[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3960":3,"related-3960":99},{"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":30,"secondary_topics":36,"classification":37,"search_phrases":83,"slug":86,"view_count":87,"doi":8,"paper":88,"created_at":98},3960,"Groundbreaking AI Robot Picks Tomatoes Autonomously——YOLOv8n-BiFPN-WIoU模型驱动采摘新范式","https:\u002F\u002Fagritechinsights.com\u002Findex.php\u002F2026\u002F10\u002F02\u002Fgroundbreaking-ai-robot-picks-tomatoes-autonomously","山东理工大学孟凡钊团队开发出基于YOLOv8n-BiFPN-WIoU轻量级深度学习模型的温室番茄自主采摘机器人，可在边缘设备NVIDIA Jetson Nano上运行，优化后达21.1 FPS实时运行；定位误差3.5±0.32mm；mAP@0.5达92.4%。系统采用六轴机械臂+双爪末端执行器，针对温室遮挡与光照变化优化，适用于商业化串番茄采收；系统基于开源ROS模块化设计，未来可适配黄瓜、辣椒、草莓等。",null,"Agritech Insights·2026年10月02日（Frontiers in Plant Science）","2026-10-02T00:00:00Z","论文",10,false,86,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":20,"comment":21},22,23,18,13,1,"轻量模型+边缘部署的番茄自主采摘机器人，方法新颖、指标扎实，具备细分行业参考价值。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","农业机器人","边缘计算","番茄采摘",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":38,"locked":13,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,53,60,66,73,78],{"code":31,"score":44,"supported":45,"title":46,"abstract":47,"tags":52},9,true,[],[48,49,50,51],"番茄","辣椒","黄瓜","草莓",[],{"code":54,"score":55,"supported":45,"title":56,"abstract":57,"tags":59},"F6",4,[],[58],"采摘机器人",[27],{"code":61,"score":55,"supported":45,"title":62,"abstract":63,"tags":65},"I2",[],[64],"深度学习",[26],{"code":67,"score":68,"supported":45,"title":69,"abstract":70,"tags":72},"B7",3,[],[71],"温室",[],{"code":74,"score":20,"supported":13,"title":75,"abstract":76,"tags":77},"I1",[],[],[25],{"code":79,"score":20,"supported":13,"title":80,"abstract":81,"tags":82},"I5",[],[],[28],[84,85],"山东理工大学 番茄采摘机器人","YOLOv8n 温室番茄 采摘","山东理工大学番茄采摘机器人-3960",8,{"doi":8,"openalex_id":8,"authors":89,"venue":8,"cited_by_count":90,"oa_url":8,"card":91,"direction":95,"ingested_from":97},[],0,{"tldr":92,"method":93,"finding":94,"direction":95,"opportunity":96},"开发基于YOLOv8n-BiFPN-WIoU的轻量模型，实现温室番茄自主采摘机器人实时运行。","YOLOv8n-BiFPN-WIoU轻量模型，Jetson Nano边缘部署，六","mAP@0.5达92.4%，21.1 FPS实时运行，定位误差3.5±0.32mm，可商业化串番茄采","智慧农业 \u002F 农业物联网","可延伸至多作物泛化、复杂遮挡与光照鲁棒性提升，以及边缘端模型轻量化与多机协同采摘。","agent","2026-10-02T11:53:16.408068Z",{"total":100,"page":20,"page_size":100,"items":101},6,[102,153,221,281,343,435],{"id":103,"title":104,"url":105,"summary":106,"summary_zh":8,"content":8,"source_name":107,"source_url":8,"published_at":108,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":109,"score_detail":110,"sources":114,"tags":116,"primary_topic":119,"secondary_topics":120,"classification":121,"search_phrases":140,"slug":143,"view_count":90,"doi":8,"paper":144,"created_at":152},5533,"基于低成本遥操作机械臂模仿学习的草莓果柄定点采摘","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.22765","该研究构建视觉运动模仿学习流程，统一感知、运动规划与接触操作，从人工遥操作演示训练基于ResNet-50骨干的动作分块Transformer策略，并在Jetson AGX Orin边缘平台以15赫兹自主部署。策略在130条演示、十万梯度步内损失由2.84降至0.091，数据集与模型权重已开源。预印本，已被IROS农业机器人研讨会接收。","arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z",68,{"impact":111,"substance":112,"depth":18,"authority":44,"freshness":55,"relevant":20,"comment":113},16,21,"方法新颖、数据与开源材料扎实，但属预印本且已过一周，适合作为细分技术进展收录而非头条精选。",[115],{"name":107,"url":105},[26,27,28,117,118],"模仿学习","草莓采摘",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":122},{"candidates":123,"agricultural_evidence":45},[124,128,132,136],{"code":31,"score":87,"supported":45,"title":125,"abstract":126,"tags":127},[51],[],[],{"code":54,"score":55,"supported":45,"title":129,"abstract":130,"tags":131},[],[27],[27],{"code":61,"score":20,"supported":13,"title":133,"abstract":134,"tags":135},[],[],[26],{"code":79,"score":20,"supported":13,"title":137,"abstract":138,"tags":139},[],[],[28],[141,142],"草莓果柄 定点采摘 机械臂","Jetson AGX Orin 采摘 模仿学习","草莓果柄定点采摘机械臂-5533",{"doi":8,"openalex_id":8,"authors":145,"venue":8,"cited_by_count":90,"oa_url":8,"card":146,"direction":150,"ingested_from":97},[],{"tldr":147,"method":148,"finding":149,"direction":150,"opportunity":151},"用低成本遥操作机械臂采集演示，模仿学习实现草莓果柄定点采摘。","ResNet-50骨干的动作分块Transformer策略，Jetson边缘部署","130条演示训练后损失降至0.091，策略可15赫兹自主采摘。","农业人工智能与决策模型","可探索小样本跨品种泛化与失败恢复，降低演示采集成本。","2026-10-22T00:07:09.891422Z",{"id":154,"title":155,"url":156,"summary":157,"summary_zh":158,"content":8,"source_name":159,"source_url":156,"published_at":160,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":161,"score_detail":162,"sources":164,"tags":166,"primary_topic":168,"secondary_topics":169,"classification":170,"search_phrases":194,"slug":197,"view_count":68,"doi":198,"paper":199,"created_at":220},2774,"SpatioFormer: spatial perception enhancement for lightweight agricultural pest and disease detection","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1925867","Introduction In precision agriculture, accurate and efficient detection of crop pests and diseases is crucial. However, existing models in complex environments are prone to insufficient spatial perception and attenuation of disease texture features, making it difficult to balance recognition accuracy and lightweighting. Methods To address this, this study proposes a lightweight spatial perception enhancement hybrid architecture, SpatioFormer. First, a Pixel-level Detail Retrieval (PDR) mechanism is designed. This mechanism leverages cross-layer dynamic routing to facilitate the fusion of deep semantic features with shallow texture features, significantly enhancing the capability to capture disease features. Second, we design a Spatially Adaptive Modulation Attention (SA-SHMA) mechanism, which utilizes large-kernel depthwise convolution to capture contextual information and combines dynamic modulation maps for fine-grained focusing, efficiently recovering spatial details, and suppressing background noise. Furthermore, this paper introduces a Context-Guided Asymmetric Gated Linear Unit (CGA-GLU), which utilizes an asymmetric design focusing on the gating branch and incorporates contextual information for guidance, enhancing the inter-channel representation capability with minimal computational overhead. Results Finally, extensive experiments on the PDDD and Tomato-Village datasets validated the effectiveness of the proposed model. The proposed model achieves a Top-1 accuracy of 81.05% on the PDDD dataset and an AP 50 of 61.53% on the Tomato-Village dataset, with testing latency on edge devices being highly competitive among existing models. Discussion Compared to existing lightweight hybrid models, SpatioFormer effectively recovers shallow spatial details and precisely suppresses complex background noise under an extremely low parameter budget. Consequently, it achieves a superior balance between practical disease localization capability and inference latency on resource-constrained edge devices.","引言 在精准农业中，准确高效地检测作物病虫害至关重要。然而，复杂环境下的现有模型容易出现空间感知不足和病害纹理特征衰减的问题，难以兼顾识别精度与轻量化。方法 为解决这一问题，本研究提出了一种轻量级空间感知增强混合架构——SpatioFormer。首先，设计了像素级细节检索（Pixel-level Detail Retrieval，PDR）机制。该机制利用跨层动态路由，促进深层语义特征与浅层纹理特征的融合，显著增强了对病害特征的捕捉能力。其次，设计了空间自适应调制注意力（Spatially Adaptive Modulation Attention，SA-SHMA）机制，该机制利用大核深度卷积捕获上下文信息，并结合动态调制图进行细粒度聚焦，高效恢复空间细节并抑制背景噪声。此外，本文引入了上下文引导非对称门控线性单元（Context-Guided Asymmetric Gated Linear Unit，CGA-GLU），其采用聚焦门控分支的非对称设计，并融入上下文信息进行引导，以极小的计算开销增强了通道间表征能力。结果 最后，在PDDD和Tomato-Village数据集上的大量实验验证了所提模型的有效性。所提模型在PDDD数据集上取得了81.05%的Top-1准确率，在Tomato-Village数据集上取得了61.53%的AP 50，其在边缘设备上的测试延迟在现有模型中极具竞争力。讨论 与现有轻量级混合模型相比，SpatioFormer在极低的参数预算下有效恢复了浅层空间细节，并精确抑制了复杂背景噪声。因此，它在实际病害定位能力与资源受限边缘设备上的推理延迟之间实现了更优的平衡。","Frontiers in Plant Science","2026-09-16T00:00:00Z",77,{"impact":111,"substance":112,"depth":18,"authority":19,"freshness":44,"relevant":20,"comment":163},"提出轻量化空间感知增强架构，在边缘设备上兼顾检测精度与推理延迟，方法新颖、实验扎实，对农业病虫害智能识别有参考价值。",[165],{"name":159,"url":156},[25,26,28,48,167],"病虫害检测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":171},{"candidates":172,"agricultural_evidence":45},[173,180,185,190],{"code":74,"score":174,"supported":45,"title":175,"abstract":176,"tags":179},7,[],[177,178],"精准农业","precision agriculture",[25],{"code":31,"score":55,"supported":45,"title":181,"abstract":182,"tags":184},[],[183],"tomato",[48],{"code":61,"score":186,"supported":13,"title":187,"abstract":188,"tags":189},2,[],[],[26,167],{"code":79,"score":20,"supported":13,"title":191,"abstract":192,"tags":193},[],[],[28],[195,196],"农业人工智能 病虫害检测 智慧农业 边缘计算","农业人工智能 病虫害检测","农业人工智能病虫害检测智慧农业边缘计算-2774","10.3389\u002Ffpls.2026.1925867",{"doi":198,"openalex_id":200,"authors":201,"venue":159,"cited_by_count":90,"oa_url":213,"card":214,"direction":95,"ingested_from":219},"W7213437661",[202,204,207,209,211],{"name":203,"orcid":8},"Wenbo Ma",{"name":205,"orcid":206},"Hao Sun","https:\u002F\u002Forcid.org\u002F0000-0002-6983-8149",{"name":208,"orcid":8},"Kun Zhou",{"name":210,"orcid":8},"Meichun Wang",{"name":212,"orcid":8},"Rui Fu","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1925867\u002Fpdf",{"tldr":215,"method":216,"finding":217,"direction":150,"opportunity":218},"提出轻量混合架构SpatioFormer，提升复杂环境下农作物病虫害检测的空间感知能力。","设计PDR跨层动态路由、SA-SHMA大核注意力与CGA-GLU门控，在PDDD","在极低参数量下恢复浅层空间细节并抑制背景噪声，边缘设备延迟具竞争力。","可探索将空间感知增强机制迁移至多作物多病害场景，并研究边缘端实时部署的能效优化。","openalex","2026-09-17T23:30:14.148727Z",{"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":161,"score_detail":228,"sources":230,"tags":232,"primary_topic":235,"secondary_topics":236,"classification":243,"search_phrases":269,"slug":272,"view_count":186,"doi":8,"paper":273,"created_at":280},2274,"ArXiv 2609.10469 AgroVisNet:轻量化卷积网络及萝卜-马铃薯-葫芦病害诊断基准","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.10469","提出AgroVisNet紧凑型卷积网络及专家验证基准BD-PlantDX,包含孟加拉国Bogura和Nilphamari地区12类萝卜、土豆、葫芦共12432张田间图像。模型参数仅29万,测试精度99.52%,加权F1 99.52%,部署后量化0.46MB,CPU推理8.40ms\u002F张。","arXiv 2609.10469","2026-09-08T16:00:00Z",{"impact":18,"substance":16,"depth":18,"authority":19,"freshness":100,"relevant":20,"comment":229},"提出29万参数轻量卷积网络与万余张田间病害基准数据集，量化后仅0.46MB、CPU单张8.4ms，对低成本边缘部署的作物病害诊断有实用参考价值。",[231],{"name":226,"url":224},[25,26,28,233,234],"植物病害识别","轻量化模型",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[237],{"code":238,"slug":239,"name":240,"path":241,"parent_code":242},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",{"status":38,"locked":13,"version":39,"method":40,"evidence":244},{"candidates":245,"agricultural_evidence":45},[246,252,257,261,265],{"code":31,"score":247,"supported":45,"title":248,"abstract":250,"tags":251},11,[249],"萝卜",[249],[],{"code":238,"score":87,"supported":45,"title":253,"abstract":255,"tags":256},[254],"马铃薯",[],[],{"code":61,"score":68,"supported":13,"title":258,"abstract":259,"tags":260},[],[],[26,233,234],{"code":74,"score":20,"supported":13,"title":262,"abstract":263,"tags":264},[],[],[25],{"code":79,"score":20,"supported":13,"title":266,"abstract":267,"tags":268},[],[],[28],[270,271],"农业人工智能 植物病害识别 轻量化模型 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别轻量化模型智慧农业-2274",{"doi":8,"openalex_id":8,"authors":274,"venue":8,"cited_by_count":90,"oa_url":8,"card":275,"direction":150,"ingested_from":97},[],{"tldr":276,"method":277,"finding":278,"direction":150,"opportunity":279},"提出轻量卷积网络AgroVisNet及萝卜、马铃薯、葫芦病害诊断基准BD-PlantDX。","构建12432张田间图像基准，设计29万参数紧凑CNN并量化部署。","测试精度99.52%，量化后仅0.46MB，CPU推理8.40ms\u002F张。","可探索跨地区跨作物泛化、田间复杂光照下的轻量模型鲁棒性与边缘部署。","2026-09-13T00:04:05.295687Z",{"id":282,"title":283,"url":284,"summary":285,"summary_zh":286,"content":8,"source_name":287,"source_url":284,"published_at":288,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":289,"score_detail":290,"sources":293,"tags":295,"primary_topic":298,"secondary_topics":299,"classification":305,"search_phrases":323,"slug":326,"view_count":90,"doi":327,"paper":328,"created_at":342},5387,"LIGHTWEIGHT FEATURE FUSED ATTENTION DRIVEN MULTI LEVEL HYBRID MOBILENET V2 FRAMEWORK FOR EARLY TOMATO LEAF DISEASE DETECTION","https:\u002F\u002Fdoi.org\u002F10.62441\u002Factainnovations.vi.1918","It is crucial to find and treat tomato crop diseases early and accurately to improve crop efficiency and make sure there is no scarcity of crop. However, computerized analysis is provocative due to lighting differences, compound backgrounds, and graphic likenesses among infection regions. Research work proposed a lightweight Attention Driven Multi Level Hybrid MobileNet-V2 algorithm that fuses the handcrafted texture structures with Deep Learning (DL) features, then image preprocessing is incorporated using Gaussian, Bilateral, and Guided filters to minimize noise by preserving the disease lesions. LAB color model along with Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to improve the contrast. Otsu thresholding is involved to effectively separate the leaf segment from diseased parts. Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) descriptors are used to obtain fine-grained features, while high level features are gained by pretrained MobileNet-V2 model. Features fusion is fed to the fully connected layers of deep learning model for training and validation purpose. Results have revealed that the suggested model attains better classification performance as compared to existing models, making it an effective explanation for real time tomato leaf disease detection for smart agriculture applications.","早期准确发现并治疗番茄作物病害，对于提高作物效率、确保作物不短缺至关重要。然而，由于光照差异、复杂背景以及感染区域之间的图形相似性，计算机化分析具有挑战性。研究提出了一种轻量级注意力驱动多层混合MobileNet-V2算法，该算法将手工纹理结构与深度学习（DL）特征相融合，然后结合高斯、双边和引导滤波器进行图像预处理，以在保留病害病变的同时最小化噪声。采用LAB颜色模型和对比度受限自适应直方图均衡化（CLAHE）来提高对比度。引入Otsu阈值分割以有效分离叶片片段与病害部分。使用局部二值模式（LBP）和灰度共生矩阵（GLCM）描述符获取细粒度特征，同时通过预训练的MobileNet-V2模型获取高层特征。特征融合后输入深度学习模型的全连接层进行训练和验证。结果表明，与现有模型相比，所提出的模型取得了更好的分类性能，使其成为智慧农业应用中实时番茄叶片病害检测的有效解决方案。","Acta Innovations","2026-10-18T00:00:00Z",64,{"impact":291,"substance":18,"depth":111,"authority":12,"freshness":87,"relevant":20,"comment":292},12,"提出融合手工纹理特征与MobileNet-V2的轻量番茄叶病检测方法，有一定方法新颖性，但属单篇论文、应用范围有限，未达每日精选门槛。",[294],{"name":287,"url":284},[25,26,64,296,297],"番茄病害","图像识别",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[300],{"code":61,"slug":301,"name":302,"path":303,"parent_code":304},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":38,"locked":13,"version":39,"method":40,"evidence":306},{"candidates":307,"agricultural_evidence":45},[308,313,318],{"code":31,"score":309,"supported":45,"title":310,"abstract":311,"tags":312},15,[183],[48,183],[296],{"code":61,"score":44,"supported":45,"title":314,"abstract":315,"tags":317},[],[64,316],"deep learning",[26,297,64],{"code":74,"score":174,"supported":45,"title":319,"abstract":320,"tags":322},[],[25,321],"smart agriculture",[25],[324,325],"MobileNet-V2 番茄叶片病害","番茄叶病 深度学习 检测","MobileNet-V2番茄叶片病害-5387","10.62441\u002Factainnovations.vi.1918",{"doi":327,"openalex_id":329,"authors":330,"venue":287,"cited_by_count":90,"oa_url":336,"card":337,"direction":95,"ingested_from":219},"W7222977034",[331,333],{"name":332,"orcid":8},"Mrs. Vijetalaxmi A Hegde",{"name":334,"orcid":335},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":338,"method":339,"finding":340,"direction":150,"opportunity":341},"提出轻量注意力多级混合MobileNet-V2框架，融合手工纹理与深度学习特征实现番茄叶片病害早期检","高斯\u002F双边\u002F引导滤波去噪，LAB+CLAHE增强，Otsu分割，LBP与GLCM","所提模型分类性能优于现有模型，可有效用于智慧农业实时番茄叶片病害检测。","可探索多作物跨域泛化、田间复杂光照下轻量模型部署与可解释性，及病害早期分级检测。","2026-10-20T23:30:10.424511Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":348,"content":8,"source_name":349,"source_url":346,"published_at":108,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":350,"score_detail":351,"sources":354,"tags":356,"primary_topic":360,"secondary_topics":364,"classification":370,"search_phrases":412,"slug":415,"view_count":90,"doi":8,"paper":416,"created_at":434},5313,"Real-Time IoT-Integrated Ensemble LSTM–Bi-LSTM Framework for Greenhouse Microclimate Forecasting","https:\u002F\u002Fwasrpublication.com\u002Findex.php\u002Findex\u002Farticle\u002Fview\u002F512","Accurate prediction of greenhouse microclimates is essential for optimizing crop growth and resource utilization in precision agriculture. The research presents an IoT-integrated ensemble deep learning framework for real-time greenhouse microclimate forecasting using Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. Environmental variables, including temperature, light intensity, soil moisture, and humidity, were acquired through IoT sensor nodes deployed in a controlled greenhouse environment. A benchmark greenhouse dataset was first used for model development and hyperparameter optimization, while an original IoT-based dataset collected during cucumber, tomato, and pepper cultivation at the Federal University Wukari, Nigeria, was used for validation and real-world deployment. The data were preprocessed through noise filtering, missing value imputation, Z-score-based outlier removal, and Min–Max normalization. A weighted ensemble strategy was then applied to combine LSTM and Bi-LSTM predictions for improved robustness. Experimental results show that the Bi-LSTM model outperformed the LSTM model, achieving R² = 0.9981, MAE = 0.0088, RMSE = 0.0110, and MSE = 0.0001, compared to LSTM results of R² = 0.9956, MAE = 0.0133, RMSE = 0.0167, and MSE = 0.0003. Statistical validation using paired t-test, Wilcoxon signed-rank test, confidence intervals, and multi-run analysis confirmed that the performance improvement is statistically significant and robust. The proposed framework enables accurate real-time microclimate forecasting and intelligent environmental monitoring, providing a scalable solution for precision greenhouse management, improved crop productivity, optimized energy utilization, and efficient irrigation scheduling.","准确预测温室微气候对于精准农业中优化作物生长和资源利用至关重要。本研究提出了一种集成物联网的集成深度学习框架，利用长短期记忆网络（LSTM）和双向长短期记忆网络（Bi-LSTM）进行实时温室微气候预测。温度、光照强度、土壤湿度和湿度等环境变量通过部署在受控温室环境中的物联网传感器节点采集。研究首先使用基准温室数据集进行模型开发和超参数优化，随后使用在尼日利亚武卡里联邦大学黄瓜、番茄和辣椒种植期间采集的原始物联网数据集进行验证和实际部署。数据经过噪声滤波、缺失值插补、基于Z分数的异常值去除和最小—最大归一化预处理。然后采用加权集成策略融合LSTM和Bi-LSTM的预测结果以提高鲁棒性。实验结果表明，Bi-LSTM模型优于LSTM模型，其R² = 0.9981、MAE = 0.0088、RMSE = 0.0110、MSE = 0.0001，而LSTM的结果为R² = 0.9956、MAE = 0.0133、RMSE = 0.0167、MSE = 0.0003。采用配对t检验、Wilcoxon符号秩检验、置信区间和多轮运行分析进行的统计验证证实，性能提升具有统计显著性和鲁棒性。所提出的框架能够实现准确的实时微气候预测和智能环境监测，为精准温室管理、提高作物生产力、优化能源利用和高效灌溉调度提供了可扩展的解决方案。","World Journal of Multidisciplinary Studies",67,{"impact":291,"substance":112,"depth":352,"authority":44,"freshness":87,"relevant":20,"comment":353},17,"方法扎实、验证充分，但属单点应用研究，公共影响有限，适合作为技术前沿条目而非头条精选。",[355],{"name":349,"url":346},[25,26,357,358,359],"农业物联网","温室环境","小气候预测",{"code":67,"slug":361,"name":362,"path":363,"parent_code":35},"protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture",[365,369],{"code":79,"slug":366,"name":367,"path":368,"parent_code":304},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":371},{"candidates":372,"agricultural_evidence":45},[373,379,385,390,394,398,405],{"code":79,"score":309,"supported":45,"title":374,"abstract":376,"tags":378},[375],"IoT",[377,375],"物联网",[357],{"code":67,"score":380,"supported":45,"title":381,"abstract":383,"tags":384},14,[382],"greenhouse",[71,382],[],{"code":31,"score":44,"supported":45,"title":386,"abstract":387,"tags":389},[],[48,49,50,183,388],"cucumber",[],{"code":74,"score":174,"supported":45,"title":391,"abstract":392,"tags":393},[],[177,178],[25],{"code":61,"score":174,"supported":45,"title":395,"abstract":396,"tags":397},[],[64,316],[26],{"code":399,"score":100,"supported":45,"title":400,"abstract":401,"tags":404},"H2",[],[402,403],"土壤","soil",[],{"code":406,"score":100,"supported":45,"title":407,"abstract":408,"tags":411},"H3",[],[409,410],"灌溉","irrigation",[],[413,414],"温室 小气候 LSTM 预测","尼日利亚 温室 IoT 黄瓜 番茄","温室小气候LSTM预测-5313",{"doi":8,"openalex_id":417,"authors":418,"venue":349,"cited_by_count":90,"oa_url":8,"card":429,"direction":95,"ingested_from":219},"W7222909837",[419,421,423,425,427],{"name":420,"orcid":8},"Siman Emmanuel*",{"name":422,"orcid":8},"Edward Onyebueke Agu",{"name":424,"orcid":8},"Musa Gani",{"name":426,"orcid":8},"Oladunjoye John Abiodun",{"name":428,"orcid":8},"Anagu Emmanuel John",{"tldr":430,"method":431,"finding":432,"direction":95,"opportunity":433},"提出物联网集成LSTM与Bi-LSTM加权集成框架，实时预测温室微气候。","IoT传感器采集温光湿数据，经预处理后用LSTM-Bi-LSTM加权集成建模。","Bi-LSTM优于LSTM，R²达0.9981，统计检验证实性能提升显著稳健。","可探索边缘端轻量化部署与多作物跨温室迁移学习，提升实时预测泛化性。","2026-10-19T23:30:13.295236Z",{"id":436,"title":437,"url":438,"summary":439,"summary_zh":8,"content":8,"source_name":440,"source_url":8,"published_at":441,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":442,"score_detail":443,"sources":445,"tags":447,"primary_topic":450,"secondary_topics":451,"classification":452,"search_phrases":477,"slug":480,"view_count":68,"doi":481,"paper":482,"created_at":489},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":16,"depth":18,"authority":19,"freshness":87,"relevant":20,"comment":444},"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。",[446],{"name":440,"url":438},[25,26,48,448,449],"病害识别","轻量级模型",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":453},{"candidates":454,"agricultural_evidence":45},[455,459,465,469,473],{"code":31,"score":291,"supported":45,"title":456,"abstract":457,"tags":458},[48],[48],[48],{"code":460,"score":68,"supported":45,"title":461,"abstract":462,"tags":464},"A3",[],[463],"玉米",[],{"code":238,"score":68,"supported":45,"title":466,"abstract":467,"tags":468},[],[254],[],{"code":61,"score":186,"supported":13,"title":470,"abstract":471,"tags":472},[],[],[26,448],{"code":74,"score":20,"supported":13,"title":474,"abstract":475,"tags":476},[],[],[25],[478,479],"MambaSeed 番茄叶病","MambaVisionMixer 病害识别","MambaSeed番茄叶病-5301","10.1371\u002Fjournal.pone.0359350",{"doi":481,"openalex_id":8,"authors":483,"venue":8,"cited_by_count":90,"oa_url":8,"card":484,"direction":150,"ingested_from":97},[],{"tldr":485,"method":486,"finding":487,"direction":150,"opportunity":488},"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"]