[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3360":3,"related-3360":62},{"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":24,"tags":26,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":61},3360,"Quantum Machine Learning for Hyperspectral Soil Nutrient Estimation in Precision Agriculture: A Review and Roadmap","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16192069","Accurate soil nutrient estimation underpins fertility assessment, precision agriculture, and sustainable land management, yet conventional laboratory analysis is slow, costly, and impractical at scale. Hyperspectral imaging (HSI) captures detailed spectral signatures linked to soil properties, but its high dimensionality and limited ground truth samples strain classical machine learning. This review examines quantum machine learning (QML) as an emerging rather than established direction for high-dimensional, low-sample hyperspectral soil analysis. We outline where classical machine learning and deep learning fall short and then assess how quantum kernel methods, variational quantum circuits, and hybrid quantum–classical architectures might improve feature representation and nonlinear modeling. Of the 150 studies reviewed, 26 report quantum machine learning results of any kind, five use soil data, and only one evaluates soil spectra directly for nutrient or property estimation. The remainder contribute transferable evidence from adjacent soil and remote sensing tasks, together with soil applications that remain proposals. Accordingly, the review weighs both the promise and the practical constraints of QML on current noisy intermediate-scale quantum hardware, including the encoding cost, measurement overhead, circuit depth, and trainability limits. Future research priorities are identified: quantum-ready hyperspectral soil datasets, reproducible benchmarking against well-tuned classical baselines, scalable hybrid pipelines, hardware-aware reporting, and field validation. Pairing QML with hyperspectral soil sensing may eventually support soil fertility assessment, variable-rate fertilization, and sustainable precision agriculture, but any such benefit must be demonstrated experimentally rather than inferred and will depend on continued progress in quantum hardware.","准确的土壤养分估算是肥力评估、精准农业和可持续土地管理的基础，然而传统实验室分析速度慢、成本高，难以大规模应用。高光谱成像（HSI）能够捕获与土壤属性相关的精细光谱特征，但其高维度和有限的真实标注样本给经典机器学习带来了挑战。本综述将量子机器学习（QML）视为面向高维、小样本高光谱土壤分析的一个新兴而非成熟的方向。我们梳理了经典机器学习和深度学习的不足之处，进而评估量子核方法、变分量子电路以及量子—经典混合架构如何可能改进特征表示与非线性建模。在综述的150项研究中，26项报告了某种形式的量子机器学习结果，5项使用了土壤数据，仅1项直接评估土壤光谱以估算养分或属性。其余研究提供了来自相邻土壤和遥感任务的可迁移证据，以及仍处于提案阶段的土壤应用。据此，本综述权衡了QML在当前含噪中等规模量子硬件上的前景与实际约束，包括编码成本、测量开销、电路深度和可训练性限制。未来研究重点包括：量子就绪的高光谱土壤数据集、针对精心调优的经典基线的可复现基准测试、可扩展的混合流程、硬件感知的报告以及田间验证。将QML与高光谱土壤传感相结合，最终可能支持土壤肥力评估、变量施肥和可持续精准农业，但任何此类收益都必须通过实验证明而非推断，并将取决于量子硬件的持续进步。",null,"Agriculture","2026-09-23T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,21,18,13,9,1,"系统梳理量子机器学习用于高光谱土壤养分估算的现状与路线图，指出仅1项研究直接验证土壤光谱，兼具前沿性与现实约束，值得进入每日精选。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","高光谱遥感","土壤养分","量子计算",[33,34],"量子机器学习 高光谱 土壤养分","精准农业 变量施肥 土壤肥力","量子机器学习高光谱土壤养分-3360",0,"10.3390\u002Fagriculture16192069",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":6,"card":54,"direction":58,"ingested_from":60},"W7214101561",[41,44,46,49,52],{"name":42,"orcid":43},"Dristi Datta","https:\u002F\u002Forcid.org\u002F0000-0002-9426-9750",{"name":45,"orcid":9},"Dipti Biswas",{"name":47,"orcid":48},"Uttam Sinha Mahapatra","https:\u002F\u002Forcid.org\u002F0009-0001-0619-0381",{"name":50,"orcid":51},"Manoranjan Paul","https:\u002F\u002Forcid.org\u002F0000-0001-6870-5056",{"name":53,"orcid":9},"Davina White",{"tldr":55,"method":56,"finding":57,"direction":58,"opportunity":59},"综述量子机器学习用于高光谱土壤养分估算，指出其尚处早期并给出研究路线图。","综述150项研究，评估量子核方法、变分量子电路与混合量子-经典架构。","仅1项研究直接评估土壤光谱养分估算，QML优势尚未实验证实。","农业遥感与作物表型","构建量子就绪高光谱土壤数据集，并与调优经典基线做可复现基准对比。","openalex","2026-09-24T23:30:20.797372Z",{"total":63,"page":22,"page_size":63,"items":64},6,[65,110,154,184,225,265],{"id":66,"title":67,"url":68,"summary":69,"summary_zh":70,"content":9,"source_name":71,"source_url":68,"published_at":72,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":73,"sources":78,"tags":80,"search_phrases":83,"slug":86,"view_count":36,"doi":87,"paper":88,"created_at":109},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。","Scientific Reports","2026-09-17T00:00:00Z",{"impact":74,"substance":18,"depth":75,"authority":76,"freshness":13,"relevant":22,"comment":77},15,17,14,"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。",[79],{"name":71,"url":68},[27,28,81,82,29],"精准施肥","番茄种植",[84,85],"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","10.1038\u002Fs41598-026-71908-1",{"doi":87,"openalex_id":89,"authors":90,"venue":71,"cited_by_count":36,"oa_url":68,"card":103,"direction":108,"ingested_from":60},"W7213472002",[91,94,97,100],{"name":92,"orcid":93},"Mohammad Vahedi Torshizi","https:\u002F\u002Forcid.org\u002F0000-0003-3648-1515",{"name":95,"orcid":96},"Sajad Sabzi","https:\u002F\u002Forcid.org\u002F0000-0003-2439-5329",{"name":98,"orcid":99},"Mohsen Azadbakht","https:\u002F\u002Forcid.org\u002F0000-0002-5726-9321",{"name":101,"orcid":102},"Razieh Pourdarbani","https:\u002F\u002Forcid.org\u002F0000-0003-0766-8305",{"tldr":104,"method":105,"finding":106,"direction":58,"opportunity":107},"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。","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","2026-09-17T23:30:59.361085Z",{"id":111,"title":112,"url":113,"summary":114,"summary_zh":115,"content":9,"source_name":116,"source_url":113,"published_at":117,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":118,"score_detail":119,"sources":122,"tags":124,"search_phrases":127,"slug":129,"view_count":36,"doi":130,"paper":131,"created_at":153},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":19,"substance":120,"depth":19,"authority":76,"freshness":21,"relevant":22,"comment":121},22,"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。",[123],{"name":116,"url":113},[27,28,125,126,29],"黄瓜","病害检测",[128,85],"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":130,"openalex_id":132,"authors":133,"venue":116,"cited_by_count":36,"oa_url":9,"card":148,"direction":58,"ingested_from":60},"W7212310174",[134,137,139,141,143,145],{"name":135,"orcid":136},"Yibin Li","https:\u002F\u002Forcid.org\u002F0000-0002-5906-5074",{"name":138,"orcid":9},"Zonghuan Han",{"name":140,"orcid":9},"Yong Wang",{"name":142,"orcid":9},"Wei Gao",{"name":144,"orcid":9},"Yiding Zhang",{"name":146,"orcid":147},"Lingxian Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-8665-7075",{"tldr":149,"method":150,"finding":151,"direction":58,"opportunity":152},"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":155,"title":156,"url":157,"summary":158,"summary_zh":9,"content":9,"source_name":159,"source_url":9,"published_at":160,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":161,"score_detail":162,"sources":166,"tags":168,"search_phrases":171,"slug":174,"view_count":36,"doi":9,"paper":175,"created_at":183},1815,"A Review of Agricultural Intelligent Architecture: The Application and Challenges of Artificial Intelligence in Agricultural Perception, Decision-Making, and Execution（MDPI Applied Sciences 2026, 16(12), 5865）","https:\u002F\u002Fwww.mdpi.com\u002F2076-3417\u002F16\u002F12\u002F5865","以\"智能感知—认知决策—自主执行\"框架系统综述农业人工智能核心技术与应用方向，重点介绍三维表型、高光谱遥感、多模态融合、因果机器学习等关键技术进展。指出当前农业AI仍面临模型泛化能力不足、数据稀缺且标注成本高、边缘部署困难、多源数据整合障碍、可解释性与工程可靠性弱等现实瓶颈。未来研究将聚焦闭环自主农场、农业大模型与智能体协同、数据中心与AI基础设施、绿色低成本AI研发。","MDPI Applied Sciences 2026, 16(12)","2026-09-02T00:00:00Z",74,{"impact":19,"substance":163,"depth":19,"authority":20,"freshness":164,"relevant":22,"comment":165},20,5,"系统综述农业AI架构与瓶颈，具前瞻性，但时效性一般。",[167],{"name":159,"url":157},[27,28,29,169,170],"因果机器学习","智能感知",[172,173],"农业人工智能 因果机器学习 高光谱遥感 智慧农业","农业人工智能 因果机器学习","农业人工智能因果机器学习高光谱遥感智慧农业-1815",{"doi":9,"openalex_id":9,"authors":176,"venue":9,"cited_by_count":36,"oa_url":9,"card":177,"direction":108,"ingested_from":182},[],{"tldr":178,"method":179,"finding":180,"direction":108,"opportunity":181},"综述农业人工智能在感知、决策、执行中的应用与挑战，提出未来研究方向。","系统综述，基于智能感知-认知决策-自主执行框架，分析关键技术。","农业AI面临泛化不足、数据稀缺、边缘部署难等瓶颈，未来聚焦闭环自主农场与农业大模型。","可研究农业大模型与智能体协同，解决数据稀缺和泛化问题，推动闭环自主农场落地。","agent","2026-09-07T00:04:41.509850Z",{"id":185,"title":186,"url":187,"summary":188,"summary_zh":189,"content":9,"source_name":190,"source_url":187,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":191,"score_detail":192,"sources":194,"tags":196,"search_phrases":200,"slug":203,"view_count":36,"doi":204,"paper":205,"created_at":224},3368,"A PCA-based deep feature optimization framework for explainable orange fruit disease classification","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs12870-026-09984-8","Accurate classification of orange fruit diseases is important for precision agriculture and yield protection. This study develops and rigorously benchmarks a hybrid deep-feature framework for classifying Black Spot, Canker, Fresh, and Greening oranges (1,090 images), combining deep feature extraction, PCA-based dimensionality reduction, and classical machine-learning classification. Eight backbones (seven CNNs and a Vision Transformer, ViT) and four classifiers (32 configurations in total) were evaluated under 5 × 5 repeated stratified cross-validation, with PCA fitted exclusively on training-fold features in every iteration to eliminate data leakage. The proposed ViT + PCA+SVM configuration achieved the highest mean accuracy, 99.12%±0.71%, significantly outperforming every CNN-based backbone, including DenseNet201 + PCA + SVM (98.48%±0.81%, p \u003C 0.001). A dedicated variance-retention sensitivity analysis justifies the 98% threshold used throughout, and ablation experiments confirm that PCA substantially reduces feature dimensionality (by ~ 55.7% for ViT and ~ 76.6% for DenseNet201) without a significant loss of accuracy for either backbone. Explainability analysis — occlusion sensitivity and SHAP for the proposed ViT model, and Grad-CAM and SHAP for the DenseNet201 comparison model — shows that both configurations base predictions on biologically relevant, disease-affected regions of the fruit rather than spurious cues. These results identify ViT + PCA+SVM as the most accurate configuration evaluated, with DenseNet201 + PCA + SVM as a closely competitive, more compact convolutional alternative for intelligent orchard disease-monitoring systems.","橙类果实病害的准确分类对精准农业和产量保护具有重要意义。本研究开发并严格基准测试了一种混合深度特征框架，用于对黑斑病、溃疡病、新鲜和黄龙病橙类（1，090张图像）进行分类，该框架结合了深度特征提取、基于PCA的降维和经典机器学习分类。在5×5重复分层交叉验证下评估了八种骨干网络（七种CNN和一种视觉Transformer，ViT）和四种分类器（共32种配置），每次迭代中PCA仅在训练折特征上拟合以消除数据泄漏。所提出的ViT + PCA+SVM配置取得了最高平均准确率，为99.12%±0.71%，显著优于所有基于CNN的骨干网络，包括DenseNet201 + PCA + SVM（98.48%±0.81%，p \u003C 0.001）。专门的方差保留敏感性分析证明了全程使用的98%阈值是合理的，消融实验证实PCA大幅降低了特征维度（ViT约降低55.7%，DenseNet201约降低76.6%），且两种骨干网络均无显著准确率损失。可解释性分析——对所提出的ViT模型采用遮挡敏感性和SHAP，对DenseNet201对比模型采用Grad-CAM和SHAP——表明两种配置均基于果实中生物学相关的病害影响区域而非虚假线索进行预测。这些结果确定ViT + PCA+SVM为所评估的最准确配置，而DenseNet201 + PCA + SVM则是一种竞争力接近且更紧凑的卷积替代方案，可用于智能果园病害监测系统。","BMC Plant Biology",79,{"impact":17,"substance":120,"depth":19,"authority":76,"freshness":21,"relevant":22,"comment":193},"方法严谨、数据与消融实验充分，对果园智能病害监测有实用参考价值，但属细分技术论文，产业影响有限。",[195],{"name":190,"url":187},[27,28,197,198,199],"可解释AI","病害识别","柑橘种植",[201,202],"柑橘病害 深度学习 分类","ViT PCA SVM 病害识别","柑橘病害深度学习分类-3368","10.1186\u002Fs12870-026-09984-8",{"doi":204,"openalex_id":206,"authors":207,"venue":190,"cited_by_count":36,"oa_url":187,"card":219,"direction":108,"ingested_from":60},"W7214068709",[208,210,212,214,217],{"name":209,"orcid":9},"Amruta Hingmire",{"name":211,"orcid":9},"Avinash Golande",{"name":213,"orcid":9},"Vinodkumar Bhutnal",{"name":215,"orcid":216},"Sagar Dhanraj Pande","https:\u002F\u002Forcid.org\u002F0000-0003-4506-6997",{"name":218,"orcid":9},"Tanuja Pande",{"tldr":220,"method":221,"finding":222,"direction":108,"opportunity":223},"提出PCA深度特征优化框架，用ViT+SVM分类橙子病害，准确率达99.12%。","8种骨干网络提取特征，PCA降维，4种分类器，5×5交叉验证。","ViT+PCA+SVM最优，PCA降维超55%且精度不降，可解释性验证有效。","可探索轻量化模型在移动端或边缘设备的实时病害检测与多作物泛化。","2026-09-24T23:30:34.116938Z",{"id":226,"title":227,"url":228,"summary":229,"summary_zh":230,"content":9,"source_name":231,"source_url":228,"published_at":232,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":233,"score_detail":234,"sources":237,"tags":239,"search_phrases":243,"slug":246,"view_count":36,"doi":247,"paper":248,"created_at":264},3367,"Digital Technology Adoption Conditioning Analysis Model in Agriculture","https:\u002F\u002Fdoi.org\u002F10.20944\u002Fpreprints202609.1880.v1","Technological advancements have been responsible for a significant part of the growth in agricultural productivity in recent years. Digital technologies have a high potential to enable the development of the agricultural sector, reshape value chains, and significantly contribute to more productive, resilient, and transparent food systems; however, their adoption in Brazil remains uneven due to regional disparities and structural bottlenecks. The research investigated this problem to build and validate the Digital Technology Adoption Conditioning Analysis Model (MAC-AgriTech), through a case study with Brazilian agricultural data, encompassing the identification of conditioning factors, their territorial evaluation, and the proposition of actions, while providing structured data collection and analysis instruments. The spatial analysis revealed deep territorial asymmetries, concentrating resources and infrastructure in the South and Southeast regions. Econometric modeling demonstrated that digital adoption is primarily driven by the producer’s digital familiarity, connectivity quality, and property scale, with 77% of producers identifying acquisition and maintenance costs as the primary barrier. The transition to digital agriculture in Brazil requires targeted, multidimensional public policies—such as expanded rural connectivity, technical training, and subsidized credit—to overcome regional gaps, and to increase agricultural competitiveness, efficiency, and sustainability.","近年来，技术进步对农业生产力增长贡献显著。数字技术具有巨大潜力，能够推动农业部门发展、重塑价值链，并为构建更高产、更具韧性且更透明的粮食体系作出重要贡献；然而，由于区域差异和结构性瓶颈，其在巴西的采用仍不均衡。本研究针对这一问题，通过一项基于巴西农业数据的案例研究，构建并验证了数字技术采用条件分析模型（MAC-AgriTech），涵盖条件因素的识别、其区域性评估以及行动建议的提出，同时提供了结构化的数据收集与分析工具。空间分析揭示了深刻的区域不对称性，资源和基础设施集中在南部和东南部地区。计量经济建模表明，数字采用主要受生产者数字熟悉度、连接质量和财产规模的驱动，其中77%的生产者将购置和维护成本视为主要障碍。巴西向数字农业的转型需要有针对性的、多维度的公共政策——如扩大农村连接、技术培训和补贴信贷——以克服区域差距，并提高农业竞争力、效率和可持续性。","Preprints.org","2026-09-22T00:00:00Z",67,{"impact":17,"substance":163,"depth":75,"authority":63,"freshness":235,"relevant":22,"comment":236},8,"基于巴西农业数据的数字技术采纳条件分析模型研究，方法系统、结论有实证支撑，但属预印本且聚焦巴西，对国内参考价值有限。",[238],{"name":231,"url":228},[240,27,28,241,242],"数字农业","巴西农业","农村数字化",[244,245],"巴西 数字农业 技术采纳","MAC-AgriTech 模型","巴西数字农业技术采纳-3367","10.20944\u002Fpreprints202609.1880.v1",{"doi":247,"openalex_id":249,"authors":250,"venue":231,"cited_by_count":36,"oa_url":228,"card":258,"direction":262,"ingested_from":60},"W7214109425",[251,254,256],{"name":252,"orcid":253},"Isabela Santos","https:\u002F\u002Forcid.org\u002F0009-0002-3659-2020",{"name":255,"orcid":9},"Eduardo Dias",{"name":257,"orcid":9},"Lidia Scoton",{"tldr":259,"method":260,"finding":261,"direction":262,"opportunity":263},"构建并验证MAC-AgriTech模型，分析巴西农业数字技术采纳的条件因素与区域差异。","巴西农业数据案例研究，空间分析与计量经济建模。","采纳主要由数字熟悉度、连接质量和农场规模驱动，77%生产者视成本为首要障碍。","数字乡村与农业信息化","可延伸至中国等发展中国家，探究数字素养、基础设施与政策组合对技术采纳的因果效应。","2026-09-24T23:30:27.046035Z",{"id":266,"title":267,"url":268,"summary":269,"summary_zh":270,"content":9,"source_name":271,"source_url":268,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":272,"score_detail":273,"sources":275,"tags":277,"search_phrases":281,"slug":284,"view_count":36,"doi":285,"paper":286,"created_at":326},3366,"Brazilian Insect Survey: A Platform for Pest Management","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs13744-026-01426-2","Abstract Modern agriculture faces significant challenges in integrated pest management, where collecting, connecting, and processing monitoring data in real time are essential. This study presents the Brazilian Insect Survey (BIS), a web-based platform designed to centralize and streamline phytosanitary data management, enabling the integration of computer vision, field experimentation, and population modeling within a unified digital ecosystem. The platform is organized into functional modules that support experimental data management (TrapSystem and AgroExperiment), automated insect detection and counting from digital images (InsectCV and AphidCV), and simulation of aphid population dynamics (ABISM). These components operate in synergy, supported by distributed processing infrastructure, to ensure scalable data handling and efficient analytical workflows. Multi-year field applications demonstrate that integrating field data acquisition and automated image analysis with mechanistic population modeling enables timely, model-driven interventions that reduce aphid infestation levels and protect crop yield potential under variable environmental conditions, providing empirical evidence for queryPlease check if the captured keywords are correct.the effectiveness of combining AI-based insect detection with population dynamics modeling in operational integrated pest management. The case studies presented here demonstrate that the BIS platform successfully integrates computer vision, field experimentation, and population modeling within a modular digital ecosystem, highlighting its potential to enhance decision-making and advance data-driven integrated pest management.","摘要 现代农业在有害生物综合治理方面面临重大挑战，其中实时采集、连接和处理监测数据至关重要。本研究提出了巴西昆虫调查平台（Brazilian Insect Survey，BIS），这是一个基于网络的平台，旨在集中化和简化植物检疫数据管理，使计算机视觉、田间试验和种群建模能够整合在一个统一的数字生态系统中。该平台按功能模块组织，支持实验数据管理（TrapSystem和AgroExperiment）、基于数字图像的昆虫自动检测与计数（InsectCV和AphidCV），以及蚜虫种群动态模拟（ABISM）。这些组件在分布式处理基础设施的支持下协同运行，以确保可扩展的数据处理和高效的分析工作流。多年田间应用表明，将田间数据采集和自动图像分析与机制性种群建模相结合，能够实现及时的、模型驱动的干预，从而在多变的环境条件下降低蚜虫侵染水平并保护作物产量潜力，为将基于人工智能的昆虫检测与种群动态建模相结合在实际有害生物综合治理中的有效性提供了经验证据。本文所呈现的案例研究表明，BIS平台成功地将计算机视觉、田间试验和种群建模整合在一个模块化数字生态系统中，凸显了其在增强决策能力和推进数据驱动有害生物综合治理方面的潜力。","Neotropical Entomology",80,{"impact":19,"substance":120,"depth":19,"authority":76,"freshness":235,"relevant":22,"comment":274},"巴西昆虫调查平台将计算机视觉与种群动态模型整合进IPM实践，方法新颖、多年田间验证，对智慧农业病虫害监测有参考价值。",[276],{"name":271,"url":268},[27,28,278,279,280],"计算机视觉","病虫害监测","种群模型",[282,283],"Brazil 蚜虫 监测平台","农业人工智能 病虫害监测 计算机视觉 智慧农业","Brazil蚜虫监测平台-3366","10.1007\u002Fs13744-026-01426-2",{"doi":285,"openalex_id":287,"authors":288,"venue":271,"cited_by_count":36,"oa_url":268,"card":320,"direction":262,"ingested_from":60},"W7214074071",[289,292,294,297,300,302,305,308,311,314,317],{"name":290,"orcid":291},"Telmo De Cesaro Júnior","https:\u002F\u002Forcid.org\u002F0000-0002-2886-229X",{"name":293,"orcid":9},"Bárbara Stella Wehrmann",{"name":295,"orcid":296},"Alexandre Tagliari Lazzaretti","https:\u002F\u002Forcid.org\u002F0009-0004-8345-8216",{"name":298,"orcid":299},"Roberto Wiest","https:\u002F\u002Forcid.org\u002F0000-0001-7982-6603",{"name":301,"orcid":9},"Jorge Luis Boeira Bavaresco",{"name":303,"orcid":304},"Brenda Slongo Taca","https:\u002F\u002Forcid.org\u002F0009-0000-6408-5523",{"name":306,"orcid":307},"Nicolas Welfer Kirinus","https:\u002F\u002Forcid.org\u002F0009-0003-5260-3161",{"name":309,"orcid":310},"Crislaine Sartori Suzana Milan","https:\u002F\u002Forcid.org\u002F0000-0003-0562-7286",{"name":312,"orcid":313},"Jayme Garcia Arnal Barbedo","https:\u002F\u002Forcid.org\u002F0000-0002-1156-8270",{"name":315,"orcid":316},"Douglas Lau","https:\u002F\u002Forcid.org\u002F0000-0001-8648-0102",{"name":318,"orcid":319},"Rafael Rieder","https:\u002F\u002Forcid.org\u002F0000-0002-7435-9054",{"tldr":321,"method":322,"finding":323,"direction":324,"opportunity":325},"巴西昆虫调查平台整合计算机视觉、田间试验与种群建模，实现害虫实时监测与治理。","构建BIS网络平台，集成InsectCV\u002FAphidCV图像识别、TrapSys","AI昆虫检测与种群动态建模结合可降低蚜虫侵害并保护作物产量。","智慧农业 \u002F 农业物联网","可探索多害虫跨区域监测数据标准化与模型迁移，构建开放植保决策生态。","2026-09-24T23:30:25.977846Z"]