[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2805":3,"related-2805":120},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":49,"search_phrases":89,"slug":92,"view_count":93,"doi":94,"paper":95,"created_at":119},2805,"Synergistic effects of spectral preprocessing and machine learning algorithms for nitrogen estimation in tomato using hyperspectral spectral data","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-71908-1","Abstract Accurate estimation of leaf nitrogen content is essential for optimizing fertilization management and improving crop productivity. This study proposes a nondestructive hyperspectral imaging framework combined with advanced machine learning algorithms to classify nitrogen levels in tomato leaves (Solanum lycopersicum L., Royal variety). A total of 300 hyperspectral samples were collected from plants subjected to three nitrogen treatments (N-30%, N-60%, and N-90%) under controlled conditions. Reflectance data (400–1000 nm) were calibrated and preprocessed using Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Savitzky–Golay (SG) filtering. Both unsupervised and supervised algorithms were systematically evaluated. Clustering results demonstrated that preprocessing substantially influenced class separability. The MSC + GMM combination yielded the best unsupervised results, with the lowest Davies–Bouldin index (0.443) and the highest silhouette coefficient (0.975), indicating improved cluster compactness and separation. In supervised learning, Neural Networks (NN) consistently outperformed the other models, achieving 100% accuracy and an ROC–AUC of 1.00 under SNV, MSC, and SG preprocessing. Gradient Boosting (GB) and Support Vector Machine (SVM) also demonstrated strong predictive capability, whereas conventional models, including LDA, LR, KNN, and NB, showed moderate improvements following preprocessing. Statistical analysis confirmed the significant effect of spectral preprocessing on both clustering and classification outcomes ( p \u003C 0.05). Overall, integrating hyperspectral imaging with appropriate preprocessing and nonlinear machine learning models provided strong classification performance under the controlled experimental conditions. However, the exceptionally high performance observed for some models should be interpreted cautiously because of the relatively small dataset and experimentally controlled nitrogen treatments. Moreover, the absence of an independent external validation dataset limits the assessment of generalizability across growing conditions, cultivars, and field environments. Therefore, independent validation using larger and more diverse datasets is required before broader application of the proposed framework in practical precision agriculture.","摘要 准确估算叶片氮含量对于优化施肥管理和提高作物生产力至关重要。本研究提出了一种无损高光谱成像框架，结合先进的机器学习算法对番茄叶片（Solanum lycopersicum L.，Royal品种）的氮水平进行分类。在受控条件下，从接受三种氮处理（N-30%、N-60%和N-90%）的植株中共采集了300个高光谱样本。反射率数据（400–1000 nm）经标准正态变量变换（SNV）、多元散射校正（MSC）和Savitzky–Golay（SG）滤波进行校准和预处理。系统评估了无监督和有监督算法。聚类结果表明，预处理对类别可分性产生了显著影响。MSC + GMM组合取得了最佳无监督结果，具有最低的Davies–Bouldin指数（0.443）和最高的轮廓系数（0.975），表明聚类紧密度和分离度得到改善。在有监督学习中，神经网络（NN）始终优于其他模型，在SNV、MSC和SG预处理下均达到100%的准确率和1.00的ROC–AUC。梯度提升（GB）和支持向量机（SVM）也表现出较强的预测能力，而传统模型（包括LDA、LR、KNN和NB）在预处理后表现出中等程度的改善。统计分析证实了光谱预处理对聚类和分类结果均有显著影响（p \u003C 0.05）。总体而言，将高光谱成像与适当的预处理及非线性机器学习模型相结合，在受控实验条件下提供了较强的分类性能。然而，由于数据集相对较小且氮处理为实验受控条件，某些模型所表现出的极高性能应谨慎解读。此外，缺乏独立的外部验证数据集限制了对跨生长条件、品种和田间环境泛化能力的评估。因此，在将该框架广泛应用于实际精准农业之前，需要使用更大规模、更多样化的数据集进行独立验证。",null,"Scientific Reports","2026-09-17T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":13,"relevant":21,"comment":22},15,21,17,14,1,"高光谱结合机器学习实现番茄叶片氮素无损估测，方法系统、结论明确，但样本量小且缺乏外部验证，属细分领域方法学进展。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","精准施肥","番茄种植","高光谱遥感",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[38,44],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":50,"locked":14,"version":51,"method":52,"evidence":53},"classified","2026-10-22.2","rules",{"candidates":54,"agricultural_evidence":56},[55,62,68,74,82],{"code":32,"score":17,"supported":56,"title":57,"abstract":59,"tags":61},true,[58],"tomato",[60,58],"番茄",[29],{"code":39,"score":17,"supported":56,"title":63,"abstract":65,"tags":67},[64],"machine learning",[66,64],"机器学习",[27],{"code":45,"score":69,"supported":56,"title":70,"abstract":72,"tags":73},12,[71],"hyperspectral",[71],[30],{"code":75,"score":76,"supported":56,"title":77,"abstract":78,"tags":81},"F3",7,[],[79,80],"施肥","fertilization",[28],{"code":83,"score":76,"supported":56,"title":84,"abstract":85,"tags":88},"I1",[],[86,87],"精准农业","precision agriculture",[26],[90,91],"农业人工智能 高光谱遥感 智慧农业 番茄种植","农业人工智能 高光谱遥感","农业人工智能高光谱遥感智慧农业番茄种植-2805",2,"10.1038\u002Fs41598-026-71908-1",{"doi":94,"openalex_id":96,"authors":97,"venue":10,"cited_by_count":110,"oa_url":6,"card":111,"direction":117,"ingested_from":118},"W7213472002",[98,101,104,107],{"name":99,"orcid":100},"Mohammad Vahedi Torshizi","https:\u002F\u002Forcid.org\u002F0000-0003-3648-1515",{"name":102,"orcid":103},"Sajad Sabzi","https:\u002F\u002Forcid.org\u002F0000-0003-2439-5329",{"name":105,"orcid":106},"Mohsen Azadbakht","https:\u002F\u002Forcid.org\u002F0000-0002-5726-9321",{"name":108,"orcid":109},"Razieh Pourdarbani","https:\u002F\u002Forcid.org\u002F0000-0003-0766-8305",0,{"tldr":112,"method":113,"finding":114,"direction":115,"opportunity":116},"用高光谱成像结合预处理与机器学习，对番茄叶片氮素水平进行分类。","300个高光谱样本，SNV、MSC、SG预处理，聚类与多种监督分类算法对比。","MSC+GMM聚类最优，神经网络在三种预处理下均达100%准确率。","农业遥感与作物表型","样本少且无外部验证，可扩展多品种、多环境田间数据并做独立验证以提升泛化性。","农业人工智能与决策模型","openalex","2026-09-17T23:30:59.361085Z",{"total":121,"page":21,"page_size":121,"items":122},6,[123,245,311,363,458,509],{"id":124,"title":125,"url":126,"summary":127,"summary_zh":128,"content":9,"source_name":129,"source_url":126,"published_at":130,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":131,"score_detail":132,"sources":137,"tags":139,"primary_topic":142,"secondary_topics":143,"classification":146,"search_phrases":224,"slug":227,"view_count":93,"doi":228,"paper":229,"created_at":244},1299,"Remote Sensing and Machine Learning for Futuristic Horticulture: A Comprehensive Review","https:\u002F\u002Fdoi.org\u002F10.25125\u002Fijoear-aug-2026-26","Horticultural crops—fruits, vegetables, plantation crops, flowers, spices and medicinal plants—form the nutritional and economic backbone of India's agricultural sector. However, they face persistent challenges of yield variability, water and nutrient inefficiency, pest and disease pressure and post-harvest losses. This review synthesises the transformative role of Remote Sensing (RS) and Machine Learning (ML) in enabling futuristic, sustainable and precision horticulture. The evolution of agricultural production systems from Agriculture 1.0 to Agriculture 5.0 is traced, followed by a comprehensive discussion of RS principles, elements, four fundamental resolutions (spatial, spectral, temporal, radiometric), and multi-platform architectures (satellite, aerial, UAV, ground-based). A parallel taxonomy of ML—supervised, semi-supervised, unsupervised, reinforcement and deep-learning frameworks—is presented, with emphasis on Random Forest, Support Vector Machine, XGBoost, and Convolutional Neural Network algorithms most widely applied to horticultural datasets. Five representative case studies are analysed in depth: (i) UAV multispectral + ensemble learning for leaf nitrogen monitoring in custard apple; (ii) hyperspectral + ANN \u002F RF \u002F DT models for mango and strawberry fruit-quality parameters; (iii) UAV-hyperspectral detection of citrus canker; (iv) machine-learning-based crop recommendation under NPK, pH and climatic variables; and (v) RS + GIS soil-site suitability for six major fruit crops in the Ganjigatti sub-watershed, Karnataka. National platforms such as CHAMAN, Bhoonidhi, Bhuvan and PMFBY are reviewed as operational demonstrations of the RS + ML value chain. Finally, technical, economic and ethical challenges—ground-truth scarcity, sensor cost, model interpretability, digital divide and data privacy—are discussed, and a way forward for Indian horticulture in the Agriculture 5.0 era is proposed.","园艺作物——包括水果、蔬菜、种植园作物、花卉、香料及药用植物——构成了印度农业部门营养与经济的基础。然而，它们持续面临产量波动、水资源与养分利用效率低下、病虫害压力以及采后损失等挑战。本综述综合探讨了遥感（Remote Sensing, RS）与机器学习（Machine Learning, ML）在推动未来化、可持续及精准园艺中的变革性作用。文章追溯了农业生产系统从农业1.0到农业5.0的演进历程，随后全面讨论了遥感的基本原理、要素、四种基本分辨率（空间、光谱、时间、辐射）以及多平台架构（卫星、航空、无人机、地面）。同时，提出了机器学习的并行分类体系——监督学习、半监督学习、无监督学习、强化学习及深度学习框架，并重点介绍了最广泛应用于园艺数据集的随机森林、支持向量机、XGBoost和卷积神经网络算法。文章深入分析了五个代表性案例研究：（i）基于无人机多光谱与集成学习对番荔枝叶片氮素监测；（ii）基于高光谱与人工神经网络\u002F随机森林\u002F决策树模型对芒果和草莓果实品质参数的评估；（iii）基于无人机高光谱的柑橘溃疡病检测；（iv）基于NPK、pH及气候变量的机器学习作物推荐系统；以及（v）基于遥感和地理信息系统（GIS）的卡纳塔克邦甘吉加蒂子流域六种主要果树土壤-立地适宜性评价。文章还回顾了CHAMAN、Bhoonidhi、Bhuvan和PMFBY等国家平台，作为遥感与机器学习价值链的运营示范。最后，讨论了技术、经济和伦理方面的挑战——包括地面真值稀缺、传感器成本、模型可解释性、数字鸿沟和数据隐私问题，并提出了印度园艺业在农业5.0时代的发展路径。","International Journal of Environmental and Agriculture Research","2026-08-31T00:00:00Z",74,{"impact":133,"substance":134,"depth":133,"authority":69,"freshness":135,"relevant":21,"comment":136},18,22,4,"综述全面，案例详实，对印度园艺精准农业有参考价值，但时效性一般。",[138],{"name":129,"url":126},[26,27,66,140,141],"遥感","园艺",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[144,145],{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":50,"locked":14,"version":51,"method":52,"evidence":147},{"candidates":148,"agricultural_evidence":56},[149,155,162,169,180,187,194,201,208,214,220],{"code":39,"score":150,"supported":56,"title":151,"abstract":152,"tags":154},19,[64],[153,66,64],"深度学习",[27,66],{"code":45,"score":133,"supported":56,"title":156,"abstract":158,"tags":161},[157],"remote sensing",[140,159,157,160,71],"无人机多光谱","multispectral",[140],{"code":32,"score":163,"supported":56,"title":164,"abstract":165,"tags":168},9,[],[34,166,167],"草莓","strawberry",[],{"code":170,"score":163,"supported":56,"title":171,"abstract":172,"tags":179},"B2",[],[173,174,175,176,177,178],"果树","柑橘","芒果","荔枝","apple","citrus",[],{"code":181,"score":121,"supported":56,"title":182,"abstract":183,"tags":186},"H2",[],[184,185],"土壤","soil",[],{"code":188,"score":121,"supported":56,"title":189,"abstract":190,"tags":193},"I4",[],[191,192],"地理信息","GIS",[],{"code":195,"score":121,"supported":56,"title":196,"abstract":197,"tags":200},"I6",[],[198,199],"数字鸿沟","digital divide",[],{"code":202,"score":203,"supported":56,"title":204,"abstract":205,"tags":207},"B4",3,[],[206],"花卉",[],{"code":209,"score":203,"supported":56,"title":210,"abstract":211,"tags":213},"B6",[],[212],"药用植物",[],{"code":215,"score":203,"supported":56,"title":216,"abstract":217,"tags":219},"H3",[],[218],"水资源",[],{"code":83,"score":21,"supported":14,"title":221,"abstract":222,"tags":223},[],[],[26],[225,226],"农业人工智能 智慧农业 机器学习 园艺","农业人工智能 智慧农业","农业人工智能智慧农业机器学习园艺-1299","10.25125\u002Fijoear-aug-2026-26",{"doi":228,"openalex_id":230,"authors":231,"venue":129,"cited_by_count":110,"oa_url":237,"card":238,"direction":243,"ingested_from":118},"W7204829467",[232,235],{"name":233,"orcid":234},"Jadala Shankaraswamy","https:\u002F\u002Forcid.org\u002F0000-0002-5623-6384",{"name":236,"orcid":9},"Md Abdul Gaffor","https:\u002F\u002Fijoear.com\u002Fassets\u002Farticles_menuscripts\u002Ffile\u002FIJOEAR-AUG-2026-26.pdf",{"tldr":239,"method":240,"finding":241,"direction":115,"opportunity":242},"综述遥感与机器学习在印度园艺作物精准管理中的应用，涵盖原理、方法、案例与挑战。","系统综述遥感平台与机器学习算法，分析五个典型案例及国家平台。","遥感与机器学习结合可提升园艺作物养分、病虫害、适种性等管理精度，但面临成本与数据挑战。","可探索低成本、可解释的遥感-机器学习模型，并集成多源数据以解决小农园艺场景的适用性问题。","智慧农业 \u002F 农业物联网","2026-09-01T23:30:09.105185Z",{"id":246,"title":247,"url":248,"summary":249,"summary_zh":250,"content":9,"source_name":251,"source_url":248,"published_at":252,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":253,"score_detail":254,"sources":256,"tags":258,"primary_topic":261,"secondary_topics":262,"classification":264,"search_phrases":284,"slug":286,"view_count":135,"doi":287,"paper":288,"created_at":310},2276,"PT-GNN: A physiological topology-aware graph neural network for multimodal early detection of cucumber downy mildew using hyperspectral and chlorophyll fluorescence sensing","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112433","PT-GNN: A physiological topology-aware graph neural network for multimodal early detection of cucumber downy mildew using hyperspectral and chlorophyll fluorescence sensing。Computers and Electronics in Agriculture","PT-GNN：一种生理拓扑感知图神经网络，利用高光谱和叶绿素荧光传感进行黄瓜霜霉病的多模态早期检测。","Computers and Electronics in Agriculture","2026-09-12T00:00:00Z",81,{"impact":133,"substance":134,"depth":133,"authority":20,"freshness":163,"relevant":21,"comment":255},"提出生理拓扑感知图神经网络融合高光谱与叶绿素荧光实现黄瓜霜霉病早期检测，方法新颖且发表于农业信息领域核心期刊，具备较强专业参考价值。",[257],{"name":251,"url":248},[26,27,259,260,30],"黄瓜","病害检测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[263],{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":265},{"candidates":266,"agricultural_evidence":56},[267,272,276,280],{"code":32,"score":17,"supported":56,"title":268,"abstract":270,"tags":271},[269],"cucumber",[259,269],[259],{"code":45,"score":69,"supported":56,"title":273,"abstract":274,"tags":275},[71],[71],[30],{"code":83,"score":21,"supported":14,"title":277,"abstract":278,"tags":279},[],[],[26],{"code":39,"score":21,"supported":14,"title":281,"abstract":282,"tags":283},[],[],[27],[285,91],"农业人工智能 高光谱遥感 智慧农业 病害检测","农业人工智能高光谱遥感智慧农业病害检测-2276","10.1016\u002Fj.compag.2026.112433",{"doi":287,"openalex_id":289,"authors":290,"venue":251,"cited_by_count":110,"oa_url":9,"card":305,"direction":115,"ingested_from":118},"W7212310174",[291,294,296,298,300,302],{"name":292,"orcid":293},"Yibin Li","https:\u002F\u002Forcid.org\u002F0000-0002-5906-5074",{"name":295,"orcid":9},"Zonghuan Han",{"name":297,"orcid":9},"Yong Wang",{"name":299,"orcid":9},"Wei Gao",{"name":301,"orcid":9},"Yiding Zhang",{"name":303,"orcid":304},"Lingxian Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-8665-7075",{"tldr":306,"method":307,"finding":308,"direction":115,"opportunity":309},"提出生理拓扑感知图神经网络PT-GNN，融合高光谱与叶绿素荧光实现黄瓜霜霉病早期检测。","构建生理拓扑图神经网络，融合高光谱与叶绿素荧光多模态传感数据。","PT-GNN能有效利用生理拓扑关系，提升黄瓜霜霉病早期检测精度。","可探索生理拓扑图构建的通用性，迁移至其他作物病害及多模态传感器融合场景。","2026-09-13T23:30:01.409569Z",{"id":312,"title":313,"url":314,"summary":315,"summary_zh":316,"content":9,"source_name":317,"source_url":314,"published_at":318,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":253,"score_detail":319,"sources":321,"tags":323,"primary_topic":325,"secondary_topics":326,"classification":328,"search_phrases":345,"slug":348,"view_count":203,"doi":349,"paper":350,"created_at":362},2158,"EfficientNet-CBAM-prototype: an attention-guided EfficientNet framework with dynamic prototype representation for tomato disease classification","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1918175","Introduction In the field of precision agriculture, one of the major hurdles is the early and accurate identification of plant diseases. Farmers may face serious irreversible loss in yield if there is a delay in diagnosis by even a few days. The CNN model has helped in improving the classification of plant diseases but faces difficulty in distinguishing fine-grained symptoms, has limited generalizability, and is not easily interpretable. Though the deep CNN model performs well in classifying plant diseases, the current methods have several flaws. Most importantly, existing algorithms misclassify visually complex samples due to their limited spatial differentiation of disease-specific morphological features, including lesion borders and necrotic regions. Classification reliability is further compromised by low inter-class embedding separability for visually comparable illness phenotypes. Apart from these representational problems, training instability is still a major problem for attention-based models. Combining randomly initialized attention modules with pretrained backbone networks causes this instability, which still limits practical application. Methods We suggest EfficientNet-CBAM-Prototype (ECP-Net), a unique end-to-end deep learning architecture, to overcome these constraints. Three complementary techniques are combined into a single framework by ECP-Net. First, parameter-efficient multi-scale feature extraction is done using an EfficientNetB0 backbone. Second, joint channel-wise and spatial feature recalibration is performed using a stabilized convolutional block attention module (CBAM). Third, a dynamic prototype memory layer uses cosine similarity-based categorization and exponential moving average (EMA) updates to maintain class-representative embedding vectors. To overcome the instability caused by randomly initialized attention weights, we further propose a two-phase training strategy wherein CBAM is frozen during phase 1 to allow prototype stabilization and then jointly fine-tuned with the learning rate in phase 2. Results Evaluated on the PlantVillage tomato subset comprising 10 disease classes across a class-balanced split of 10,000 training, 500 validation, and 500 test samples, ECP-Net achieves 98.6% test accuracy, 98.59% F1-score, and 98.65% precision with only 4.80M parameters and 85.04 ms average inference time. These results outperformed baselines including VGG16 (97.00%), ResNet50 (81.20%), MobileNetV2 (81.20%), and CNN (70.00%). Discussion Generalization is further validated on 35 real-field tomato leaf images captured under natural, uncontrolled conditions, confirming practical deployment potential.","引言 在精准农业领域，植物病害的早期准确识别是主要难题之一。若诊断延迟哪怕几天，农民可能面临严重的不可逆产量损失。CNN模型有助于改进植物病害分类，但在区分细粒度症状方面存在困难，泛化能力有限，且不易解释。尽管深度CNN模型在植物病害分类中表现良好，当前方法仍存在若干缺陷。最重要的是，现有算法由于对病害特异性形态特征（包括病斑边缘和坏死区域）的空间区分能力有限，会对视觉上复杂的样本产生误分类。对于视觉上相似的病害表型，类间嵌入可分性低，进一步损害了分类可靠性。除这些表征问题外，训练不稳定性仍是基于注意力模型的主要问题。随机初始化的注意力模块与预训练骨干网络相结合会导致这种不稳定性，这仍然限制了实际应用。方法 我们提出EfficientNet-CBAM-Prototype（ECP-Net），一种新颖的端到端深度学习架构，以克服这些限制。ECP-Net将三种互补技术结合到一个统一框架中。首先，使用EfficientNetB0骨干网络进行参数高效的多尺度特征提取。其次，使用稳定化的卷积块注意力模块（CBAM）进行通道与空间的联合特征重校准。第三，动态原型记忆层使用基于余弦相似度的分类和指数移动平均（EMA）更新来维护类代表性嵌入向量。为克服随机初始化注意力权重引起的不稳定性，我们进一步提出两阶段训练策略，其中CBAM在第一阶段冻结以使原型稳定，然后在第二阶段以学习率联合微调。结果 在PlantVillage番茄子集上评估，该子集包含10个病害类别，按类别均衡划分的10,000个训练样本、500个验证样本和500个测试样本，ECP-Net达到98.6%的测试准确率、98.59%的F1分数和98.65%的精确率，仅需4.80M参数和85.04 ms平均推理时间。这些结果优于基线，包括VGG16（97.00%）、ResNet50（81.20%）、MobileNetV2（81.20%）和CNN（70.00%）。","Frontiers in Plant Science","2026-09-10T00:00:00Z",{"impact":133,"substance":134,"depth":133,"authority":20,"freshness":163,"relevant":21,"comment":320},"提出注意力引导与动态原型结合的番茄病害识别框架，在公开数据集上取得98.6%准确率并完成真实田间图像验证，方法新颖、数据扎实，对作物病害智能诊断有实用参考价值。",[322],{"name":317,"url":314},[26,27,153,324,29],"病虫害识别",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[327],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":329},{"candidates":330,"agricultural_evidence":56},[331,336,341],{"code":32,"score":133,"supported":56,"title":332,"abstract":333,"tags":335},[58],[60,334,58],"茄子",[29],{"code":39,"score":163,"supported":56,"title":337,"abstract":338,"tags":340},[],[153,339],"deep learning",[27,153,324],{"code":83,"score":76,"supported":56,"title":342,"abstract":343,"tags":344},[],[86,87],[26],[346,347],"农业人工智能 病虫害识别 智慧农业 深度学习","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深度学习-2158","10.3389\u002Ffpls.2026.1918175",{"doi":349,"openalex_id":351,"authors":352,"venue":317,"cited_by_count":110,"oa_url":314,"card":357,"direction":115,"ingested_from":118},"W7212120374",[353,355],{"name":354,"orcid":9},"E Jansi",{"name":356,"orcid":9},"Kavitha BR",{"tldr":358,"method":359,"finding":360,"direction":117,"opportunity":361},"提出ECP-Net，用注意力与动态原型提升番茄病害分类精度与可解释性。","EfficientNetB0+稳定CBAM+动态原型记忆层，两阶段训练策略。","在PlantVillage番茄10类上达98.6%准确率，仅4.80M参数，优于多个基线。","可探索原型可解释性在田间复杂背景与跨域病害识别中的泛化能力。","2026-09-11T23:30:25.043704Z",{"id":364,"title":365,"url":366,"summary":367,"summary_zh":368,"content":9,"source_name":369,"source_url":366,"published_at":370,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":371,"score_detail":372,"sources":375,"tags":377,"primary_topic":381,"secondary_topics":382,"classification":384,"search_phrases":431,"slug":434,"view_count":110,"doi":435,"paper":436,"created_at":457},5582,"AI-Based RGB Imaging and 14-Channel Multispectral Food Quality Scanner","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85255","Food-quality assessment plays an important role in food safety, agricultural processing, storage, and supply-chain management. Conventional inspection methods depend on visual judgement or laboratory-based testing, which may require considerable time, specialised equipment, and manual effort. Recent developments in computer vision, multispectral sensing, and artificial intelligence (AI) provide opportunities for automated, non-destructive food-quality assessment. This paper reviews the application of RGB imaging, multispectral sensing, machine learning, and deep learning for fruit-ripeness estimation, surfacedefect detection, grain classification, and food-authenticity assessment. The reviewed literature demonstrates that RGB imaging can extract visible features such as colour, shape, and texture, whereas multispectral sensing provides wavelength-dependent information associated with food characteristics. Published studies have reported promising results in tomato-ripeness classification, apple-defect detection, rice-grain analysis, and honey-adulteration screening. Based on these findings, a compact food-quality scanner integrating an RGB camera, a 14-channel multispectral sensor, controlled illumination, and an embedded processing unit is proposed. The review discusses sensor integration, data preprocessing, feature fusion, classification methods, evaluation metrics, and implementation challenges. It also identifies the need for broader datasets, standardised illumination, independent validation, and resource-efficient AI models to improve the reliability of portable food-inspection systems.","食品质量评估在食品安全、农产品加工、储运和供应链管理中发挥着重要作用。传统检测方法依赖人工目视判断或实验室检测，往往需要较长时间、专用设备和人工投入。近年来，计算机视觉、多光谱传感和人工智能（AI）的发展为自动化、无损食品质量评估提供了新的机遇。本文综述了RGB成像、多光谱传感、机器学习和深度学习在果实成熟度估计、表面缺陷检测、谷物分类和食品真实性评估中的应用。所综述的文献表明，RGB成像能够提取颜色、形状和纹理等可见特征，而多光谱传感则可提供与食品特性相关的波长依赖信息。已发表研究在番茄成熟度分类、苹果缺陷检测、稻米籽粒分析和蜂蜜掺假筛查等方面取得了良好结果。基于上述研究结果，本文提出一种集成了RGB相机、14通道多光谱传感器、受控照明和嵌入式处理单元的紧凑型食品质量扫描仪。综述讨论了传感器集成、数据预处理、特征融合、分类方法、评价指标和实现挑战，并指出需要更广泛的数据集、标准化照明、独立验证和资源高效的AI模型，以提高便携式食品检测系统的可靠性。","International Journal for Research in Applied Science and Engineering Technology","2026-10-21T00:00:00Z",65,{"impact":69,"substance":133,"depth":373,"authority":163,"freshness":13,"relevant":21,"comment":374},16,"综述性论文，提出集成RGB与14通道多光谱的便携食品质量扫描仪方案，方法框架清晰但缺乏自有实验数据，属细分领域技术进展，可作参考但非重大突破。",[376],{"name":369,"url":366},[26,27,378,379,380],"无损检测","多光谱成像","食品质量检测",{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},[383],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":385},{"candidates":386,"agricultural_evidence":56},[387,391,398,405,412,416,421,427],{"code":45,"score":69,"supported":56,"title":388,"abstract":389,"tags":390},[160],[160],[379],{"code":39,"score":13,"supported":56,"title":392,"abstract":393,"tags":397},[],[153,66,394,64,339,395,396],"计算机视觉","artificial intelligence","computer vision",[27],{"code":399,"score":76,"supported":56,"title":400,"abstract":401,"tags":404},"E4",[],[402,403],"食品安全","food safety",[378],{"code":406,"score":121,"supported":56,"title":407,"abstract":408,"tags":411},"A1",[],[409,410],"稻米","rice",[],{"code":32,"score":121,"supported":56,"title":413,"abstract":414,"tags":415},[],[60,58],[],{"code":170,"score":121,"supported":56,"title":417,"abstract":418,"tags":420},[],[419,177],"苹果",[],{"code":422,"score":203,"supported":56,"title":423,"abstract":424,"tags":426},"E1",[],[425],"农产品加工",[],{"code":83,"score":21,"supported":14,"title":428,"abstract":429,"tags":430},[],[],[26],[432,433],"RGB成像 多光谱 食品质量","14通道 多光谱 扫描仪","RGB成像多光谱食品质量-5582","10.22214\u002Fijraset.2026.85255",{"doi":435,"openalex_id":437,"authors":438,"venue":369,"cited_by_count":110,"oa_url":366,"card":451,"direction":456,"ingested_from":118},"W7223139905",[439,441,443,445,447,449],{"name":440,"orcid":9},"Eshwari Take",{"name":442,"orcid":9},"Avanish Raut",{"name":444,"orcid":9},"Vedant Joshi",{"name":446,"orcid":9},"Shravani Akolkar",{"name":448,"orcid":9},"R. M. Gharat",{"name":450,"orcid":9},"Shruti Dive",{"tldr":452,"method":453,"finding":454,"direction":117,"opportunity":455},"综述RGB与多光谱成像结合AI的食品品质无损检测，并提出一款集成14通道多光谱传感器的紧凑型扫描仪方","综述RGB成像、多光谱传感与机器学习\u002F深度学习在食品检测中的应用，并提出传感器集","RGB与多光谱融合在番茄成熟度、苹果缺陷、稻米分类和蜂蜜掺假检测中表现良好。","可研究多源光谱特征融合与轻量化模型，构建标准化数据集和便携设备独立验证体系。","数字乡村与农业信息化","2026-10-22T11:20:48.684398Z",{"id":459,"title":460,"url":461,"summary":462,"summary_zh":463,"content":9,"source_name":464,"source_url":461,"published_at":370,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":465,"score_detail":466,"sources":470,"tags":472,"primary_topic":475,"secondary_topics":476,"classification":478,"search_phrases":493,"slug":496,"view_count":110,"doi":497,"paper":498,"created_at":508},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。","Zenodo (CERN European Organization for Nuclear Research)",67,{"impact":467,"substance":468,"depth":19,"authority":69,"freshness":13,"relevant":21,"comment":469},8,20,"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[471],{"name":464,"url":461},[26,27,473,140,474],"产量预测","可解释性",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[477],{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":479},{"candidates":480,"agricultural_evidence":56},[481,485,489],{"code":39,"score":69,"supported":56,"title":482,"abstract":483,"tags":484},[396],[394],[27],{"code":45,"score":467,"supported":56,"title":486,"abstract":487,"tags":488},[],[140,157],[473,140],{"code":83,"score":21,"supported":14,"title":490,"abstract":491,"tags":492},[],[],[26],[494,495],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":497,"openalex_id":499,"authors":500,"venue":464,"cited_by_count":110,"oa_url":461,"card":503,"direction":115,"ingested_from":118},"W7223114002",[501],{"name":502,"orcid":9},"Kadiatou Barry",{"tldr":504,"method":505,"finding":506,"direction":115,"opportunity":507},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":510,"title":511,"url":512,"summary":513,"summary_zh":514,"content":9,"source_name":515,"source_url":512,"published_at":516,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":517,"score_detail":518,"sources":520,"tags":522,"primary_topic":525,"secondary_topics":526,"classification":528,"search_phrases":544,"slug":547,"view_count":110,"doi":548,"paper":549,"created_at":563},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":69,"substance":133,"depth":373,"authority":13,"freshness":467,"relevant":21,"comment":519},"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。",[521],{"name":515,"url":512},[26,27,153,523,524],"番茄病害","图像识别",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[527],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":529},{"candidates":530,"agricultural_evidence":56},[531,535,539],{"code":32,"score":17,"supported":56,"title":532,"abstract":533,"tags":534},[58],[60,58],[523],{"code":39,"score":163,"supported":56,"title":536,"abstract":537,"tags":538},[],[153,339],[27,524,153],{"code":83,"score":76,"supported":56,"title":540,"abstract":541,"tags":543},[],[26,542],"smart agriculture",[26],[545,546],"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":548,"openalex_id":550,"authors":551,"venue":515,"cited_by_count":110,"oa_url":557,"card":558,"direction":243,"ingested_from":118},"W7222977034",[552,554],{"name":553,"orcid":9},"Mrs. Vijetalaxmi A Hegde",{"name":555,"orcid":556},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":559,"method":560,"finding":561,"direction":117,"opportunity":562},"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"]