[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2428":3,"related-2428":85},{"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,"primary_topic":9,"secondary_topics":31,"classification":32,"search_phrases":62,"slug":65,"view_count":66,"doi":67,"paper":68,"created_at":84},2428,"Transformer-Fused Hybrid Descriptors for Remote Sensing Scene Classification, Integrating Texture-Morphology Features with EfficientNetV2 Semantic Embeddings on MLRSNet","https:\u002F\u002Fdoi.org\u002F10.14445\u002F23488549\u002Fijece-v13i8p108","Classification in remote sensing images is a difficult problem, given high intra-class variability, inter-class similarity, and spatial complexity. In this paper, a novel transformer-fused hybrid feature learning model is developed to effectively combine handcrafted and deep features for accurate Land Use\u002FLand Cover (LULC) scene classification. In this model, texture features are represented using Local Binary Patterns (LBPs) and Grey-Level Co-occurrence Matrix (GLCM) features, while morphological region features provide shape information for scene characterization. Meanwhile, deep semantic features are also learned from EfficientNetV2-B0. To effectively fuse these features, a novel multi-head self-attention fusion mechanism is developed to learn explicit feature dependencies between texture, morphological, and semantic features for a compact yet discriminative feature representation. Experimental evaluation is conducted using the complete MLRSNet dataset comprising all 46 scene classes and 46,000 images, with 1,000 images considered from each class to ensure a balanced and comprehensive experimental setting. The proposed framework achieves an average five-fold accuracy of 99.98%, demonstrating high learning consistency across the complete set of diverse and visually similar remote sensing scenes. Comparative evaluation with established pretrained CNN and transformer-based models under the same experimental setting, together with component-wise ablation analysis, further demonstrates the contribution of the handcrafted descriptors, EfficientNetV2 semantic embeddings, and transformer-guided fusion mechanism. This fusion approach is effective for improving inter-class discriminability for visually similar LULC classes, which is a powerful tool for large-scale LULC mapping, urban growth analysis, environmental surveillance, etc., from remote sensing images.","遥感图像分类因类内差异大、类间相似度高以及空间复杂度高而成为一个难题。本文提出了一种新颖的Transformer融合混合特征学习模型，旨在有效结合手工特征与深度特征，实现精确的土地利用\u002F土地覆盖（LULC）场景分类。在该模型中，纹理特征采用局部二值模式（LBP）和灰度共生矩阵（GLCM）特征表示，形态区域特征则为场景表征提供形状信息。同时，深度语义特征从EfficientNetV2-B0中学习获得。为有效融合这些特征，本文提出了一种新颖的多头自注意力融合机制，用于学习纹理、形态和语义特征之间的显式特征依赖关系，从而获得紧凑且具有判别力的特征表示。实验评估使用完整的MLRSNet数据集，包含全部46个场景类别和46,000幅图像，每类选取1,000幅图像以确保均衡且全面的实验设置。所提框架实现了99.98%的平均五折准确率，在完整的多类别且视觉相似的遥感场景集上展现出高度一致的学习性能。在相同实验设置下与已有预训练CNN和基于Transformer的模型进行对比评估，并结合逐组件消融分析，进一步验证了手工描述符、EfficientNetV2语义嵌入和Transformer引导融合机制的贡献。该融合方法有效提升了视觉相似LULC类别间的类间判别能力，是从遥感图像进行大规模LULC制图、城市增长分析、环境监测等的有力工具。",null,"International Journal of Electronics and Communication Engineering","2026-09-11T00:00:00Z","论文",10,false,63,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},8,18,16,12,9,1,"方法新颖、数据规模大且精度极高，但属遥感场景分类的通用技术论文，对农业信息化的直接产业影响有限，可作为技术前沿收录。",[25],{"name":10,"url":6},[27,28,29,30],"智慧农业","农业人工智能","遥感","土地利用",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":36},"needs_review","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":14,"reason":61},[38,46,51,56],{"code":39,"score":40,"supported":41,"title":42,"abstract":44,"tags":45},"I3",15,true,[43],"remote sensing",[29,43],[29],{"code":47,"score":22,"supported":14,"title":48,"abstract":49,"tags":50},"H6",[],[],[30],{"code":52,"score":22,"supported":14,"title":53,"abstract":54,"tags":55},"I1",[],[],[27],{"code":57,"score":22,"supported":14,"title":58,"abstract":59,"tags":60},"I2",[],[],[28],"农业相关性需要复核",[63,64],"农业人工智能 土地利用 智慧农业 遥感","农业人工智能 土地利用","农业人工智能土地利用智慧农业遥感-2428",2,"10.14445\u002F23488549\u002Fijece-v13i8p108",{"doi":67,"openalex_id":69,"authors":70,"venue":10,"cited_by_count":75,"oa_url":76,"card":77,"direction":81,"ingested_from":83},"W7212235225",[71,73],{"name":72,"orcid":9},"Cheruku Bujji Babu",{"name":74,"orcid":9},"Gurumurthy Hari Krishnan",0,"https:\u002F\u002Fwww.internationaljournalssrg.org\u002F..\u002FIJECE\u002F2026\u002FVolume13-Issue8\u002FIJECE-V13I8P108.pdf",{"tldr":78,"method":79,"finding":80,"direction":81,"opportunity":82},"提出Transformer融合手工纹理形态特征与EfficientNetV2深度特征的遥感场景分类模","LBP、GLCM与形态特征结合EfficientNetV2-B0，用多头自注意力","平均五折准确率达99.98%，融合机制显著提升相似地物类间区分能力。","农业遥感与作物表型","可探索轻量化融合与跨数据集泛化，并迁移至作物精细分类与长时序LULC监测。","openalex","2026-09-14T23:30:26.024527Z",{"total":86,"page":22,"page_size":86,"items":87},6,[88,159,225,277,391,462],{"id":89,"title":90,"url":91,"summary":92,"summary_zh":93,"content":9,"source_name":94,"source_url":91,"published_at":95,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":96,"score_detail":97,"sources":101,"tags":103,"primary_topic":105,"secondary_topics":110,"classification":111,"search_phrases":136,"slug":139,"view_count":66,"doi":140,"paper":141,"created_at":158},4497,"A SwiGLU enhanced ConvNeXt framework for multispectral Sentinel-2 land use and land cover classification","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-67985-x","Land use and land cover (LCLU) classification from multispectral satellite imagery is important for applications such as urban planning, environmental monitoring, agriculture, and disaster management. Existing deep learning based approaches have improved LCLU; however, most of them utilize only the red, green, and blue (RGB) bands of multispectral sentinel-2 imagery, thereby underutilizing the complementary spectral information available in the near-infrared (NIR), short-wave infrared (SWIR), and derived spectral indices such as normalized difference built-up Index (NDBI), Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI). In this work, we propose a convolutional neural network (CNN), SwigNeXT, based on a modified ConvNeXt architecture for the classification of multispectral Sentinel-2 imagery using spectral band combinations which are RGB, NIR–Red–Green, SWIR–NIR–Red, and derived index combination NDBI–NDVI–NDWI rather than using only the RGB. The SwigNeXT incorporates SwiGLU-based gated feature modulation to improve spectral spatial feature representation. The final classification is obtained by ensembling the predictions of the three spectral band combinations and the derived index combination. Experimental results show that the proposed ensemble framework achieved an overall accuracy of 99.19% with a Kappa coefficient ( \\(\\kappa \\) ) of 0.9909, outperforming conventional CNNs, transfer learning based CNNs and transformer based approaches. A gradient based SHapley Additive exPlanations framework was further integrated to analyse spatial and spectral feature contributions. The proposed framework was further validated on Sentinel-2 imagery from the Delhi–NCR region, to examine its applicability under geographically distinct real world imaging conditions.","多光谱卫星影像的土地利用与土地覆盖（LCLU）分类对城市规划、环境监测、农业和灾害管理等应用具有重要意义。现有的基于深度学习的方法改进了LCLU分类；然而，大多数方法仅利用多光谱Sentinel-2影像的红、绿、蓝（RGB）波段，从而未能充分利用近红外（NIR）、短波红外（SWIR）以及归一化差异建成区指数（NDBI）、归一化差异植被指数（NDVI）和归一化差异水体指数（NDWI）等衍生光谱指数中可用的互补光谱信息。在本研究中，我们提出了一种基于改进ConvNeXt架构的卷积神经网络（CNN）——SwigNeXT，用于多光谱Sentinel-2影像分类，采用RGB、NIR–Red–Green、SWIR–NIR–Red等光谱波段组合以及NDBI–NDVI–NDWI衍生指数组合，而非仅使用RGB。SwigNeXT引入了基于SwiGLU的门控特征调制，以改进光谱空间特征表示。最终分类通过集成三种光谱波段组合和衍生指数组合的预测结果获得。实验结果表明，所提出的集成框架达到了99.19%的总体精度，Kappa系数（\\(\\kappa\\)）为0.9909，优于传统CNN、基于迁移学习的CNN以及基于Transformer的方法。进一步集成了基于梯度的SHapley加性解释框架，以分析空间和光谱特征贡献。所提出的框架在德里–NCR地区的Sentinel-2影像上进一步验证，以检验其在地理上不同的真实成像条件下的适用性。","Scientific Reports","2026-10-07T00:00:00Z",81,{"impact":18,"substance":98,"depth":18,"authority":99,"freshness":21,"relevant":22,"comment":100},22,14,"提出融合SwiGLU门控与多光谱波段组合的ConvNeXt集成框架，在Sentinel-2土地利用分类上达99.19%精度，方法新颖且对农业遥感监测有实用价值。",[102],{"name":94,"url":91},[27,28,29,104,30],"NDVI",{"code":39,"slug":106,"name":107,"path":108,"parent_code":109},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":112,"locked":14,"version":34,"method":35,"evidence":113},"classified",{"candidates":114,"agricultural_evidence":41},[115,121,128,132],{"code":39,"score":116,"supported":41,"title":117,"abstract":119,"tags":120},13,[118],"multispectral",[118],[104,29],{"code":57,"score":122,"supported":41,"title":123,"abstract":124,"tags":127},7,[],[125,126],"深度学习","deep learning",[28],{"code":47,"score":22,"supported":14,"title":129,"abstract":130,"tags":131},[],[],[30],{"code":52,"score":22,"supported":14,"title":133,"abstract":134,"tags":135},[],[],[27],[137,138],"Sentinel-2 多光谱 土地覆盖分类","ConvNeXt SwiGLU 遥感分类","Sentinel-2多光谱土地覆盖分类-4497","10.1038\u002Fs41598-026-67985-x",{"doi":140,"openalex_id":142,"authors":143,"venue":94,"cited_by_count":75,"oa_url":151,"card":152,"direction":157,"ingested_from":83},"W7220869344",[144,146,148],{"name":145,"orcid":9},"Neeraj Kumar",{"name":147,"orcid":9},"Navin Rajpal",{"name":149,"orcid":150},"Pramod Kumar Soni","https:\u002F\u002Forcid.org\u002F0000-0003-0632-5044","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-67985-x_reference.pdf",{"tldr":153,"method":154,"finding":155,"direction":81,"opportunity":156},"提出SwiGLU增强的ConvNeXt框架，融合多光谱波段与指数集成分类Sentinel-2土地利用","改进ConvNeXt加SwiGLU门控，用RGB、NIR、SWIR及NDVI\u002FN","集成框架总体精度99.19%、Kappa 0.9909，优于CNN、迁移学习和Transformer","可探索多光谱指数组合与门控机制在作物精细分类及跨区域迁移中的泛化能力。","智慧农业 \u002F 农业物联网","2026-10-09T23:30:12.234854Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":164,"content":9,"source_name":165,"source_url":162,"published_at":166,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":167,"score_detail":168,"sources":170,"tags":172,"primary_topic":175,"secondary_topics":179,"classification":180,"search_phrases":208,"slug":211,"view_count":75,"doi":212,"paper":213,"created_at":224},5588,"Certified Temporal Fusion of Artificial Intelligence Climate Analytics for Crop Failure Early Warning Under Sparse Agricultural Sensors: Error Bounds and Famine Relief Targeting","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545489","Sparse agricultural sensor networks across sub-Saharan Africa leave crop-failure early-warning systems with too little ground observation to support reliable famine relief targeting. The framework treats sensor sparsity as a missing-data problem with a known observation operator and propagates climate-analytics uncertainty through a temporal Kalman-Buys filter whose gain is constrained by a certified risk envelope. Using NASA POWER monthly reanalysis for Accra, Ghana (2000-2023, 312 observations), the analysis establishes a mean temperature of 26.521 C and a warming trend of 0.1622 C per decade, which calibrates the climate-analytics prior. The derived bounds show that relief-targeting error scales with the square root of sensor density and with the Lipschitz constant of the crop-response function, yielding an explicit sensor-placement rule for a target misclassification rate. The contribution is a certified, assumption-explicit bridge between climate analytics and famine relief targeting that states the conditions under which early warning is trustworthy.","撒哈拉以南非洲稀疏的农业传感器网络使得作物歉收预警系统缺乏足够的地面观测数据，难以支撑可靠的饥荒救援目标定位。该框架将传感器稀疏性视为具有已知观测算子的缺失数据问题，并通过时间Kalman-Buys滤波器传播气候分析不确定性，该滤波器的增益受经认证的风险包络约束。利用NASA POWER对加纳阿克拉的月度再分析数据（2000—2023年，312个观测值），分析确定了平均气温为26.521°C、每十年0.1622°C的增暖趋势，据此校准了气候分析先验。推导出的界限表明，救援目标定位误差随传感器密度的平方根以及作物响应函数的Lipschitz常数缩放，从而为目标误分类率给出了明确的传感器布设规则。该研究的贡献在于构建了一个经认证的、假设明确的气候分析与饥荒救援目标定位之间的桥梁，阐明了早期预警可信赖的条件。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",74,{"impact":20,"substance":98,"depth":18,"authority":20,"freshness":13,"relevant":22,"comment":169},"该研究提出一种带误差界认证的时序融合方法，用于稀疏传感器条件下的作物歉收预警与饥荒救援瞄准，方法新颖、结论明确，但案例局限于加纳阿克拉，产业影响有限，适合作为技术前沿条目收录。",[171],{"name":165,"url":162},[27,28,173,29,174],"粮食安全","气候分析",{"code":57,"slug":176,"name":177,"path":178,"parent_code":109},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":112,"locked":14,"version":34,"method":35,"evidence":181},{"candidates":182,"agricultural_evidence":41},[183,188,195,200,204],{"code":57,"score":21,"supported":41,"title":184,"abstract":186,"tags":187},[185],"artificial intelligence",[],[28],{"code":189,"score":190,"supported":41,"title":191,"abstract":192,"tags":194},"I5",3,[],[193],"农业传感",[],{"code":196,"score":22,"supported":14,"title":197,"abstract":198,"tags":199},"A8",[],[],[173],{"code":52,"score":22,"supported":14,"title":201,"abstract":202,"tags":203},[],[],[27],{"code":39,"score":22,"supported":14,"title":205,"abstract":206,"tags":207},[],[],[29],[209,210],"NASA POWER 加纳 气候分析","作物歉收 早期预警 传感器","NASAPOWER加纳气候分析-5588","10.5281\u002Fzenodo.23545489",{"doi":212,"openalex_id":214,"authors":215,"venue":165,"cited_by_count":75,"oa_url":162,"card":218,"direction":223,"ingested_from":83},"W7223111766",[216],{"name":217,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":219,"method":220,"finding":221,"direction":81,"opportunity":222},"提出带误差界的时间融合框架，在稀疏传感器下用气候分析预警作物歉收。","卡尔曼-布西滤波+NASA POWER再分析数据，风险包络约束增益。","救济瞄准误差随传感器密度平方根和作物响应Lipschitz常数缩放，给出布点规则。","可将该认证误差界框架扩展到多作物多区域，结合卫星遥感弥补地面传感器稀疏。","农业人工智能与决策模型","2026-10-22T11:21:02.682497Z",{"id":226,"title":227,"url":228,"summary":229,"summary_zh":230,"content":9,"source_name":165,"source_url":228,"published_at":166,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":231,"score_detail":232,"sources":236,"tags":238,"primary_topic":241,"secondary_topics":242,"classification":244,"search_phrases":261,"slug":264,"view_count":75,"doi":265,"paper":266,"created_at":276},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。",67,{"impact":17,"substance":233,"depth":234,"authority":20,"freshness":13,"relevant":22,"comment":235},20,17,"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。",[237],{"name":165,"url":228},[27,28,239,29,240],"产量预测","可解释性",{"code":57,"slug":176,"name":177,"path":178,"parent_code":109},[243],{"code":39,"slug":106,"name":107,"path":108,"parent_code":109},{"status":112,"locked":14,"version":34,"method":35,"evidence":245},{"candidates":246,"agricultural_evidence":41},[247,253,257],{"code":57,"score":20,"supported":41,"title":248,"abstract":250,"tags":252},[249],"computer vision",[251],"计算机视觉",[28],{"code":39,"score":17,"supported":41,"title":254,"abstract":255,"tags":256},[],[29,43],[239,29],{"code":52,"score":22,"supported":14,"title":258,"abstract":259,"tags":260},[],[],[27],[262,263],"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":265,"openalex_id":267,"authors":268,"venue":165,"cited_by_count":75,"oa_url":228,"card":271,"direction":81,"ingested_from":83},"W7223114002",[269],{"name":270,"orcid":9},"Kadiatou Barry",{"tldr":272,"method":273,"finding":274,"direction":81,"opportunity":275},"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":278,"title":279,"url":280,"summary":281,"summary_zh":282,"content":9,"source_name":283,"source_url":280,"published_at":166,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":284,"score_detail":285,"sources":287,"tags":289,"primary_topic":292,"secondary_topics":298,"classification":304,"search_phrases":362,"slug":365,"view_count":75,"doi":366,"paper":367,"created_at":390},5564,"Dynamic thermal imaging for crop water stress detection across phenological stages: Enhancing irrigation scheduling precision","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.17728","Thermal remote sensing and derived indices such as the crop water stress index (CWSI) can assess crop water status and support precision irrigation. However, most operational and artificial intelligence (AI)-based approaches rely on fixed, season-long thresholds to interpret canopy–air temperature differences and often overlook the influence of crop phenology. This review synthesises evidence from grapevine, wheat, maize, potato and several other crops on how developmental stage affects the non-water-stressed baseline (NWSB), CWSI thresholds and irrigation-scheduling algorithms. It covers CWSI theory and estimation practices; crop-specific, phenology-dependent behaviour of baselines and thresholds; a comparison of threshold-based, machine learning, Internet of Things (IoT), digital twin and Food and Agriculture Organization (FAO)-56 approaches with respect to crop phenology; and a conceptual framework for phenology-aware scheduling. Across the reviewed crops, baseline behaviour generally varied systematically across the growing season, the relationship between CWSI and crop water status generally strengthened after canopy closure and CWSI measured during reproductive stages was generally most closely related to yield. A quantitative audit of 56 AI-, thermal-imaging-, or CWSI-based studies found that 78.6 % either did not explicitly incorporate crop phenology or relied on day of year as a temporal proxy, whereas only 5.4 % explicitly encoded phenological stage. The proposed framework considers phenology explicitly in baseline estimation, threshold setting and data fusion or machine learning for irrigation scheduling; the framework will require multi-year, multi-site field validation before operational use. Future research should prioritise standardised phenology definitions and long-term, multi-location studies to establish and validate stage-specific parameters.","热红外遥感及其衍生的作物水分胁迫指数（crop water stress index, CWSI）等指标可评估作物水分状况并支持精准灌溉。然而，大多数业务化方法和基于人工智能（artificial intelligence, AI）的方法依赖固定的全生育期阈值来解释冠层—空气温差，且往往忽视作物物候的影响。本文综述了葡萄、小麦、玉米、马铃薯及其他若干作物在发育阶段如何影响非水分胁迫基线（non-water-stressed baseline, NWSB）、CWSI阈值和灌溉调度算法的相关证据。综述内容涵盖CWSI理论与估算实践；基线和阈值的作物特异性、物候依赖性行为；基于阈值、机器学习、物联网（Internet of Things, IoT）、数字孪生及联合国粮农组织（Food and Agriculture Organization, FAO）-56等方法在作物物候方面的比较；以及物候感知调度的概念框架。在所综述的作物中，基线行为在整个生长季通常呈系统性变化，CWSI与作物水分状况之间的关系在冠层封垄后总体增强，且在生殖阶段测得的CWSI与产量的关系总体最为密切。对56项基于AI、热成像或CWSI的研究进行的定量审查发现，78.6%的研究要么未明确纳入作物物候，要么依赖年积日作为时间代理变量，而仅5.4%的研究明确编码了物候阶段。所提出的框架在基线估算、阈值设定以及用于灌溉调度的数据融合或机器学习中明确考虑物候；该框架在投入业务应用前尚需多年、多站点的田间验证。未来研究应优先建立标准化的物候定义，并开展长期、多地点研究以建立和验证阶段特异性参数。","Plant Science Today",79,{"impact":18,"substance":98,"depth":18,"authority":20,"freshness":21,"relevant":22,"comment":286},"系统综述热成像与CWSI在物候期感知灌溉中的应用，含56项研究量化审计，方法学价值突出，但属综述类论文，影响偏学术层面。",[288],{"name":283,"url":280},[27,28,29,290,291],"作物水分胁迫","精准灌溉",{"code":293,"slug":294,"name":295,"path":296,"parent_code":297},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[299,300],{"code":57,"slug":176,"name":177,"path":178,"parent_code":109},{"code":189,"slug":301,"name":302,"path":303,"parent_code":109},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":112,"locked":14,"version":34,"method":35,"evidence":305},{"candidates":306,"agricultural_evidence":41},[307,312,318,325,331,335,342,349,356],{"code":293,"score":40,"supported":41,"title":308,"abstract":309,"tags":311},[294],[310,294],"灌溉",[291],{"code":57,"score":13,"supported":41,"title":313,"abstract":314,"tags":317},[],[315,316,185],"机器学习","machine learning",[28],{"code":189,"score":21,"supported":41,"title":319,"abstract":320,"tags":324},[],[321,322,323],"物联网","internet of things","IoT",[],{"code":52,"score":122,"supported":41,"title":326,"abstract":327,"tags":330},[],[328,329],"数字孪生","digital twin",[27],{"code":39,"score":122,"supported":41,"title":332,"abstract":333,"tags":334},[],[29,43],[29],{"code":336,"score":86,"supported":41,"title":337,"abstract":338,"tags":341},"A2",[],[339,340],"小麦","wheat",[],{"code":343,"score":86,"supported":41,"title":344,"abstract":345,"tags":348},"A3",[],[346,347],"玉米","maize",[],{"code":350,"score":86,"supported":41,"title":351,"abstract":352,"tags":355},"A5",[],[353,354],"马铃薯","potato",[],{"code":357,"score":190,"supported":41,"title":358,"abstract":359,"tags":361},"B2",[],[360],"葡萄",[],[363,364],"热成像 作物水分胁迫","CWSI 灌溉调度","热成像作物水分胁迫-5564","10.14719\u002Fpst.17728",{"doi":366,"openalex_id":368,"authors":369,"venue":283,"cited_by_count":75,"oa_url":280,"card":385,"direction":157,"ingested_from":83},"W7223088921",[370,373,376,379,382],{"name":371,"orcid":372},"R M Jeya","https:\u002F\u002Forcid.org\u002F0009-0001-3621-8533",{"name":374,"orcid":375},"P. C. Prabu","https:\u002F\u002Forcid.org\u002F0000-0002-7237-9481",{"name":377,"orcid":378},"K P Ragunath","https:\u002F\u002Forcid.org\u002F0000-0002-7851-4437",{"name":380,"orcid":381},"P. Kannan","https:\u002F\u002Forcid.org\u002F0000-0001-7003-3535",{"name":383,"orcid":384},"P. M. Shanmugam","https:\u002F\u002Forcid.org\u002F0000-0002-6706-8419",{"tldr":386,"method":387,"finding":388,"direction":81,"opportunity":389},"综述物候期对热成像CWSI阈值的影响，提出物候感知灌溉调度框架。","综述葡萄、小麦、玉米等作物的热遥感CWSI研究，并审计56项AI\u002F热成像研究。","78.6%研究未显式纳入物候，仅5.4%编码物候期；CWSI与产量在生殖期关联最强。","可开展多站点多年物候期特异性CWSI阈值标定与标准化物候定义研究。","2026-10-22T11:20:24.526683Z",{"id":392,"title":393,"url":394,"summary":395,"summary_zh":396,"content":9,"source_name":397,"source_url":394,"published_at":398,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":399,"score_detail":400,"sources":402,"tags":404,"primary_topic":406,"secondary_topics":411,"classification":413,"search_phrases":443,"slug":446,"view_count":75,"doi":447,"paper":448,"created_at":461},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z",78,{"impact":18,"substance":98,"depth":18,"authority":20,"freshness":17,"relevant":22,"comment":401},"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[403],{"name":397,"url":394},[27,28,405,239,29],"水稻",{"code":407,"slug":408,"name":405,"path":409,"parent_code":410},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[412],{"code":39,"slug":106,"name":107,"path":108,"parent_code":109},{"status":112,"locked":14,"version":34,"method":35,"evidence":414},{"candidates":415,"agricultural_evidence":41},[416,420,424,429,435,439],{"code":407,"score":40,"supported":41,"title":417,"abstract":418,"tags":419},[408],[405,408],[405],{"code":39,"score":17,"supported":41,"title":421,"abstract":422,"tags":423},[],[29,43],[239,29],{"code":196,"score":86,"supported":41,"title":425,"abstract":426,"tags":428},[],[173,427],"food security",[],{"code":430,"score":190,"supported":41,"title":431,"abstract":432,"tags":434},"J1",[],[433],"农业规划",[],{"code":52,"score":22,"supported":14,"title":436,"abstract":437,"tags":438},[],[],[27],{"code":57,"score":22,"supported":14,"title":440,"abstract":441,"tags":442},[],[],[28],[444,445],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":447,"openalex_id":449,"authors":450,"venue":397,"cited_by_count":75,"oa_url":394,"card":456,"direction":81,"ingested_from":83},"W7222942064",[451,453],{"name":452,"orcid":9},"Nayana Venkatesh",{"name":454,"orcid":455},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":457,"method":458,"finding":459,"direction":81,"opportunity":460},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","2026-10-20T23:30:19.292634Z",{"id":463,"title":464,"url":465,"summary":466,"summary_zh":467,"content":9,"source_name":468,"source_url":465,"published_at":398,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":469,"score_detail":470,"sources":472,"tags":474,"primary_topic":476,"secondary_topics":477,"classification":478,"search_phrases":494,"slug":497,"view_count":75,"doi":498,"paper":499,"created_at":522},5393,"IMPLEMENTATION OF META-HEURISTIC OPTIMIZATION ALGORITHMS IN CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT DETECTION AND CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr251214006i","CNNs have grown to form the backbone of modern computer vision systems, producing outstanding object detection and classification performance within diverse application domains. However, the manual development of suitable CNN architectures and, correspondingly, the selection of optimal hyperparameter sets are still inconvenient and time-consuming processes. The aim of this survey is to contribute a comprehensive review regarding how meta-heuristic optimization algorithms such as Genetic Algorithms, Particle Swarm Optimization, and other swarm intelligence-based methods are embedded in the CNN-based pipelines with the intent to achieve better detection and classification results. We gather recent progress regarding automated architecture search, hyperparameter tuning, model compression, and ensemble learning. We identify how hybrid optimization approaches consistently yield superior accuracy with computational efficiency by systematically reviewing applications in medical imaging, agriculture, vehicular recognition, and remote sensing. Optimized CNN models outperform their baseline versions many times, especially in health diagnostics, where several fine-tuned architectures reach accuracies greater than 99%. This survey provides a structured and updated overview of methodological developments, implementation practices, and emerging research directions for those practitioners and researchers who will apply meta-heuristic optimization within deep learning-based computer vision systems.","卷积神经网络（CNNs）已发展成为现代计算机视觉系统的核心骨干，在多个应用领域中展现出卓越的目标检测与分类性能。然而，人工设计合适的CNN架构并相应地选择最优超参数集仍然是繁琐且耗时的过程。本综述旨在全面回顾遗传算法、粒子群优化及其他群体智能方法等元启发式优化算法如何嵌入基于CNN的流程中以获得更优的检测与分类结果。我们汇集了自动化架构搜索、超参数调优、模型压缩和集成学习方面的最新进展。通过系统梳理在医学影像、农业、车辆识别和遥感领域的应用，我们揭示了混合优化方法如何以计算效率持续实现更优的精度。优化后的CNN模型在多数情况下远超其基线版本，尤其在健康诊断领域，若干精细调优的架构达到了超过99%的准确率。本综述为将在基于深度学习的计算机视觉系统中应用元启发式优化的从业者和研究者，提供了关于方法学进展、实施实践和新兴研究方向的结构化且更新的概述。","Facta Universitatis Series Automatic Control and Robotics",61,{"impact":17,"substance":18,"depth":40,"authority":20,"freshness":17,"relevant":22,"comment":471},"综述系统梳理元启发式优化在CNN视觉任务中的嵌入方法，含农业应用，但属通用方法综述，非农业专属突破。",[473],{"name":468,"url":465},[27,28,475,29],"目标检测",{"code":57,"slug":176,"name":177,"path":178,"parent_code":109},[],{"status":112,"locked":14,"version":34,"method":35,"evidence":479},{"candidates":480,"agricultural_evidence":41},[481,486,490],{"code":57,"score":482,"supported":41,"title":483,"abstract":484,"tags":485},11,[],[475,125,251,126,249],[28,475],{"code":39,"score":122,"supported":41,"title":487,"abstract":488,"tags":489},[],[29,43],[29],{"code":52,"score":22,"supported":14,"title":491,"abstract":492,"tags":493},[],[],[27],[495,496],"元启发式优化 卷积神经网络","CNN 目标检测","元启发式优化卷积神经网络-5393","10.22190\u002Ffuacr251214006i",{"doi":498,"openalex_id":500,"authors":501,"venue":468,"cited_by_count":75,"oa_url":465,"card":517,"direction":81,"ingested_from":83},"W7222920697",[502,505,508,511,514],{"name":503,"orcid":504},"Nikola Ivačko","https:\u002F\u002Forcid.org\u002F0000-0003-4367-119X",{"name":506,"orcid":507},"Ivan S Ciric","https:\u002F\u002Forcid.org\u002F0000-0003-0430-8937",{"name":509,"orcid":510},"Milica Tasić","https:\u002F\u002Forcid.org\u002F0009-0001-9160-6379",{"name":512,"orcid":513},"Ljiljana Radović","https:\u002F\u002Forcid.org\u002F0000-0002-4099-1289",{"name":515,"orcid":516},"Žarko Ćojbašić","https:\u002F\u002Forcid.org\u002F0000-0002-4581-1048",{"tldr":518,"method":519,"finding":520,"direction":223,"opportunity":521},"综述元启发式算法嵌入CNN流程以优化目标检测与分类的研究进展。","系统综述遗传算法、粒子群等群智能方法用于CNN架构搜索与超参调优。","混合优化方法在医学影像、农业等领域兼顾精度与效率，部分模型准确率超99%。","农业场景下元启发式优化CNN的架构搜索与轻量化部署仍缺乏系统基准与田间验证。","2026-10-20T23:30:19.233167Z"]