[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1506":3,"related-1506":73},{"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":29,"secondary_topics":35,"classification":36,"search_phrases":58,"slug":61,"view_count":20,"doi":8,"paper":62,"created_at":72},1506,"MOIR-Net: A Lightweight Crop Disease and Pest Recognition Network Based on Multi-Scale Reparameterization and Energy Attention","https:\u002F\u002Fwww.sciltp.com\u002Fjournals\u002Faiet\u002Farticles\u002F2608004943","针对边缘设备资源约束下复杂田间场景对作物病虫害识别的挑战，研究提出 MOIR-Net——多尺度 Omnikernel 倒残差（MOIR）与无参数 SimAM 注意力机制结合的轻量框架。MOIR 模块采用结构重参数化策略，将多分支训练拓扑在推理时转换为单路径架构，从而以零推理时内存开销实现无损特征聚合。在 IP102、PlantVillage 和 PlantDoc 数据集上的广泛评估表明，MOIR-Net 实现精度与效率平衡且计算成本极小（仅 0.967M 参数、2.30 ms 延迟）；在 IP102 基准上达到 Top-1 64.18% 准确率、mAP 58.32%。",null,"AIET (Scilight Press)","2026-08-28T00:00:00Z","论文",10,false,69,{"impact":16,"substance":17,"depth":18,"authority":12,"freshness":19,"relevant":20,"comment":21},15,20,18,6,1,"轻量级病虫害识别网络在精度与效率间取得良好平衡，对边缘设备部署有参考价值。",[23],{"name":9,"url":6},[25,26,27,28],"智慧农业","农业人工智能","边缘计算","病虫害识别",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":37,"locked":13,"version":38,"method":39,"evidence":40},"classified","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":44},[42,48,53],{"code":30,"score":43,"supported":44,"title":45,"abstract":46,"tags":47},5,true,[],[28],[26,28],{"code":49,"score":20,"supported":13,"title":50,"abstract":51,"tags":52},"I1",[],[],[25],{"code":54,"score":20,"supported":13,"title":55,"abstract":56,"tags":57},"I5",[],[],[27],[59,60],"农业人工智能 病虫害识别 智慧农业 边缘计算","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边缘计算-1506",{"doi":8,"openalex_id":8,"authors":63,"venue":8,"cited_by_count":64,"oa_url":8,"card":65,"direction":69,"ingested_from":71},[],0,{"tldr":66,"method":67,"finding":68,"direction":69,"opportunity":70},"提出轻量级作物病虫害识别网络MOIR-Net，结合多尺度重参数化与能量注意力，实现高效精准识别。","多尺度Omnikernel倒残差模块、结构重参数化、无参数SimAM注意力，在I","MOIR-Net仅0.967M参数、2.30ms延迟，IP102上Top-1达64.18%，精度效率","农业人工智能与决策模型","可探索将MOIR-Net部署于真实边缘设备，或结合知识蒸馏与联邦学习，提升田间多场景泛化能力。","agent","2026-09-03T00:06:44.884359Z",{"total":19,"page":20,"page_size":19,"items":74},[75,158,242,323,390,440],{"id":76,"title":77,"url":78,"summary":79,"summary_zh":80,"content":8,"source_name":81,"source_url":78,"published_at":82,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":83,"score_detail":84,"sources":89,"tags":91,"primary_topic":94,"secondary_topics":95,"classification":96,"search_phrases":132,"slug":135,"view_count":20,"doi":136,"paper":137,"created_at":157},5248,"An entropy-guided dynamic lightweight network for identification of wild edible vegetables of BTR","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02528-x","Wild edible vegetables of Bodoland Territorial Region (BTR) are the species of plants that grow naturally and are commonly consumed as food by the indigenous communities. These plants are important sources of nutritional and therapeutic properties and are essential for food security and socio-economic development of rural communities. Therefore, sustainable conservation and utilization of these unique plant resources are of great significance. Developing an efficient and accurate automatic identification system is an essential conservation strategy for them. Current plant identification methods are mainly based on classical machine learning (ML) methods and deep convolutional neural network (CNN) architectures for recognition and classification. These methods are effective for images taken under controlled or pristine conditions, but the performance is often far from ideal in the complex and natural environments of forest and grassland, where wild edible plants are found. This paper proposes an entropy-guided dynamic lightweight deep learning architecture for automatic detection of wild edible vegetables in BTR. The proposed model employs adaptive computation with Dynamic Kernel Selection (DKS), Region-wise Adaptive Feature Routing (RAFR), Ultra-Light Context Encoding (ULCE), and Entropy-Guided Global Pooling (EGGP) to capture multi-scale plant characteristics efficiently and reduce redundant computations. The novelty of our proposed framework lies in its coordinated integration of these modules that is designed to reduce computational overhead without compromising with performance. Experimental results show that the proposed model achieves excellent classification accuracy of 90.69% with significantly reduced parameter complexity and floating-point operations (FLOPs), which is well-suited for real-time precision agriculture and low-resource edge deployment applications.","博多兰领土区域（BTR）的野生食用蔬菜是自然生长并被土著社区普遍作为食物食用的植物物种。这些植物是营养和治疗特性的重要来源，对农村社区的粮食安全和社会经济发展至关重要。因此，对这些独特植物资源的可持续保护和利用具有重要意义。开发高效准确的自动识别系统是保护这些植物资源的重要策略。当前的植物识别方法主要基于经典机器学习（ML）方法和深度卷积神经网络（CNN）架构进行识别和分类。这些方法对于在受控或原始条件下拍摄的图像是有效的，但在野生食用植物所处的森林和草地复杂自然环境中，其性能往往远不理想。本文提出了一种熵引导的动态轻量级深度学习架构，用于自动检测BTR中的野生食用蔬菜。所提出的模型采用动态核选择（DKS）、区域自适应特征路由（RAFR）、超轻量上下文编码（ULCE）和熵引导全局池化（EGGP）的自适应计算，以高效捕捉多尺度植物特征并减少冗余计算。我们所提出框架的新颖性在于这些模块的协同集成，旨在在不影响性能的情况下降低计算开销。实验结果表明，所提出的模型达到了90.69%的优异分类准确率，同时显著降低了参数复杂度和浮点运算量（FLOPs），非常适合实时精准农业和低资源边缘部署应用。","Discover Artificial Intelligence","2026-10-17T00:00:00Z",70,{"impact":85,"substance":17,"depth":86,"authority":85,"freshness":87,"relevant":20,"comment":88},12,17,9,"提出熵引导动态轻量网络用于野生食用蔬菜识别，准确率90.69%且参数与算力显著降低，方法有新意、结论可靠，但属细分应用研究，公共影响有限。",[90],{"name":81,"url":78},[25,26,27,92,93],"野生蔬菜","植物识别",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":97},{"candidates":98,"agricultural_evidence":44},[99,107,114,121,128],{"code":30,"score":12,"supported":44,"title":100,"abstract":101,"tags":106},[],[102,103,104,105],"深度学习","机器学习","machine learning","deep learning",[26],{"code":49,"score":108,"supported":44,"title":109,"abstract":110,"tags":113},7,[],[111,112],"精准农业","precision agriculture",[25],{"code":115,"score":19,"supported":44,"title":116,"abstract":117,"tags":120},"A8",[],[118,119],"粮食安全","food security",[],{"code":122,"score":123,"supported":44,"title":124,"abstract":125,"tags":127},"B1",3,[],[126],"蔬菜",[],{"code":54,"score":20,"supported":13,"title":129,"abstract":130,"tags":131},[],[],[27],[133,134],"BTR 野生食用蔬菜 识别","熵引导 轻量网络 植物识别","BTR野生食用蔬菜识别-5248","10.1007\u002Fs44163-026-02528-x",{"doi":136,"openalex_id":138,"authors":139,"venue":81,"cited_by_count":64,"oa_url":78,"card":151,"direction":69,"ingested_from":156},"W7222842686",[140,142,145,148],{"name":141,"orcid":8},"Tania Sarkar",{"name":143,"orcid":144},"Pranav Kumar Singh","https:\u002F\u002Forcid.org\u002F0000-0001-8987-0229",{"name":146,"orcid":147},"Parag Bhuyan","https:\u002F\u002Forcid.org\u002F0009-0006-4430-1851",{"name":149,"orcid":150},"Anshuman Kalla","https:\u002F\u002Forcid.org\u002F0000-0002-3985-4578",{"tldr":152,"method":153,"finding":154,"direction":69,"opportunity":155},"提出熵引导动态轻量网络，用于识别BTR野生食用蔬菜。","动态核选择、区域自适应特征路由、超轻上下文编码与熵引导池化。","分类准确率达90.69%，参数量和FLOPs显著降低，适合边缘部署。","可探索复杂自然场景下轻量模型在低资源边缘设备的实时植物识别与保护应用。","openalex","2026-10-18T23:30:58.805321Z",{"id":159,"title":160,"url":161,"summary":162,"summary_zh":163,"content":8,"source_name":164,"source_url":161,"published_at":165,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":166,"sources":169,"tags":171,"primary_topic":173,"secondary_topics":179,"classification":181,"search_phrases":202,"slug":205,"view_count":20,"doi":206,"paper":207,"created_at":241},5164,"Lightweight Hybrid CNN-Transformer Network for Robust Maize Leaf Disease Detection and Edge Deployment","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.50","Early and accurate detection of maize leaf diseases is essential for improving crop productivity and supporting precision agriculture.However, deep learning models trained on controlled leaf-image datasets often experience performance degradation under real-world agricultural conditions because of illumination variation, background clutter, occlusion, leaf orientation, and imaging noise.To address these challenges, this study develops a lightweight deep learning framework for robust maize leaf disease classification and edge-oriented deployment.The framework employs MobileNetV3-Small for efficient extraction of disease-discriminative visual features and investigates lightweight feature-learning strategies for improving classification under challenging field conditions.Experiments were conducted using PlantVillage-Maize and Field-Maize datasets comprising 6,188 images from four categories: Maize Leaf Blight (MLB), Common Rust, Healthy, and Leaf Spot.The image-only MobileNetV3-Small model achieved 97.8% accuracy and a 97.4% F1-score on the controlled PlantVillage-Maize dataset, while its performance decreased to 86.1% accuracy and an 83.9% F1-score on Field-Maize, highlighting the domain gap between controlled and real-field imagery.Robustness was further evaluated under Gaussian noise, illumination variation, and partial occlusion, together with computational-efficiency and edge-deployment analyses.The findings demonstrate the importance of lightweight and robust visual feature learning for practical maize disease diagnosis under real-world agricultural imaging conditions.","早期准确检测玉米叶片病害对于提高作物生产力和支持精准农业至关重要。然而，在受控叶片图像数据集上训练的深度学习模型，在真实农业条件下往往会出现性能下降，原因包括光照变化、背景杂乱、遮挡、叶片朝向以及成像噪声。为应对这些挑战，本研究开发了一个轻量级深度学习框架，用于稳健的玉米叶片病害分类和面向边缘的部署。该框架采用MobileNetV3-Small高效提取具有病害判别力的视觉特征，并研究轻量级特征学习策略，以提升在复杂田间条件下的分类性能。实验使用PlantVillage-Maize和Field-Maize数据集进行，共包含来自四个类别的6，188张图像：玉米大斑病（Maize Leaf Blight，MLB）、普通锈病（Common Rust）、健康（Healthy）和叶斑病（Leaf Spot）。仅使用图像的MobileNetV3-Small模型在受控的PlantVillage-Maize数据集上达到了97.8%的准确率和97.4%的F1分数，而在Field-Maize上的性能下降至86.1%的准确率和83.9%的F1分数，凸显了受控图像与真实田间图像之间的域差距。研究进一步在高斯噪声、光照变化和部分遮挡条件下评估了稳健性，并进行了计算效率和边缘部署分析。研究结果表明，轻量级且稳健的视觉特征学习对于真实农业成像条件下的实际玉米病害诊断具有重要意义。","International journal of intelligent engineering and systems","2026-10-16T00:00:00Z",{"impact":85,"substance":17,"depth":167,"authority":85,"freshness":87,"relevant":20,"comment":168},16,"该研究提出轻量级玉米叶病检测框架，并揭示受控数据集与田间数据之间的性能差距，方法扎实、结论有参考价值，但属细分技术论文，公共影响有限。",[170],{"name":164,"url":161},[25,26,27,102,172],"玉米病害",{"code":174,"slug":175,"name":176,"path":177,"parent_code":178},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[180],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":182},{"candidates":183,"agricultural_evidence":44},[184,189,194,198],{"code":174,"score":185,"supported":44,"title":186,"abstract":187,"tags":188},14,[175],[176,175],[],{"code":30,"score":190,"supported":44,"title":191,"abstract":192,"tags":193},8,[],[102,105],[26,102],{"code":49,"score":108,"supported":44,"title":195,"abstract":196,"tags":197},[],[111,112],[25],{"code":54,"score":20,"supported":13,"title":199,"abstract":200,"tags":201},[],[],[27],[203,204],"MobileNetV3 玉米叶部病害","玉米叶片病害 边缘部署","MobileNetV3玉米叶部病害-5164","10.22266\u002Fijies2026.1130.50",{"doi":206,"openalex_id":208,"authors":209,"venue":164,"cited_by_count":64,"oa_url":161,"card":235,"direction":240,"ingested_from":156},"W7222602850",[210,213,216,218,220,223,225,227,230,232],{"name":211,"orcid":212},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":214,"orcid":215},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":217,"orcid":8},"Bhavani K",{"name":219,"orcid":8},"Sailee N. Panchbhai",{"name":221,"orcid":222},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":224,"orcid":8},"Manoj Kumar S B",{"name":226,"orcid":8},"Dharamvir",{"name":228,"orcid":229},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":231,"orcid":8},"Rani Chhagan Dalvi",{"name":233,"orcid":234},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",{"tldr":236,"method":237,"finding":238,"direction":69,"opportunity":239},"构建轻量MobileNetV3-Small框架实现玉米叶片病害分类并评估边缘部署。","MobileNetV3-Small，PlantVillage-Maize与Fie","受控数据准确率97.8%，田间降至86.1%，揭示明显域差距。","可研究跨域自适应与田间鲁棒特征学习，缩小受控与真实场景性能差距。","农业遥感与作物表型","2026-10-17T23:30:28.248539Z",{"id":243,"title":244,"url":245,"summary":246,"summary_zh":247,"content":8,"source_name":248,"source_url":245,"published_at":165,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":249,"score_detail":250,"sources":254,"tags":256,"primary_topic":258,"secondary_topics":263,"classification":265,"search_phrases":282,"slug":285,"view_count":20,"doi":286,"paper":287,"created_at":322},5150,"MSFANet: a multi-scale feature aggregation network for tobacco pest recognition","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1871587","Introduction Tobacco is a globally significant economic crop, and pest infestation represents one of the primary factors contributing to declines in both yield and quality. However, tobacco pests encompass a wide variety of species that differ substantially in morphology and scale. Field-captured images are frequently subject to complex background interference and class imbalance, presenting considerable challenges for automated recognition. Existing deep learning approaches remain limited in their capacity for multi-scale feature extraction and discriminative feature representation under such conditions. To address these challenges, this study proposes a Multi-Scale Feature Aggregation Network (MSFANet) for tobacco pest recognition, formulated here as a single-label image classification task. Methods To address scale variation and complex field backgrounds, two task-oriented modules were developed. The Multi-Scale Pyramid Pooling (MSPP) module aggregates contextual information across multiple receptive fields through parallel feature extraction and adaptive cross-branch fusion. The Hierarchical Feature Fusion Block (HFFB) subsequently refines the feature representations through spatial gating and partial convolution. An auxiliary classification head and Focal Loss were incorporated during training to provide intermediate supervision and address class imbalance, respectively. Results The effectiveness of MSFANet was evaluated on a dataset comprising 13 tobacco-associated pest and natural-enemy categories. The model achieved accuracy, precision, recall, and F1-score of 97.63%, 97.89%, 97.59%, and 97.71%, respectively, with a parameter count of 1.21 M. Among the models trained from random initialization, MSFANet shared the highest accuracy while using the fewest parameters. Discussion By combining multi-scale contextual aggregation with hierarchical feature refinement, MSFANet achieved accurate classification across the 13 tobacco-associated categories under complex field conditions. The proposed method provides effective technical support for automated and precision-oriented pest monitoring in tobacco fields, offering practical value for advancing precise pest management and the broader development of smart agriculture.","引言 烟草是全球重要的经济作物，虫害侵染是导致其产量和品质下降的主要因素之一。然而，烟草害虫种类繁多，形态和尺度差异显著。田间采集的图像常受到复杂背景干扰和类别不平衡的影响，给自动化识别带来了相当大的挑战。现有深度学习方法在此类条件下进行多尺度特征提取和判别性特征表示的能力仍然有限。为应对这些挑战，本研究提出了一种用于烟草害虫识别的多尺度特征聚合网络（Multi-Scale Feature Aggregation Network，MSFANet），并将其形式化为单标签图像分类任务。方法 针对尺度变化和复杂田间背景，开发了两个面向任务的模块。多尺度金字塔池化（Multi-Scale Pyramid Pooling，MSPP）模块通过并行特征提取和自适应跨分支融合，聚合多个感受野的上下文信息。分层特征融合模块（Hierarchical Feature Fusion Block，HFFB）随后通过空间门控和部分卷积对特征表示进行细化。训练过程中引入辅助分类头和Focal Loss，分别提供中间监督和处理类别不平衡。结果 在包含13个烟草相关害虫及天敌类别的数据集上评估了MSFANet的有效性。模型的准确率、精确率、召回率和F1分数分别为97.63%、97.89%、97.59%和97.71%，参数量为1.21 M。在随机初始化训练的模型中，MSFANet以最少的参数量取得了最高准确率。讨论 通过结合多尺度上下文聚合与分层特征细化，MSFANet在复杂田间条件下实现了对13个烟草相关类别的准确分类。所提方法为烟草田间害虫的自动化和精准监测提供了有效的技术支持，对推进精准害虫管理和智慧农业的更广泛发展具有实用价值。","Frontiers in Plant Science",76,{"impact":167,"substance":251,"depth":86,"authority":252,"freshness":87,"relevant":20,"comment":253},21,13,"该论文提出轻量化多尺度特征聚合网络，在烟草害虫识别上取得97%以上精度且参数量仅1.21M，方法新颖、数据扎实，对智慧农业虫情监测有实用价值，值得进入每日精选。",[255],{"name":248,"url":245},[25,26,102,28,257],"烟草",{"code":259,"slug":260,"name":261,"path":262,"parent_code":178},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops",[264],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":266},{"candidates":267,"agricultural_evidence":44},[268,273,277],{"code":259,"score":16,"supported":44,"title":269,"abstract":271,"tags":272},[270],"tobacco",[257,270],[257],{"code":30,"score":87,"supported":44,"title":274,"abstract":275,"tags":276},[],[102,105],[26,102,28],{"code":49,"score":108,"supported":44,"title":278,"abstract":279,"tags":281},[],[25,280],"smart agriculture",[25],[283,284],"MSFANet 烟草害虫识别","多尺度特征聚合 害虫识别","MSFANet烟草害虫识别-5150","10.3389\u002Ffpls.2026.1871587",{"doi":286,"openalex_id":288,"authors":289,"venue":248,"cited_by_count":64,"oa_url":315,"card":316,"direction":321,"ingested_from":156},"W7222603139",[290,292,294,296,298,300,302,304,307,310,313],{"name":291,"orcid":8},"Shun He",{"name":293,"orcid":8},"Sifan Li",{"name":295,"orcid":8},"Xinjian Li",{"name":297,"orcid":8},"Qianqian Luo",{"name":299,"orcid":8},"Dong Sufen",{"name":301,"orcid":8},"Lu Lei",{"name":303,"orcid":8},"Xingjiang Chen",{"name":305,"orcid":306},"Liuti Cai","https:\u002F\u002Forcid.org\u002F0000-0002-9151-8002",{"name":308,"orcid":309},"Jian‐Yu Meng","https:\u002F\u002Forcid.org\u002F0000-0002-5796-1086",{"name":311,"orcid":312},"Ning Lu","https:\u002F\u002Forcid.org\u002F0000-0003-0214-5038",{"name":314,"orcid":8},"Hancheng Wang","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1871587\u002Fpdf",{"tldr":317,"method":318,"finding":319,"direction":69,"opportunity":320},"提出MSFANet多尺度特征聚合网络，实现复杂田间背景下烟草害虫的自动识别。","多尺度金字塔池化MSPP、分层特征融合HFFB、辅助分类头与Focal Loss","模型准确率97.63%、参数量仅1.21M，在随机初始化模型中精度最高且参数最少。","可探索轻量多尺度网络在边缘设备部署及跨作物害虫迁移识别，结合类不平衡与复杂背景的鲁棒性研究。","智慧农业 \u002F 农业物联网","2026-10-17T23:30:08.695455Z",{"id":324,"title":325,"url":326,"summary":327,"summary_zh":328,"content":8,"source_name":329,"source_url":326,"published_at":330,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":331,"score_detail":332,"sources":334,"tags":336,"primary_topic":339,"secondary_topics":340,"classification":341,"search_phrases":366,"slug":369,"view_count":370,"doi":371,"paper":372,"created_at":389},4990,"Smart Crop Advisory System","https:\u002F\u002Fdoi.org\u002F10.55041\u002Fijcope.v2i10.081","The Smart Crop Advisory System is a web-based agricultural decision-support platform that uses Artificial Intelligence (AI) and Machine Learning (ML) technologies to assist farmers in making informed farming decisions. Traditional agriculture faces several challenges, including unsuitable crop selection, unpredictable weather conditions, crop diseases, and fluctuations in market prices. The proposed system integrates essential agricultural services, including crop recommendation, weather forecasting, crop disease detection, agricultural market price information, and an AI-based multilingual voice assistant. It also provides farmer profile management, crop price trend analysis, and rainfall trend visualization through an interactive dashboard. The crop recommendation module helps farmers identify suitable crops based on relevant agricultural parameters, while the disease detection module supports the identification of potential crop diseases. Weather and market information help farmers plan agricultural activities and make informed selling decisions. The multilingual voice assistant aims to improve accessibility by enabling farmers to interact with the system through voice-based communication. Overall, the Smart Crop Advisory System aims to improve access to agricultural information, support effective decision-making, promote efficient resource utilization, and encourage sustainable farming practices. Keywords: Smart Agriculture, Crop Recommendation, Machine Learning, Crop Disease Detection, Weather Forecasting, Market Price Analysis, Voice Assistant, Sustainable Agriculture.","智能作物咨询系统是一个基于网络的农业决策支持平台，利用人工智能（AI）和机器学习（ML）技术帮助农民做出明智的农作决策。传统农业面临诸多挑战，包括作物选择不当、天气条件不可预测、作物病害以及市场价格波动。所提出的系统整合了基本农业服务，包括作物推荐、天气预报、作物病害检测、农产品市场价格信息以及基于AI的多语言语音助手。它还通过交互式仪表板提供农民档案管理、作物价格趋势分析和降雨趋势可视化。作物推荐模块帮助农民根据相关农业参数识别适宜作物，而病害检测模块支持识别潜在作物病害。天气和市场信息帮助农民规划农业活动并做出明智的销售决策。多语言语音助手旨在通过使农民能够以语音方式与系统交互来提高可及性。总体而言，智能作物咨询系统旨在改善农业信息的获取，支持有效决策，促进资源高效利用，并鼓励可持续农业实践。关键词：智慧农业、作物推荐、机器学习、作物病害检测、天气预报、市场价格分析、语音助手、可持续农业。","International Journal of Creative and Open Research in Engineering and Management","2026-10-14T00:00:00Z",48,{"impact":190,"substance":185,"depth":85,"authority":19,"freshness":190,"relevant":20,"comment":333},"面向农户的AI农业决策支持系统论文，功能集成度较高但方法新颖性与数据规模有限，属细分领域进展，可作为智慧农业主题聚合素材。",[335],{"name":329,"url":326},[25,26,28,337,338],"农业气象","作物推荐",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":342},{"candidates":343,"agricultural_evidence":44},[344,350,354,361],{"code":30,"score":345,"supported":44,"title":346,"abstract":347,"tags":349},11,[],[103,104,348],"artificial intelligence",[26,28],{"code":49,"score":108,"supported":44,"title":351,"abstract":352,"tags":353},[],[25,280],[25],{"code":355,"score":19,"supported":44,"title":356,"abstract":357,"tags":360},"H8",[],[358,359],"可持续农业","sustainable agriculture",[],{"code":362,"score":20,"supported":13,"title":363,"abstract":364,"tags":365},"H7",[],[],[337],[367,368],"AI 作物推荐 语音助手","农业人工智能 病虫害识别 作物推荐 农业气象","AI作物推荐语音助手-4990",2,"10.55041\u002Fijcope.v2i10.081",{"doi":371,"openalex_id":373,"authors":374,"venue":329,"cited_by_count":64,"oa_url":383,"card":384,"direction":321,"ingested_from":156},"W7221803029",[375,377,379,381],{"name":376,"orcid":8},"Bhuvana H P",{"name":378,"orcid":8},"Kavya C M",{"name":380,"orcid":8},"Manjula S",{"name":382,"orcid":8},"Priyanka A","https:\u002F\u002Fijcope.org\u002Fwp-content\u002Fuploads\u002F2026\u002F10\u002FSmart-Crop-Advisory-System.pdf",{"tldr":385,"method":386,"finding":387,"direction":69,"opportunity":388},"构建基于AI\u002FML的Web农业决策支持平台，为农民提供作物推荐、病害检测、天气与市场价格等服务。","集成机器学习模型、多语言语音助手与交互式仪表盘，整合天气、市场及农业参数数据。","系统可提升农业信息获取与决策效率，促进资源高效利用和可持续耕作。","可探索多源数据融合的轻量化模型与本地化语音交互，提升小农户采纳率与实时决策精度。","2026-10-15T23:30:09.048921Z",{"id":391,"title":392,"url":393,"summary":394,"summary_zh":8,"content":8,"source_name":395,"source_url":8,"published_at":396,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":397,"sources":399,"tags":401,"primary_topic":404,"secondary_topics":405,"classification":406,"search_phrases":428,"slug":431,"view_count":64,"doi":8,"paper":432,"created_at":439},4967,"SADR-VSS:一种用于轻量级农业目标检测的场景自适应动态路由视觉状态空间模块","https:\u002F\u002Fwww.ebiotrade.com\u002Fnewsf\u002F2026-10\u002F20261013084746521.htm","本文提出场景自适应动态路由视觉状态空间模块SADR-VSS,用于复杂田间条件下的轻量级农业目标检测。该方法引入场景自适应路由机制,动态协调局部卷积表示和长距离状态空间建模,从而在异质农业场景中实现更灵活的特征提取。大量实验表明,SADR-VSS实现了改善的检测性能,验证了其在嵌入式设备和农业自动化平台上的部署潜力。研究面向自动除草平台的高分辨率图像,在YOLOv11n基线基础上展示更集中的目标激活响应。","生物通 2026 年 10 月 13 日","2026-10-13T00:00:00Z",{"impact":16,"substance":17,"depth":86,"authority":190,"freshness":87,"relevant":20,"comment":398},"提出场景自适应动态路由视觉状态空间模块，在YOLOv11n基线上提升复杂田间轻量检测性能，方法新颖且面向嵌入式除草平台，具备较强专业参考价值。",[400],{"name":395,"url":393},[25,26,27,402,403],"农业目标检测","智能除草",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":407},{"candidates":408,"agricultural_evidence":44},[409,414,420,424],{"code":30,"score":85,"supported":44,"title":410,"abstract":412,"tags":413},[411],"目标检测",[411],[26],{"code":415,"score":123,"supported":44,"title":416,"abstract":417,"tags":419},"F4",[],[418],"除草",[],{"code":49,"score":20,"supported":13,"title":421,"abstract":422,"tags":423},[],[],[25],{"code":54,"score":20,"supported":13,"title":425,"abstract":426,"tags":427},[],[],[27],[429,430],"SADR-VSS 农业目标检测","YOLOv11n 自动除草","SADR-VSS农业目标检测-4967",{"doi":8,"openalex_id":8,"authors":433,"venue":8,"cited_by_count":64,"oa_url":8,"card":434,"direction":69,"ingested_from":71},[],{"tldr":435,"method":436,"finding":437,"direction":69,"opportunity":438},"提出场景自适应动态路由视觉状态空间模块SADR-VSS，用于复杂田间轻量级农业目标检测。","结合局部卷积与长距离状态空间建模，基于YOLOv11n在自动除草高分辨率图像上验","SADR-VSS提升检测性能，目标激活更集中，具备嵌入式农业平台部署潜力。","可探索动态路由机制在更多作物与杂草场景的泛化性，及与边缘计算硬件的协同优化。","2026-10-15T00:06:08.643930Z",{"id":441,"title":442,"url":443,"summary":444,"summary_zh":445,"content":8,"source_name":446,"source_url":443,"published_at":447,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":448,"score_detail":449,"sources":451,"tags":453,"primary_topic":455,"secondary_topics":460,"classification":462,"search_phrases":478,"slug":481,"view_count":64,"doi":482,"paper":483,"created_at":506},4818,"Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1837896","Early and accurate diagnosis of potato leaf diseases is critical for preventing yield losses under real field conditions. This study proposes a hybrid deep feature–based machine learning framework that combines transfer learning and ensemble classifiers to automatically identify seven potato leaf disease classes from images. A total of 4,260 images from the publicly available Potato Leaf Disease Dataset were organized into seven categories: Bacteria, Virus, Pest, Fungi, Nematode, Phytophthora, and Healthy. Real-time image augmentation was performed using Keras ImageDataGenerator to improve strength to field variability. Deep feature vectors were extracted from three pre-trained convolutional neural networks (ResNet50, EfficientNetB0, and MobileNetV2), each followed by a lightweight dense head, and concatenated into 768-dimensional feature representations. After standardization, dimensionality reduction was applied via principal component analysis, and class imbalance in the training set was addressed using the SMOTE-ENN hybrid resampling method. On these deep features, 32 classical machine learning and ensemble models including SVMs, tree-based methods, boosting algorithms, multilayer perceptrons, and four ensemble schemes, were trained. Model performance was assessed by three-fold cross-validation on the training set and final evaluation on the held-out validation set using accuracy, precision, recall, and macro F1-score. Ensemble models outperformed individual classifiers. The best performance was obtained with the StackingClassifier_L2 model, which combines XGBoost, LightGBM, Random Forest, SVM with RBF kernel, and Extra Trees within a stacking framework. This model achieved an accuracy of 81.34% and a macro F1-score of 81.74% on the validation set. The proposed hybrid system, which integrates multi-backbone deep feature extraction with comprehensive classical and ensemble classifiers, provides a robust and practical solution for automatic potato leaf disease classification in uncontrolled field conditions. The results suggest that stacking-based ensembles on top of deep features can capture complex visual patterns more effectively than single models and may support decision-making in precision agriculture.","在马铃薯实际田间条件下，早期准确地诊断叶片病害对于防止产量损失至关重要。本研究提出了一种基于混合深度特征的机器学习框架，该框架结合迁移学习和集成分类器，从图像中自动识别七类马铃薯叶片病害。来自公开可用的马铃薯叶片病害数据集的4,260张图像被分为七个类别：细菌（Bacteria）、病毒（Virus）、害虫（Pest）、真菌（Fungi）、线虫（Nematode）、疫霉（Phytophthora）和健康（Healthy）。使用Keras ImageDataGenerator进行实时图像增强，以提高对田间变异的鲁棒性。从三个预训练的卷积神经网络（ResNet50、EfficientNetB0和MobileNetV2）中提取深度特征向量，每个网络后接一个轻量级密集头，并将其拼接为768维特征表示。经过标准化后，通过主成分分析进行降维，并使用SMOTE-ENN混合重采样方法解决训练集中的类别不平衡问题。在这些深度特征上，训练了32种经典机器学习和集成模型，包括支持向量机、基于树的方法、提升算法、多层感知机以及四种集成方案。通过训练集上的三折交叉验证和保留验证集上的最终评估，使用准确率、精确率、召回率和宏F1分数评估模型性能。集成模型优于单个分类器。最佳性能由StackingClassifier_L2模型获得，该模型在堆叠框架内结合了XGBoost、LightGBM、随机森林、带RBF核的支持向量机和极端随机树。该模型在验证集上达到了81.34%的准确率和81.74%的宏F1分数。所提出的混合系统将多骨干深度特征提取与全面的经典分类器和集成分类器相结合，为无控制田间条件下的马铃薯叶片病害自动分类提供了一种稳健且实用的解决方案。结果表明，基于深度特征的堆叠集成能够比单一模型更有效地捕捉复杂的视觉模式，并可能支持精准农业中的决策。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",65,{"impact":190,"substance":17,"depth":167,"authority":252,"freshness":190,"relevant":20,"comment":450},"方法组合较全面、数据规模明确，但验证集准确率仅81.34%，属细分领域技术进展，可作主题聚合素材而非头条精选。",[452],{"name":446,"url":443},[25,26,454,28,111],"马铃薯",{"code":456,"slug":457,"name":458,"path":459,"parent_code":178},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains",[461],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":463},{"candidates":464,"agricultural_evidence":44},[465,469,474],{"code":30,"score":167,"supported":44,"title":466,"abstract":467,"tags":468},[104],[103,104],[26,28],{"code":456,"score":16,"supported":44,"title":470,"abstract":472,"tags":473},[471],"potato",[454,471],[454],{"code":49,"score":190,"supported":44,"title":475,"abstract":476,"tags":477},[],[111,112],[25,111],[479,480],"马铃薯 叶片病害 深度学习","Potato Leaf Disease Dataset 集成学习","马铃薯叶片病害深度学习-4818","10.15832\u002Fankutbd.1837896",{"doi":482,"openalex_id":484,"authors":485,"venue":446,"cited_by_count":64,"oa_url":500,"card":501,"direction":321,"ingested_from":156},"W7221546496",[486,489,491,494,497],{"name":487,"orcid":488},"Cihan Ünal","https:\u002F\u002Forcid.org\u002F0000-0002-5255-4078",{"name":490,"orcid":8},"Cengizhan Tumer",{"name":492,"orcid":493},"Elham Tahsin Yasin","https:\u002F\u002Forcid.org\u002F0000-0003-3246-6000",{"name":495,"orcid":496},"İlkay Çınar","https:\u002F\u002Forcid.org\u002F0000-0003-0611-3316",{"name":498,"orcid":499},"Murat Köklü","https:\u002F\u002Forcid.org\u002F0000-0002-2737-2360","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5487015",{"tldr":502,"method":503,"finding":504,"direction":69,"opportunity":505},"融合三种CNN深度特征与集成学习，实现田间马铃薯叶片七类病害分类。","ResNet50\u002FEfficientNetB0\u002FMobileNetV2特征拼接+","StackingClassifier_L2最优，验证集准确率81.34%、宏F1为81.74%。","可探索轻量化模型与多模态数据融合，提升非受控田间小样本病害识别鲁棒性。","2026-10-13T23:30:16.021066Z"]