert evaluation, increasing the demand for automated solutions. This study systematically compared three state-of the-art deep learning architectures-EfficientNet-B0, ConvNeXt-Tiny, and Vision Transformer (ViT-B\u002F16)-on the Orange Fruit dataset, which comprises healthy, citrus canker, and melanose samples. To enhance generalization and mitigate overfitting, transfer learning with ImageNet pretraining was combined with advanced data augmentation strategies like Mixup and Cutout. Experimental results demonstrated that the ConvNeXt-Tiny architecture, supported by these techniques, achieved superior performance, reaching 98.76% Accuracy, 99% F1-Score, and 99.95% ROC-AUC. Beyond numerical metrics, model transparency was investigated using Explainable Artificial Intelligence (XAI). The study evaluated the widely used Gradient-weighted Class Activation Mapping (Grad-CAM) method alongside Randomized Input Sampling for Explanation (RISE), which, to the best of our knowledge, represents one of the first applications of RISE in plant disease image analysis. RISE provided more comprehensive visualizations of the fruit surface regions influencing decisions, thereby strengthening interpretability. These findings confirm the high potential of modern deep learning for early disease diagnosis and highlight that XAI integration significantly enhances the reliability of agricultural decision support systems. Five fold cross-validation experiments and paired t-test analysis further confirmed the robustness and statistical significance of these findings.","橙病严重威胁果实品质和农业生产力，造成重大经济损失。传统诊断方法受限于劳动强度大、成本高以及依赖专家主观评估，增加了对自动化解决方案的需求。本研究在包含健康、柑橘溃疡病和黑斑病样本的橙果数据集上，系统比较了三种先进的深度学习架构——EfficientNet-B0、ConvNeXt-Tiny和Vision Transformer（ViT-B\u002F16）。为增强泛化能力并缓解过拟合，将基于ImageNet预训练的迁移学习与Mixup和Cutout等先进数据增强策略相结合。实验结果表明，在这些技术的支持下，ConvNeXt-Tiny架构取得了最优性能，达到98.76%的准确率、99%的F1分数和99.95%的ROC-AUC。除数值指标外，本研究还利用可解释人工智能（XAI）探讨了模型透明度。研究评估了广泛使用的梯度加权类激活映射（Grad-CAM）方法以及随机输入采样解释方法（RISE），据我们所知，这是RISE在植物病害图像分析中的首批应用之一。RISE提供了更全面的果实表面区域可视化，展示了影响决策的区域，从而增强了可解释性。这些发现证实了现代深度学习在早期病害诊断中的巨大潜力，并表明XAI的整合显著提升了农业决策支持系统的可靠性。五折交叉验证实验和配对t检验分析进一步证实了这些发现的稳健性和统计显著性。","Tarım Bilimleri Dergisi",72,{"impact":158,"substance":292,"depth":90,"authority":19,"freshness":159,"relevant":20,"comment":425},"系统比较三种深度学习架构并首次将RISE用于植物病害图像分析，方法新颖、数据可靠，对智慧农业病害诊断有参考价值。",[427],{"name":422,"url":419},[25,26,429,430,28],"可解释AI","柑橘",{"code":38,"slug":167,"name":168,"path":169,"parent_code":170},[],{"status":173,"locked":13,"version":33,"method":34,"evidence":434},{"candidates":435,"agricultural_evidence":58},[436,441,447],{"code":38,"score":292,"supported":58,"title":437,"abstract":438,"tags":440},[376],[375,376,439,179],"artificial intelligence",[26,429,28],{"code":442,"score":184,"supported":58,"title":443,"abstract":444,"tags":446},"B2",[],[430,445],"citrus",[430],{"code":44,"score":20,"supported":13,"title":448,"abstract":449,"tags":450},[],[],[25],[452,453],"ConvNeXt 柑橘病害检测","RISE 可解释AI 植物病害","ConvNeXt柑橘病害检测-4804","10.15832\u002Fankutbd.1850038",{"doi":455,"openalex_id":457,"authors":458,"venue":422,"cited_by_count":67,"oa_url":468,"card":469,"direction":142,"ingested_from":144},"W7221532433",[459,462,465],{"name":460,"orcid":461},"Kürşad Buğrahan Yapar","https:\u002F\u002Forcid.org\u002F0009-0006-7666-6177",{"name":463,"orcid":464},"Nurettin Doğan","https:\u002F\u002Forcid.org\u002F0000-0002-8267-8469",{"name":466,"orcid":467},"Özgür Öksüz","https:\u002F\u002Forcid.org\u002F0000-0001-5568-6116","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5543457",{"tldr":470,"method":471,"finding":472,"direction":72,"opportunity":473},"比较三种深度学习模型检测橙子病害，并用RISE提升可解释性。","EfficientNet-B0、ConvNeXt-Tiny、ViT-B\u002F16，迁","ConvNeXt-Tiny达98.76%准确率，RISE比Grad-CAM提供更全面可解释可视化。","RISE在植物病害分析中应用尚少，可探索更多XAI方法提升农业决策系统可信度。","2026-10-13T23:30:08.943247Z"]