[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2608":3,"related-2608":91},{"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":23,"tags":28,"primary_topic":8,"secondary_topics":34,"classification":35,"search_phrases":59,"slug":62,"view_count":63,"doi":64,"paper":65,"created_at":90},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。",null,"Frontiers in Plant Science 1939691","2026-09-15T01:00:00Z","论文",25,false,78,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},16,21,18,13,10,1,"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。",[24,25],{"name":9,"url":6},{"name":26,"url":27},"Frontiers in Plant Science","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1939691",[29,30,31,32,33],"智慧农业","农业人工智能","作物病害","病害识别","隐私保护",[],{"status":36,"locked":13,"version":37,"method":38,"evidence":39},"unclassified","2026-10-22.2","rules",{"candidates":40,"agricultural_evidence":57,"reason":58},[41,47,52],{"code":42,"score":43,"supported":13,"title":44,"abstract":45,"tags":46},"I2",2,[],[],[30,32],{"code":48,"score":21,"supported":13,"title":49,"abstract":50,"tags":51},"I1",[],[],[29],{"code":53,"score":21,"supported":13,"title":54,"abstract":55,"tags":56},"I6",[],[],[33],true,"缺少足够的主题证据",[60,61],"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":64,"openalex_id":66,"authors":67,"venue":26,"cited_by_count":82,"oa_url":27,"card":83,"direction":87,"ingested_from":89},"W7214909957",[68,70,72,74,77,79],{"name":69,"orcid":8},"Hai Yu",{"name":71,"orcid":8},"Yutao Xia",{"name":73,"orcid":8},"Yandong Ding",{"name":75,"orcid":76},"Xin Li","https:\u002F\u002Forcid.org\u002F0000-0002-4770-8968",{"name":78,"orcid":8},"Zhenqi Cheng",{"name":80,"orcid":81},"Han Jiao","https:\u002F\u002Forcid.org\u002F0000-0003-0750-9777",0,{"tldr":84,"method":85,"finding":86,"direction":87,"opportunity":88},"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",{"total":92,"page":21,"page_size":92,"items":93},6,[94,146,210,279,341,411],{"id":95,"title":96,"url":97,"summary":98,"summary_zh":8,"content":8,"source_name":99,"source_url":8,"published_at":100,"category":11,"cover_url":8,"hotness":20,"is_selected":13,"score":101,"score_detail":102,"sources":106,"tags":108,"primary_topic":8,"secondary_topics":110,"classification":111,"search_phrases":131,"slug":134,"view_count":135,"doi":8,"paper":136,"created_at":145},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。","Agritech Insights·2026年10月01日（Frontiers in Plant Science）","2026-10-01T00:00:00Z",76,{"impact":103,"substance":17,"depth":104,"authority":19,"freshness":20,"relevant":21,"comment":105},15,17,"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。",[107],{"name":99,"url":97},[29,30,109,32,33],"作物监测",[],{"status":36,"locked":13,"version":37,"method":38,"evidence":112},{"candidates":113,"agricultural_evidence":57,"reason":58},[114,118,122,127],{"code":42,"score":43,"supported":13,"title":115,"abstract":116,"tags":117},[],[],[30,32],{"code":48,"score":21,"supported":13,"title":119,"abstract":120,"tags":121},[],[],[29],{"code":123,"score":21,"supported":13,"title":124,"abstract":125,"tags":126},"I3",[],[],[109],{"code":53,"score":21,"supported":13,"title":128,"abstract":129,"tags":130},[],[],[33],[132,133],"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":137,"venue":8,"cited_by_count":82,"oa_url":8,"card":138,"direction":142,"ingested_from":144},[],{"tldr":139,"method":140,"finding":141,"direction":142,"opportunity":143},"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",{"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":20,"is_selected":13,"score":154,"score_detail":155,"sources":159,"tags":161,"primary_topic":164,"secondary_topics":169,"classification":170,"search_phrases":190,"slug":193,"view_count":82,"doi":194,"paper":195,"created_at":209},5584,"Distributionally-Robust Evaluation of Computer Vision Agriculture Disease Classifiers Under Climate-Driven Pathogen Range Shifts: An Artificial Intelligence Worst-Case Generalization Bound","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544150","Computer vision classifiers for crop disease are evaluated almost exclusively on held-out samples drawn from the same distribution as their training data, yet climate-driven pathogen range shifts mean that deployment environments are systematically out of distribution. The framework treats the deployment distribution as an adversarial perturbation of the training distribution within a Wasserstein ball whose radius is calibrated to observed climate displacement. Using NASA POWER monthly reanalysis for Harare, Zimbabwe (2000-2023, 312 monthly observations), the analysis estimates a mean air temperature of 18.914 C, a standard deviation of 3.107 C, and a warming trend of 0.2001 C per decade. These estimates anchor the radius of the ambiguity set and the resulting bound. The bound decomposes worst-case risk into an empirical risk term, a Wasserstein radius term scaled by the Lipschitz constant of the classifier, and a concentration term. Under plausible Lipschitz constants for convolutional backbones, the radius term dominates the empirical risk term once the climate displacement exceeds a threshold that the Harare record already approaches. The contribution is a formal evaluation criterion that replaces the i. i. d. assumption with a climate-calibrated ambiguity set, together with the analytical machinery needed to compute it.","作物病害的计算机视觉分类器几乎完全在与训练数据同分布的留出样本上进行评估，然而气候驱动的病原体分布范围变化意味着部署环境系统性地处于分布之外。该框架将部署分布视为训练分布在Wasserstein球内的对抗性扰动，球的半径根据观测到的气候位移进行校准。利用NASA POWER对津巴布韦哈拉雷的月度再分析数据（2000—2023年，312个月度观测值），分析估计平均气温为18.914°C，标准差为3.107°C，每十年升温趋势为0.2001°C。这些估计值锚定了模糊集的半径及由此得到的界。该界将最坏情况风险分解为经验风险项、由分类器Lipschitz常数缩放后的Wasserstein半径项以及集中项。在卷积骨干网络合理的Lipschitz常数下，一旦气候位移超过哈拉雷记录已接近的阈值，半径项便主导经验风险项。本文的贡献在于提出了一种形式化评估准则，以气候校准的模糊集替代独立同分布（i.i.d.）假设，并提供了计算该准则所需的分析工具。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",75,{"impact":156,"substance":157,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":158},12,22,"方法新颖、数据具体，但属方法论预印论文，产业影响有限，适合作为专业精选而非头条。",[160],{"name":152,"url":149},[29,30,162,31,163],"计算机视觉","气候变化",{"code":42,"slug":165,"name":166,"path":167,"parent_code":168},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":171,"locked":13,"version":37,"method":38,"evidence":172},"classified",{"candidates":173,"agricultural_evidence":57},[174,181,186],{"code":42,"score":175,"supported":57,"title":176,"abstract":179,"tags":180},24,[177,178],"artificial intelligence","computer vision",[162,178],[30,162],{"code":182,"score":21,"supported":13,"title":183,"abstract":184,"tags":185},"H7",[],[],[163],{"code":48,"score":21,"supported":13,"title":187,"abstract":188,"tags":189},[],[],[29],[191,192],"NASA POWER 哈拉雷 气温","Wasserstein 分布鲁棒 病害分类","NASAPOWER哈拉雷气温-5584","10.5281\u002Fzenodo.23544150",{"doi":194,"openalex_id":196,"authors":197,"venue":152,"cited_by_count":82,"oa_url":149,"card":204,"direction":142,"ingested_from":89},"W7223087892",[198,200,202],{"name":199,"orcid":8},"Kossi Afeli",{"name":201,"orcid":8},"Akouvi Amegashie",{"name":203,"orcid":8},"Komlan Sélom Dossou",{"tldr":205,"method":206,"finding":207,"direction":142,"opportunity":208},"提出气候校准的分布鲁棒评估准则，替代i.i.d.假设评价作物病害视觉分类器。","用Wasserstein球建模部署分布偏移，以NASA POWER哈拉雷气温数据","气候位移超阈值后，半径项主导经验风险，现有评估会高估模型泛化能力。","可将气候校准的鲁棒评估扩展到多作物多区域，并研究适应分布偏移的鲁棒训练方法。","2026-10-22T11:21:00.036937Z",{"id":211,"title":212,"url":213,"summary":214,"summary_zh":215,"content":8,"source_name":216,"source_url":213,"published_at":217,"category":11,"cover_url":8,"hotness":20,"is_selected":13,"score":218,"score_detail":219,"sources":224,"tags":226,"primary_topic":229,"secondary_topics":230,"classification":231,"search_phrases":265,"slug":268,"view_count":82,"doi":269,"paper":270,"created_at":278},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":220,"substance":221,"depth":156,"authority":92,"freshness":222,"relevant":21,"comment":223},8,14,9,"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。",[225],{"name":216,"url":213},[29,30,227,32,228],"决策支持系统","灌溉管理",{"code":42,"slug":165,"name":166,"path":167,"parent_code":168},[],{"status":171,"locked":13,"version":37,"method":38,"evidence":232},{"candidates":233,"agricultural_evidence":57},[234,240,248,255,261],{"code":42,"score":235,"supported":57,"title":236,"abstract":238,"tags":239},11,[237],"decision support",[],[30,227,32],{"code":241,"score":242,"supported":57,"title":243,"abstract":244,"tags":247},"H3",7,[],[245,246],"灌溉","irrigation",[228],{"code":249,"score":92,"supported":57,"title":250,"abstract":251,"tags":254},"H2",[],[252,253],"土壤","soil",[],{"code":256,"score":135,"supported":57,"title":257,"abstract":258,"tags":260},"F3",[],[259],"肥料",[],{"code":48,"score":21,"supported":13,"title":262,"abstract":263,"tags":264},[],[],[29],[266,267],"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":269,"openalex_id":271,"authors":272,"venue":216,"cited_by_count":82,"oa_url":213,"card":273,"direction":87,"ingested_from":89},"W7222785888",[],{"tldr":274,"method":275,"finding":276,"direction":142,"opportunity":277},"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":280,"title":281,"url":282,"summary":283,"summary_zh":8,"content":8,"source_name":284,"source_url":8,"published_at":285,"category":11,"cover_url":8,"hotness":20,"is_selected":13,"score":286,"score_detail":287,"sources":289,"tags":291,"primary_topic":294,"secondary_topics":300,"classification":301,"search_phrases":328,"slug":331,"view_count":43,"doi":332,"paper":333,"created_at":340},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":18,"substance":157,"depth":18,"authority":19,"freshness":220,"relevant":21,"comment":288},"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。",[290],{"name":284,"url":282},[29,30,292,32,293],"番茄","轻量级模型",{"code":295,"slug":296,"name":297,"path":298,"parent_code":299},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":171,"locked":13,"version":37,"method":38,"evidence":302},{"candidates":303,"agricultural_evidence":57},[304,308,314,320,324],{"code":295,"score":156,"supported":57,"title":305,"abstract":306,"tags":307},[292],[292],[292],{"code":309,"score":135,"supported":57,"title":310,"abstract":311,"tags":313},"A3",[],[312],"玉米",[],{"code":315,"score":135,"supported":57,"title":316,"abstract":317,"tags":319},"A5",[],[318],"马铃薯",[],{"code":42,"score":43,"supported":13,"title":321,"abstract":322,"tags":323},[],[],[30,32],{"code":48,"score":21,"supported":13,"title":325,"abstract":326,"tags":327},[],[],[29],[329,330],"MambaSeed 番茄叶病","MambaVisionMixer 病害识别","MambaSeed番茄叶病-5301","10.1371\u002Fjournal.pone.0359350",{"doi":332,"openalex_id":8,"authors":334,"venue":8,"cited_by_count":82,"oa_url":8,"card":335,"direction":142,"ingested_from":144},[],{"tldr":336,"method":337,"finding":338,"direction":142,"opportunity":339},"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":342,"title":343,"url":344,"summary":345,"summary_zh":346,"content":8,"source_name":26,"source_url":344,"published_at":347,"category":11,"cover_url":8,"hotness":20,"is_selected":13,"score":101,"score_detail":348,"sources":350,"tags":352,"primary_topic":355,"secondary_topics":356,"classification":357,"search_phrases":373,"slug":376,"view_count":21,"doi":377,"paper":378,"created_at":410},5147,"FDUNet-LRSA: efficient frequency-adaptive segmentation for automated crop disease inspection","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1963106","The transition toward industrialized and automated agriculture requires reliable machine vision for high-throughput crop health monitoring and field decision support. Automated sweetpotato disease inspection, however, remains challenging because field images exhibit substantial variations in leaf scale, appearance, illumination, occlusion, and background complexity. Conventional U-shaped networks rely primarily on fixed convolutional kernels and local feature aggregation, whereas Transformer-based alternatives often introduce considerable computational overhead. This article proposes FDUNet-LRSA, a frequency-adaptive segmentation network that integrates frequency-domain dynamic convolution, low-resolution self-attention, and boundary-aware refinement. Frequency-domain dynamic convolution reconstructs input-dependent spatial kernels to improve feature adaptation under changing imaging conditions. Low-resolution self-attention captures long-range contextual dependencies in a fixed compact feature space, while boundary-aware refinement preserves irregular leaf contours during mask reconstruction. Under the reported evaluation protocol, FDUNet-LRSA achieved a mean test foreground IoU of 0.94 and a Dice coefficient of 0.97, with 3.72 GFLOPs. Additional experiments indicate that task-oriented moderate augmentation improves generalization compared with stronger augmentation. The proposed network provides an efficient visual perception approach for automated crop inspection systems.","向工业化与自动化农业转型，需要可靠的机器视觉技术，以支持高通量作物健康监测与田间决策。然而，甘薯病害自动检测仍具挑战性，因为田间图像在叶片尺度、外观、光照、遮挡和背景复杂度方面存在显著变化。传统U形网络主要依赖固定卷积核和局部特征聚合，而基于Transformer的替代方案往往带来较大的计算开销。本文提出FDUNet-LRSA，一种频率自适应分割网络，融合了频域动态卷积、低分辨率自注意力与边界感知细化。频域动态卷积重建依赖输入的空间卷积核，以提升成像条件变化下的特征适应性。低分辨率自注意力在固定的紧凑特征空间中捕获长程上下文依赖，而边界感知细化在掩码重建过程中保留不规则叶片轮廓。在所报告的评估协议下，FDUNet-LRSA取得了0.94的平均测试前景IoU和0.97的Dice系数，计算量为3.72 GFLOPs。额外实验表明，与更强的增强相比，面向任务的中等增强可提升泛化能力。所提出的网络为自动化作物检测系统提供了一种高效的视觉感知方法。","2026-10-16T00:00:00Z",{"impact":16,"substance":17,"depth":104,"authority":19,"freshness":222,"relevant":21,"comment":349},"提出频域自适应分割网络，在甘薯病害检测上取得高精度且计算量低，方法有新意、结论可靠，属细分领域实质进展，值得进入每日精选。",[351],{"name":26,"url":344},[29,30,31,353,354],"甘薯","图像分割",{"code":42,"slug":165,"name":166,"path":167,"parent_code":168},[],{"status":171,"locked":13,"version":37,"method":38,"evidence":358},{"candidates":359,"agricultural_evidence":57},[360,365,369],{"code":42,"score":361,"supported":57,"title":362,"abstract":363,"tags":364},5,[],[237],[30,354],{"code":315,"score":63,"supported":57,"title":366,"abstract":367,"tags":368},[],[353],[353],{"code":48,"score":21,"supported":13,"title":370,"abstract":371,"tags":372},[],[],[29],[374,375],"FDUNet-LRSA 甘薯病害","甘薯病害 图像分割","FDUNet-LRSA甘薯病害-5147","10.3389\u002Ffpls.2026.1963106",{"doi":377,"openalex_id":379,"authors":380,"venue":26,"cited_by_count":82,"oa_url":403,"card":404,"direction":87,"ingested_from":89},"W7222502318",[381,384,387,390,392,395,397,399,401],{"name":382,"orcid":383},"Ru Han","https:\u002F\u002Forcid.org\u002F0009-0000-5128-1314",{"name":385,"orcid":386},"Lei Shu","https:\u002F\u002Forcid.org\u002F0000-0002-6700-9347",{"name":388,"orcid":389},"Grzegorz Cielniak","https:\u002F\u002Forcid.org\u002F0000-0002-6299-8465",{"name":391,"orcid":8},"Yan Zhu",{"name":393,"orcid":394},"Jucheng Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5046-2663",{"name":396,"orcid":8},"Fan Yang",{"name":398,"orcid":8},"Weihan Song",{"name":400,"orcid":8},"Qian Zhang",{"name":402,"orcid":8},"Kai Huang","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1963106\u002Fpdf",{"tldr":405,"method":406,"finding":407,"direction":408,"opportunity":409},"提出频域自适应分割网络FDUNet-LRSA，用于甘薯病害自动巡检。","频域动态卷积、低分辨率自注意力与边界感知细化，结合适度数据增强。","测试前景IoU达0.94、Dice达0.97，仅3.72 GFLOPs，轻量高效。","农业遥感与作物表型","可探索频域动态卷积在多种作物病害与复杂田间光照下的跨域泛化与边缘部署。","2026-10-17T23:30:08.487857Z",{"id":412,"title":413,"url":414,"summary":415,"summary_zh":8,"content":8,"source_name":416,"source_url":8,"published_at":285,"category":11,"cover_url":8,"hotness":20,"is_selected":13,"score":417,"score_detail":418,"sources":421,"tags":423,"primary_topic":425,"secondary_topics":430,"classification":431,"search_phrases":458,"slug":461,"view_count":135,"doi":8,"paper":462,"created_at":469},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":103,"substance":419,"depth":104,"authority":222,"freshness":20,"relevant":21,"comment":420},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。",[422],{"name":416,"url":414},[29,30,318,424,32],"边缘计算",{"code":315,"slug":426,"name":427,"path":428,"parent_code":429},"tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",[],{"status":171,"locked":13,"version":37,"method":38,"evidence":432},{"candidates":433,"agricultural_evidence":57},[434,439,445,449,453],{"code":315,"score":156,"supported":57,"title":435,"abstract":437,"tags":438},[436],"potato",[318],[318],{"code":440,"score":135,"supported":57,"title":441,"abstract":442,"tags":444},"A8",[],[443],"粮食安全",[],{"code":42,"score":43,"supported":13,"title":446,"abstract":447,"tags":448},[],[],[30,32],{"code":48,"score":21,"supported":13,"title":450,"abstract":451,"tags":452},[],[],[29],{"code":454,"score":21,"supported":13,"title":455,"abstract":456,"tags":457},"I5",[],[],[424],[459,460],"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":463,"venue":8,"cited_by_count":82,"oa_url":8,"card":464,"direction":142,"ingested_from":144},[],{"tldr":465,"method":466,"finding":467,"direction":142,"opportunity":468},"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"]