[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1206":3,"related-1206":88},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":65,"slug":68,"view_count":20,"doi":69,"paper":70,"created_at":87},1206,"DINOv3 meets YOLO26 for enhanced crop-weed detection toward precision vegetable weeding","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112344","DINOv3 meets YOLO26 for enhanced crop-weed detection toward precision vegetable weeding。Computers and Electronics in Agriculture",null,"Computers and Electronics in Agriculture","2026-08-25T00:00:00Z","论文",10,false,65,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},15,18,16,14,2,1,"结合DINOv3与YOLO26提升作物-杂草检测精度，对精准蔬菜除草有实质进展，但时效性较低。",[24],{"name":9,"url":6},[26,27,28,29],"智慧农业","农业人工智能","杂草防控","作物识别",{"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},[43,50,55,60],{"code":31,"score":44,"supported":45,"title":46,"abstract":48,"tags":49},11,true,[47],"vegetable",[47],[],{"code":51,"score":21,"supported":13,"title":52,"abstract":53,"tags":54},"F4",[],[],[28],{"code":56,"score":21,"supported":13,"title":57,"abstract":58,"tags":59},"I1",[],[],[26],{"code":61,"score":21,"supported":13,"title":62,"abstract":63,"tags":64},"I2",[],[],[27],[66,67],"农业人工智能 作物识别 智慧农业 杂草防控","农业人工智能 作物识别","农业人工智能作物识别智慧农业杂草防控-1206","10.1016\u002Fj.compag.2026.112344",{"doi":69,"openalex_id":71,"authors":72,"venue":9,"cited_by_count":79,"oa_url":8,"card":80,"direction":84,"ingested_from":86},"W7204155031",[73,76],{"name":74,"orcid":75},"Boyang Deng","https:\u002F\u002Forcid.org\u002F0009-0001-4582-4375",{"name":77,"orcid":78},"Yuzhen Lu","https:\u002F\u002Forcid.org\u002F0000-0002-3636-1137",0,{"tldr":81,"method":82,"finding":83,"direction":84,"opportunity":85},"结合DINOv3与YOLO26提升蔬菜田间作物与杂草检测精度，助力精准除草。","融合DINOv3视觉Transformer与YOLO26目标检测，用于作物杂草识","DINOv3与YOLO26结合显著提高检测性能，优于单一模型。","农业人工智能与决策模型","可探索轻量化模型部署及多场景泛化，或结合机器人实现实时精准除草。","openalex","2026-09-01T04:03:02.261888Z",{"total":89,"page":21,"page_size":89,"items":90},6,[91,159,259,320,385,430],{"id":92,"title":93,"url":94,"summary":95,"summary_zh":96,"content":8,"source_name":97,"source_url":94,"published_at":98,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":99,"score_detail":100,"sources":104,"tags":106,"primary_topic":110,"secondary_topics":111,"classification":117,"search_phrases":138,"slug":141,"view_count":79,"doi":142,"paper":143,"created_at":158},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":101,"substance":17,"depth":18,"authority":12,"freshness":102,"relevant":21,"comment":103},12,8,"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。",[105],{"name":97,"url":94},[26,27,107,108,109],"深度学习","番茄病害","图像识别",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[112],{"code":61,"slug":113,"name":114,"path":115,"parent_code":116},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":38,"locked":13,"version":39,"method":40,"evidence":118},{"candidates":119,"agricultural_evidence":45},[120,126,132],{"code":31,"score":16,"supported":45,"title":121,"abstract":123,"tags":125},[122],"tomato",[124,122],"番茄",[108],{"code":61,"score":127,"supported":45,"title":128,"abstract":129,"tags":131},9,[],[107,130],"deep learning",[27,109,107],{"code":56,"score":133,"supported":45,"title":134,"abstract":135,"tags":137},7,[],[26,136],"smart agriculture",[26],[139,140],"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":142,"openalex_id":144,"authors":145,"venue":97,"cited_by_count":79,"oa_url":151,"card":152,"direction":157,"ingested_from":86},"W7222977034",[146,148],{"name":147,"orcid":8},"Mrs. Vijetalaxmi A Hegde",{"name":149,"orcid":150},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":153,"method":154,"finding":155,"direction":84,"opportunity":156},"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。","智慧农业 \u002F 农业物联网","2026-10-20T23:30:10.424511Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":164,"content":8,"source_name":165,"source_url":162,"published_at":166,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":167,"score_detail":168,"sources":172,"tags":174,"primary_topic":178,"secondary_topics":183,"classification":190,"search_phrases":236,"slug":239,"view_count":79,"doi":8,"paper":240,"created_at":258},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","2026-10-16T00:00:00Z",67,{"impact":101,"substance":169,"depth":170,"authority":127,"freshness":102,"relevant":21,"comment":171},21,17,"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。",[173],{"name":165,"url":162},[26,27,175,176,177],"农业物联网","温室环境","小气候预测",{"code":179,"slug":180,"name":181,"path":182,"parent_code":35},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture",[184,189],{"code":185,"slug":186,"name":187,"path":188,"parent_code":116},"I5","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":191},{"candidates":192,"agricultural_evidence":45},[193,199,205,212,218,222,229],{"code":185,"score":16,"supported":45,"title":194,"abstract":196,"tags":198},[195],"IoT",[197,195],"物联网",[175],{"code":179,"score":19,"supported":45,"title":200,"abstract":202,"tags":204},[201],"greenhouse",[203,201],"温室",[],{"code":31,"score":127,"supported":45,"title":206,"abstract":207,"tags":211},[],[124,208,209,122,210],"辣椒","黄瓜","cucumber",[],{"code":56,"score":133,"supported":45,"title":213,"abstract":214,"tags":217},[],[215,216],"精准农业","precision agriculture",[26],{"code":61,"score":133,"supported":45,"title":219,"abstract":220,"tags":221},[],[107,130],[27],{"code":223,"score":89,"supported":45,"title":224,"abstract":225,"tags":228},"H2",[],[226,227],"土壤","soil",[],{"code":230,"score":89,"supported":45,"title":231,"abstract":232,"tags":235},"H3",[],[233,234],"灌溉","irrigation",[],[237,238],"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":241,"authors":242,"venue":165,"cited_by_count":79,"oa_url":8,"card":253,"direction":157,"ingested_from":86},"W7222909837",[243,245,247,249,251],{"name":244,"orcid":8},"Siman Emmanuel*",{"name":246,"orcid":8},"Edward Onyebueke Agu",{"name":248,"orcid":8},"Musa Gani",{"name":250,"orcid":8},"Oladunjoye John Abiodun",{"name":252,"orcid":8},"Anagu Emmanuel John",{"tldr":254,"method":255,"finding":256,"direction":157,"opportunity":257},"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":260,"title":261,"url":262,"summary":263,"summary_zh":8,"content":8,"source_name":264,"source_url":8,"published_at":265,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":266,"score_detail":267,"sources":271,"tags":273,"primary_topic":276,"secondary_topics":277,"classification":278,"search_phrases":306,"slug":309,"view_count":287,"doi":310,"paper":311,"created_at":319},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":17,"substance":268,"depth":17,"authority":269,"freshness":102,"relevant":21,"comment":270},22,13,"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。",[272],{"name":264,"url":262},[26,27,124,274,275],"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":279},{"candidates":280,"agricultural_evidence":45},[281,285,292,298,302],{"code":31,"score":101,"supported":45,"title":282,"abstract":283,"tags":284},[124],[124],[124],{"code":286,"score":287,"supported":45,"title":288,"abstract":289,"tags":291},"A3",3,[],[290],"玉米",[],{"code":293,"score":287,"supported":45,"title":294,"abstract":295,"tags":297},"A5",[],[296],"马铃薯",[],{"code":61,"score":20,"supported":13,"title":299,"abstract":300,"tags":301},[],[],[27,274],{"code":56,"score":21,"supported":13,"title":303,"abstract":304,"tags":305},[],[],[26],[307,308],"MambaSeed 番茄叶病","MambaVisionMixer 病害识别","MambaSeed番茄叶病-5301","10.1371\u002Fjournal.pone.0359350",{"doi":310,"openalex_id":8,"authors":312,"venue":8,"cited_by_count":79,"oa_url":8,"card":313,"direction":84,"ingested_from":318},[],{"tldr":314,"method":315,"finding":316,"direction":84,"opportunity":317},"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。","agent","2026-10-19T00:07:48.589614Z",{"id":321,"title":322,"url":323,"summary":324,"summary_zh":325,"content":8,"source_name":326,"source_url":323,"published_at":327,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":328,"score_detail":329,"sources":332,"tags":334,"primary_topic":336,"secondary_topics":337,"classification":339,"search_phrases":356,"slug":359,"view_count":21,"doi":360,"paper":361,"created_at":384},4494,"Tomato ripeness classification with weight-based and texture-adaptive pooling in CNNs","https:\u002F\u002Fdoi.org\u002F10.64960\u002Feasr.2026.266223","This research introduces a weight-based mixed pooling and adaptive fuzzy pooling mechanism based on feature map texture analysis for attention mechanism Squeeze-and-Excitation Networks (SE) and Convolutional Neural Networks (CNNs) in tomato ripeness classification. Traditional CNNs and SE networks rely on deterministic pooling strategies that can be suboptimal for capturing diverse visual features such as texture and color gradients in fruit. A novel fuzzy pooling system is proposed that dynamically adjusts the fusion ratio of min and max pooling based on real-time texture analysis of feature maps via a Laplacian filter. This mechanism was integrated into Darknet53, ResNet34, and ResNet101 architectures, both directly and within the SE attention block. The method was evaluated on a five-class tomato ripeness dataset using 10-fold cross-validation against traditional and fixed-weight pooling methods. The fuzzy and mixed pooling approach demonstrated superior performance on certain models which include ESEnet: Darknet53 + SE (Fuzzy pool) achieved an average F1 score across folds of 0.8429, outperforming Darknet53 + baseline SE (Average pool) at 0.8350; Extended Net: ResNet34 + Fuzzy pool achieved an average F1 score across folds of 0.8305, outperforming baseline ResNet34 at 0.8130 and ResNet101 + Fuzzy pool achieved an average F1 score across folds of 0.8284, outperforming baseline ResNet101 at 0.8267. This improvement was realized with minimal increase in computational overhead. Specifically, measurements of model parameters (M) and FLOPs (GMACs) showed only a slight increase across all architectures after integrating SEnet into the system, and zero increase after integrating the Laplacian filter and fuzzy logic. The study concludes that logic-based adaptive pooling is a robust strategy that improves feature representation in CNNs, achieving a balance between classification accuracy and computational cost. These findings offer practical value for developing more reliable automated harvesting systems and provide a generalizable enhancement for a wide range of computer vision classification tasks.","本研究提出了一种基于特征图纹理分析的权重混合池化与自适应模糊池化机制，用于番茄成熟度分类中的注意力机制挤压激励网络（Squeeze-and-Excitation Networks, SE）和卷积神经网络（Convolutional Neural Networks, CNNs）。传统的CNN和SE网络依赖确定性池化策略，在捕捉果实纹理和颜色梯度等多样化视觉特征时可能并非最优。本文提出了一种新颖的模糊池化系统，通过拉普拉斯滤波器对特征图进行实时纹理分析，动态调整最小池化和最大池化的融合比例。该机制被集成到Darknet53、ResNet34和ResNet101架构中，既可直接集成，也可嵌入SE注意力模块内。该方法在五类番茄成熟度数据集上采用10折交叉验证，与传统池化及固定权重池化方法进行了对比评估。模糊池化和混合池化方法在部分模型上表现出优越性能，包括：ESEnet：Darknet53 + SE（模糊池化）在各折上的平均F1得分为0.8429，优于Darknet53 + 基线SE（平均池化）的0.8350；扩展网络：ResNet34 + 模糊池化在各折上的平均F1得分为0.8305，优于基线ResNet34的0.8130；ResNet101 + 模糊池化在各折上的平均F1得分为0.8284，优于基线ResNet101的0.8267。这一改进仅带来了极小的计算开销增加。具体而言，模型参数量（M）和浮点运算次数（GMACs）的测量结果表明，将SEnet集成到系统后所有架构仅有轻微增加，而集成拉普拉斯滤波器和模糊逻辑后则无任何增加。研究结论认为，基于逻辑的自适应池化是一种鲁棒策略，能够改善CNN中的特征表示，在分类精度和计算成本之间实现平衡。这些发现为开发更可靠的自动化收获系统提供了实用价值，并为广泛的计算机视觉分类任务提供了一种可推广的增强方法。","Engineering and Applied Science Research","2026-10-07T00:00:00Z",66,{"impact":102,"substance":330,"depth":170,"authority":101,"freshness":127,"relevant":21,"comment":331},20,"提出基于纹理自适应模糊池化的CNN改进方法，在番茄成熟度分类上取得小幅但稳定的F1提升且算力开销几乎不增，对自动采摘与农业视觉识别有参考价值，但属细分方法类论文，影响面有限。",[333],{"name":326,"url":323},[26,27,124,109,335],"自动采摘",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[338],{"code":61,"slug":113,"name":114,"path":115,"parent_code":116},{"status":38,"locked":13,"version":39,"method":40,"evidence":340},{"candidates":341,"agricultural_evidence":45},[342,346,352],{"code":31,"score":16,"supported":45,"title":343,"abstract":344,"tags":345},[122],[124,122],[124],{"code":61,"score":102,"supported":45,"title":347,"abstract":348,"tags":351},[],[349,350],"计算机视觉","computer vision",[27,109],{"code":56,"score":21,"supported":13,"title":353,"abstract":354,"tags":355},[],[],[26],[357,358],"番茄 成熟度 分类 卷积神经网络","Darknet53 ResNet 番茄 成熟度","番茄成熟度分类卷积神经网络-4494","10.64960\u002Feasr.2026.266223",{"doi":360,"openalex_id":362,"authors":363,"venue":326,"cited_by_count":79,"oa_url":378,"card":379,"direction":157,"ingested_from":86},"W7220840158",[364,366,368,370,373,375],{"name":365,"orcid":8},"Rut Yatigul",{"name":367,"orcid":8},"Wisanu Jitviriya",{"name":369,"orcid":8},"Eiji Hayashi",{"name":371,"orcid":372},"Aran Blattler","https:\u002F\u002Forcid.org\u002F0000-0002-8684-6239",{"name":374,"orcid":8},"Watcharin Tangsuksant",{"name":376,"orcid":377},"Teppakorn Sittiwanchai","https:\u002F\u002Forcid.org\u002F0000-0001-9653-8750","https:\u002F\u002Fph01.tci-thaijo.org\u002Findex.php\u002Feasr\u002Farticle\u002Fdownload\u002F266223\u002F176569",{"tldr":380,"method":381,"finding":382,"direction":84,"opportunity":383},"提出基于纹理自适应模糊池化机制，提升CNN番茄成熟度分类性能。","用Laplacian滤波分析特征图纹理，动态调整最大最小池化融合比，集成到Dar","模糊池化在多个模型上F1提升，且计算开销几乎不增加。","可探索自适应池化在其它果蔬成熟度或田间复杂光照下的泛化能力。","2026-10-09T23:30:09.993787Z",{"id":386,"title":387,"url":388,"summary":389,"summary_zh":8,"content":390,"source_name":391,"source_url":8,"published_at":392,"category":393,"cover_url":8,"hotness":12,"is_selected":13,"score":394,"score_detail":395,"sources":397,"tags":399,"primary_topic":403,"secondary_topics":404,"classification":406,"search_phrases":425,"slug":428,"view_count":20,"doi":8,"paper":8,"created_at":429},4459,"中国农科院环发所构建知识与数据双驱动模型精准预测温室番茄生长态势","https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572492.shtm","中国农业科学院农业环境与可持续发展研究所设施植物环境工程创新团队以番茄为对象，构建知识与数据双驱动的尺度自适应时序卷积混合模型，根据番茄不同生育期动态调整时序特征提取尺度，结合机理模型合成数据预训练与生理阈值约束，实现番茄不同器官干物质及叶面积指数的精准预测；研究成果发表在Computers and Electronics in Agriculture；仅依靠常规温室环境数据即可无损估算生长态势，对推动温室智能环控、产量预测具重要应用价值。","[![Image 1: 科学网新闻频道](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Fnews.jpg)](https:\u002F\u002Fnews.sciencenet.cn\u002F)\n\n[生命科学](https:\u002F\u002Fwww.sciencenet.cn\u002Flife\u002F) | [医学科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fmedicine\u002F) | [化学科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fchemistry\u002F) | [工程材料](https:\u002F\u002Fwww.sciencenet.cn\u002Fmaterial\u002F) | [信息科学](https:\u002F\u002Fwww.sciencenet.cn\u002Finformation\u002F) | [地球科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fearth\u002F) | [数理科学](https:\u002F\u002Fwww.sciencenet.cn\u002Fmathematics\u002F) | [管理综合](https:\u002F\u002Fwww.sciencenet.cn\u002Fpolicy\u002F)[站内规定](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-45-1064777.html) | [手机版](https:\u002F\u002Fwap.sciencenet.cn\u002F)\n\n[首页](https:\u002F\u002Fwww.sciencenet.cn\u002F) | [新闻](https:\u002F\u002Fnews.sciencenet.cn\u002F) | [博客](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php) | [院士](https:\u002F\u002Fnews.sciencenet.cn\u002Fys\u002F) | [人才](https:\u002F\u002Ftalent.sciencenet.cn\u002F) | [会议](https:\u002F\u002Fmeeting.sciencenet.cn\u002F) | [基金·项目](https:\u002F\u002Ffund.sciencenet.cn\u002F) | [论文](https:\u002F\u002Fpaper.sciencenet.cn\u002F) | [绘图](https:\u002F\u002Fvisual-web.sciencenet.cn\u002F) | [视频·直播](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php?mod=video) | [小柯机器人](https:\u002F\u002Fpaper.sciencenet.cn\u002FAInews) | [医学科普](https:\u002F\u002Fyxkp.sciencenet.cn\u002F)\n\n作者：李晨,王佳 来源：中国科学报 发布时间：2026\u002F10\u002F4 22:09:23 选择字号：小 中 大 双驱动模型可精准预测温室番茄生长态势 近日，中国农业科学院农业环境与可持续发展研究所设施植物环境工程创新团队构建了知识与数据双驱动模型，实现温室番茄生长的高精度无损预测，相关研究成果发表在《农业计算机与电子学》（_**Computers and Electronics in Agriculture**_）上。 作物生长精准估算是温室智能控制的核心前提。然而，传统机理模型参数获取难、泛化有限，而纯数据驱动模型常因缺乏生理约束致预测失真。因此，如何融合环境时序数据与作物生长规律，实现高精度且生理合理的生长预测仍是关键挑战。 科研团队以番茄为对象，提出一种知识与数据双驱动的尺度自适应时序卷积混合模型。该模型根据番茄不同生育期动态调整时序特征提取尺度，结合机理模型合成数据预训练与生理阈值约束，实现番茄不同器官干物质及叶面积指数的精准预测。该模型依靠常规温室环境数据即可无损估算生长态势，对推动温室智能环控、产量预测具有重要应用价值。 相关论文信息：https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112281 版权声明：凡本网注明“来源：中国科学报、科学网、科学新闻杂志”的所有作品，网站转载，请在正文上方注明来源和作者，且不得对内容作实质性改动；微信公众号、头条号等新媒体平台，转载请联系授权。邮箱：shouquan@stimes.cn。\n\n打印 发E-mail给：\n\n以下评论只代表网友个人观点，不代表科学网观点。\n\n 无标题页 \n\n[![Image 2](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Fnewcomm.gif)](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtml\u002Fcomment.aspx?id=572492)\n\n相关新闻 相关论文\n*   1\n*   [《科学》（20261001出版）一周论文导读](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572487.shtm)\n\n*   2\n*   [2026年度湖南省科学技术奖提名工作启动](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572486.shtm)\n\n*   3\n*   [河南中央引导地方科技发展资金项目结项验收结果公示](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572485.shtm)\n\n*   4\n*   [江西组织开展2027年度自然科学基金项目申报工作](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572484.shtm)\n\n*   5\n*   [中国人民大学收到一校友捐资5.03亿](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572483.shtm)\n\n*   6\n*   [2026年度辽宁省科学技术奖提名工作启动](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572482.shtm)\n\n*   7\n*   [北京市自然科学基金资助项目验收结论公布](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572481.shtm)\n\n*   8\n*   [湖北省科技计划项目2026年第六批验收结果公示](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572480.shtm)\n\n*   1\n*   [草酸二甲酯加氢催化剂研究：解锁三类高价值化学品定向合成](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F202610318254299156239.shtm)\n\n*   2\n*   [杨孟昊研究员：人工智能赋能能源材料研究——从经典机器学习到大模型的技术演进与应用](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F2026103174511786156238.shtm)\n\n*   3\n*   [西北工业大学卢乾波教授：系统梳理压电驱动器种类，为其应用提供“知识地图”](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F202610317332521156234.shtm)\n\n*   4\n*   [异辛醇氧化工艺优化：混合建模策略实现节能降碳双提升](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F202610316823146156233.shtm)\n\n*   5\n*   [从物理智能到分子设计：跨尺度机制学习推动药物发现](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F202610316233349156232.shtm)\n\n*   6\n*   [流场+磁场双驱动—等离子体固氮技术](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F2026103151851943156231.shtm)\n\n*   7\n*   [根际细菌的“生化部队”能让植物更耐旱吗？](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F2026103105344865156230.shtm)\n\n*   8\n*   [从4000小时到更长寿命：解密PEM电解槽多孔传输层的设计哲学与产业博弈](https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F2026101231244224156228.shtm)\n\n[图片新闻](https:\u002F\u002Fnews.sciencenet.cn\u002Fimgnews.aspx)\n\n[![Image 3: 他们为二维滑移铁电体装原子层“方向盘”](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F10\u002F20261061524217710.png)](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572520.shtm)[![Image 4: 这种紫花苜蓿新种质可同时耐受两种除草剂](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F10\u002F2026104223520990.jpg)](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F572493.shtm)\n[![Image 5: “鹏城首发星”成功入轨](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F9\u002F20269231515219900.png)](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F9\u002F571953.shtm)[![Image 6: 研究揭示甲烷部分氧化制合成气驱动因素](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fupload\u002Fnews\u002Fimages\u002F2026\u002F9\u002F2026917125225680.jpg)](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F9\u002F571610.shtm)\n[>>更多](https:\u002F\u002Fnews.sciencenet.cn\u002Fimgnews.aspx)\n\n[一周新闻排行](https:\u002F\u002Fnews.sciencenet.cn\u002Fzphnews.aspx)\n*   1\n*   [2026年诺贝尔生理学或医学奖揭晓！](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572511.shtm)\n\n*   2\n*   [刚刚，2026年诺贝尔物理奖揭晓！](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572524.shtm)\n\n*   3\n*   [刚刚，2026年诺贝尔化学奖揭晓！](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572558.shtm)\n\n*   4\n*   [中国学者创立新体系被增设进入IFAC十二大技术领域](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572427.shtm)\n\n*   5\n*   [直播回放｜2026诺贝尔物理学奖解读](https:\u002F\u002Fnews.sciencenet.cn\u002Fhttps:\u002F\u002Fweibo.com\u002Fl\u002Fwblive\u002Fp\u002Fshow\u002F1022:2321325346726952435780)\n\n*   6\n*   [诺贝尔物理学奖揭晓在即：凝聚态物理研究受关注](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572459.shtm)\n\n*   7\n*   [施郁：今年诺贝尔物理学奖，我为何看好他们](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572473.shtm)\n\n*   8\n*   [美国白蛾大暴发，北京释放11亿头“天敌”！](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572445.shtm)\n\n*   9\n*   [诺贝尔生理学或医学奖今年花落谁家？](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572448.shtm)\n\n*   10\n*   [华人物理学家叶军获“诺奖风向标”沃尔夫物理学奖](https:\u002F\u002Fnews.sciencenet.cn\u002F\u002Fhtmlnews\u002F2026\u002F10\u002F572453.shtm)\n\n[编辑部推荐博文](http:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php?mod=recommend)\n*   ![Image 7](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [封面文章|《水生生物学报》：微藻蛋白的研究进展](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-45-1554679.html)\n\n*   ![Image 8](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [科学网2026年8月十佳博文榜单公布！](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-45-1551789.html)\n\n*   ![Image 9](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [化学反应中的“神奇效应”](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-3380716-1555615.html)\n\n*   ![Image 10](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [主流同行评审模式盘点，投稿前没了解清楚？难怪初审总出状况](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-3574014-1555614.html)\n\n*   ![Image 11](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [柔性电子重塑未来科技形态](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-3496796-1555605.html)\n\n*   ![Image 12](https:\u002F\u002Fnews.sciencenet.cn\u002Fimages\u002Ft11.gif)\n*   [即将截止 | 填写问卷，告诉我们您对选刊工具的使用偏好，更有机会获得 ...](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog-3411312-1555592.html)\n\n*   [更多>>](https:\u002F\u002Fblog.sciencenet.cn\u002Fblog.php?mod=recommend)\n\n[关于我们](http:\u002F\u002Fwww.sciencenet.cn\u002Faboutus.aspx) | [网站声明](http:\u002F\u002Fwww.sciencenet.cn\u002Fshengming.aspx) | [服务条款](http:\u002F\u002Fwww.sciencenet.cn\u002Ftiaokuang.aspx) | [联系方式](http:\u002F\u002Fwww.sciencenet.cn\u002Fcontact.aspx) | [举报](https:\u002F\u002Fwww.sciencenet.cn\u002Fjubao.aspx) | [中国科学报社](https:\u002F\u002Fstimes.sciencenet.cn\u002F)  \n[京ICP备07017567号-12](http:\u002F\u002Fwww.beian.miit.gov.cn\u002F)互联网新闻信息服务许可证10120230008 京公网安备 11010802032783  \nCopyright @ 2007-2026 中国科学报社 All Rights Reserved  \n地址：北京市海淀区中关村南一条乙三号 电话：010-62580783","科学网 中国农业科学院 2026-10-04","2026-10-04T00:00:00Z","报道",80,{"impact":268,"substance":169,"depth":170,"authority":19,"freshness":89,"relevant":21,"comment":396},"国家级科研机构在智慧农业领域的模型方法突破，方法新颖、结论可靠，对温室智能环控与产量预测有应用价值，值得进入每日精选。",[398],{"name":391,"url":388},[26,27,400,401,402],"作物生长模型","设施番茄","温室环控",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[405],{"code":179,"slug":180,"name":181,"path":182,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":407},{"candidates":408,"agricultural_evidence":45},[409,413,417,421],{"code":31,"score":101,"supported":45,"title":410,"abstract":411,"tags":412},[124],[124],[401],{"code":179,"score":44,"supported":45,"title":414,"abstract":415,"tags":416},[203],[203],[],{"code":61,"score":20,"supported":13,"title":418,"abstract":419,"tags":420},[],[],[400,27],{"code":56,"score":21,"supported":13,"title":422,"abstract":423,"tags":424},[],[],[26],[426,427],"中国农科院环发所 温室番茄 生长预测","知识与数据双驱动 番茄 干物质","中国农科院环发所温室番茄生长预测-4459","2026-10-09T00:04:56.060677Z",{"id":431,"title":432,"url":433,"summary":434,"summary_zh":435,"content":8,"source_name":436,"source_url":433,"published_at":327,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":437,"score_detail":438,"sources":440,"tags":442,"primary_topic":446,"secondary_topics":447,"classification":448,"search_phrases":467,"slug":470,"view_count":79,"doi":471,"paper":472,"created_at":489},4417,"CuFormer U-Net: a transformer-enhanced multi-task network for cucumber leaf disease detection and segmentation","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1975030","Cucumber foliar symptoms reduce functional leaf area and complicate greenhouse scouting. This study presents CuFormer U-Net, a Transformer-enhanced multi-task network for three-class image-level classification on the 3,754-image Kaggle benchmark (healthy, powdery mildew, and downy mildew) and binary visible-symptom segmentation on a separate 400-image greenhouse cohort (200 healthy and 200 affected leaves). The greenhouse annotations comprise 2,705 rectangles (1,741 color-abnormality and 964 tissue-damage instances); rectangle-seeded lesion masks were manually refined for the dense-prediction experiments. The reported fixed-split point estimates were 96.7% accuracy, 96.3% macro precision, 95.8% macro recall, and 96.0% macro F1 for classification, and 92.4% mean image-wise Dice, 83.1% macro IoU, 93.2% foreground precision, and 91.7% foreground recall for segmentation. The complete internal-validation ablation configuration reached 93.1% Dice and 87.3% IoU. The available experiment archive does not contain independent-seed reruns, per-image predictions for inferential testing, annotator-level masks, quantitative results for the separate 100-image greenhouse stress-test cohort, or reproducible hardware profiling. Accordingly, all between-model differences are interpreted descriptively, the external cohort is not presented as formal external validation, and robustness and deployment claims have been moderated. CuFormer U-Net provides a technically motivated basis for joint recognition and spatial characterization, but confirmatory multi-run and multi-site evaluation is required. boundary refinement, cucumber leaf disease, multi-task learning, plant disease, precision agriculture, semantic segmentation, vision transformer","黄瓜叶片症状会减少有效叶面积，并增加温室巡查的难度。本研究提出CuFormer U-Net，这是一种经Transformer增强的多任务网络，用于在包含3，754张图像的Kaggle基准数据集上进行三类图像级分类（健康、白粉病和霜霉病），并在一个独立的包含400张图像的温室队列（200张健康叶片和200张受影响叶片）上进行二值可见症状分割。温室标注包含2，705个矩形框（1，741个颜色异常实例和964个组织损伤实例）；用于密集预测实验的矩形框种子病灶掩膜经过人工精修。所报告的固定划分点估计结果为：分类任务准确率96.7%、宏平均精确率96.3%、宏平均召回率95.8%、宏平均F1值96.0%；分割任务平均图像级Dice系数92.4%、宏平均IoU 83.1%、前景精确率93.2%、前景召回率91.7%。完整的内部验证消融配置达到Dice 93.1%和IoU 87.3%。现有实验档案不包含独立随机种子重跑、用于推断性检验的逐图像预测、标注者级别掩膜、针对独立100张图像温室压力测试队列的定量结果，或可复现的硬件性能分析。因此，所有模型间差异均以描述性方式解释，外部队列不作为正式外部验证呈现，稳健性和部署相关主张也已作审慎表述。CuFormer U-Net为联合识别与空间表征提供了具有技术依据的基础，但仍需开展验证性多轮次和多站点评估。边界精修、黄瓜叶部病害、多任务学习、植物病害、精准农业、语义分割、视觉Transformer","Frontiers in Plant Science",73,{"impact":16,"substance":330,"depth":170,"authority":269,"freshness":102,"relevant":21,"comment":439},"方法新颖、数据与指标披露充分且自我限定严谨，但属单作物单场景研究，产业影响有限，适合作为技术类精选。",[441],{"name":436,"url":433},[26,27,443,444,445],"植物病害识别","图像分割","黄瓜种植",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":449},{"candidates":450,"agricultural_evidence":45},[451,455,459,463],{"code":31,"score":19,"supported":45,"title":452,"abstract":453,"tags":454},[210],[209,210],[],{"code":56,"score":133,"supported":45,"title":456,"abstract":457,"tags":458},[],[215,216],[26],{"code":179,"score":89,"supported":45,"title":460,"abstract":461,"tags":462},[],[203,201],[],{"code":61,"score":287,"supported":13,"title":464,"abstract":465,"tags":466},[],[],[27,444,443],[468,469],"CuFormer U-Net 黄瓜叶部病害","黄瓜 霜霉病 白粉病 识别","CuFormerU-Net黄瓜叶部病害-4417","10.3389\u002Ffpls.2026.1975030",{"doi":471,"openalex_id":473,"authors":474,"venue":436,"cited_by_count":79,"oa_url":482,"card":483,"direction":157,"ingested_from":86},"W7220838309",[475,478,480],{"name":476,"orcid":477},"Batyrkhan Omarov","https:\u002F\u002Forcid.org\u002F0000-0002-8341-7113",{"name":479,"orcid":8},"Sayat Ibrayev",{"name":481,"orcid":8},"Nurbibi Imanbayeva","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1975030\u002Fpdf",{"tldr":484,"method":485,"finding":486,"direction":487,"opportunity":488},"提出CuFormer U-Net多任务网络，同时实现黄瓜叶病分类与病斑分割。","Transformer增强U-Net，用Kaggle 3754图分类和400图温","分类准确率96.7%，分割Dice 92.4%，但缺独立重复与外部验证。","农业遥感与作物表型","需多轮多站点验证，并补全外部压力测试与可复现部署评估。","2026-10-08T23:30:09.461430Z"]