[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3060":3,"related-3060":59},{"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":58},3060,"Geospatial Intelligence for Peri-Urban Land-Use Conflicts: Evaluating Agricultural Suitability against Rapid Urbanisation using the Analytical Hierarchy Process and Cloud Computing","https:\u002F\u002Fdoi.org\u002F10.59543\u002F6mpcwr41","This paper presents a geospatial multi-criteria evaluation of agricultural potential in the suburban region of Bapatla using eight physical and land-use characteristics: elevation, slope, road accessibility, proximity to water bodies, Land Surface Temperature (LST), Normalised Difference Vegetation Index (NDVI), Land Use\u002FLand Cover (LULC), and soil texture, processed using Google Earth Engine. The Analytic Hierarchy Process (AHP) was used to determine the relative weights of each criterion. NDVI received the highest weight (26.33%), followed by LST, slope, and proximity to water bodies (14.96% each), while elevation received the lowest weight (4.6%) due to the region's flat terrain. Weighted overlay analysis classified the 142.25 km² study area into Suitable (108.90 km²; 76.55%), Not Suitable (32.60 km²; 22.92%), and Highly Suitable (0.75 km²; 0.53%) categories. Suitable areas are mainly distributed across the southern and peripheral agricultural zones, whereas unsuitable areas are concentrated within Bapatla Urban and its surroundings. The limited extent of highly suitable land highlights the scarcity of optimal agricultural sites. The results reveal land-use conflicts driven primarily by urbanisation rather than environmental constraints. The AHP-weighted suitability map provides an evidence-based tool for agricultural land conservation, water-resource management, and sustainable urban expansion.","本文基于八项自然与土地利用特征，对巴帕特拉（Bapatla）郊区农业潜力进行了地理空间多准则评价，这些特征包括：海拔、坡度、道路可达性、距水体远近、地表温度（LST）、归一化植被指数（NDVI）、土地利用\u002F土地覆盖（LULC）以及土壤质地，并利用Google Earth Engine进行处理。采用层次分析法（AHP）确定各准则的相对权重。NDVI权重最高（26.33%），其次为LST、坡度和距水体远近（均为14.96%），而海拔因该地区地形平坦权重最低（4.6%）。加权叠加分析将142.25 km²的研究区划分为适宜（108.90 km²；76.55%）、不适宜（32.60 km²；22.92%）和高适宜（0.75 km²；0.53%）三类。适宜区主要分布于南部及外围农业区，而不适宜区集中于巴帕特拉城区及其周边。高适宜土地面积有限，凸显了优质农业用地的稀缺性。结果表明，土地利用冲突主要由城市化驱动，而非环境限制。基于AHP的适宜性地图为农业用地保护、水资源管理和可持续城市扩张提供了循证工具。",null,"Journal of Urban Intelligence and Smart Systems","2026-09-19T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,13,8,1,"该论文利用遥感与AHP方法评估城郊农业用地冲突，方法新颖、数据详实，对农业土地保护有参考价值，但属细分领域研究，影响范围有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业遥感","农业信息化","遥感","土地利用",[33,34],"Bapatla 农业用地 城市化","Google Earth Engine 农业适宜性","Bapatla农业用地城市化-3060",0,"10.59543\u002F6mpcwr41",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":49,"card":50,"direction":56,"ingested_from":57},"W7213644047",[41,43,45,47],{"name":42,"orcid":9},"Sreerama Naik Naik S R",{"name":44,"orcid":9},"T K Prasad",{"name":46,"orcid":9},"Feba Jose Jasmine",{"name":48,"orcid":9},"Jayapal G","https:\u002F\u002Fjuiss.org\u002Findex.php\u002Fjuiss\u002Farticle\u002Fdownload\u002F366\u002F231",{"tldr":51,"method":52,"finding":53,"direction":54,"opportunity":55},"用AHP与云平台评估印度Bapatla城郊农业适宜性，揭示城市化引发的土地利用冲突。","Google Earth Engine处理8个因子，AHP加权叠加分析142.2","76.55%区域适宜农业，但高度适宜仅0.53%，冲突主因是城市化而非环境限制。","农业遥感与作物表型","可引入时序遥感与动态城市扩张模拟，构建城郊农业保护与城市增长协同优化模型。","智慧农业 \u002F 农业物联网","openalex","2026-09-21T23:30:09.448414Z",{"total":60,"page":22,"page_size":60,"items":61},6,[62,99,134,164,207,231],{"id":63,"title":64,"url":65,"summary":66,"summary_zh":67,"content":9,"source_name":68,"source_url":65,"published_at":69,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":70,"score_detail":71,"sources":76,"tags":78,"search_phrases":80,"slug":83,"view_count":36,"doi":84,"paper":85,"created_at":98},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。","International Journal of Electronics and Communication Engineering","2026-09-11T00:00:00Z",63,{"impact":21,"substance":72,"depth":73,"authority":17,"freshness":74,"relevant":22,"comment":75},18,16,9,"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。",[77],{"name":68,"url":65},[27,79,30,31],"农业人工智能",[81,82],"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","10.14445\u002F23488549\u002Fijece-v13i8p108",{"doi":84,"openalex_id":86,"authors":87,"venue":68,"cited_by_count":36,"oa_url":92,"card":93,"direction":54,"ingested_from":57},"W7212235225",[88,90],{"name":89,"orcid":9},"Cheruku Bujji Babu",{"name":91,"orcid":9},"Gurumurthy Hari Krishnan","https:\u002F\u002Fwww.internationaljournalssrg.org\u002F..\u002FIJECE\u002F2026\u002FVolume13-Issue8\u002FIJECE-V13I8P108.pdf",{"tldr":94,"method":95,"finding":96,"direction":54,"opportunity":97},"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。","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。","2026-09-14T23:30:26.024527Z",{"id":100,"title":101,"url":102,"summary":103,"summary_zh":9,"content":9,"source_name":104,"source_url":9,"published_at":105,"category":12,"cover_url":9,"hotness":13,"is_selected":106,"score":107,"score_detail":108,"sources":114,"tags":116,"search_phrases":120,"slug":123,"view_count":36,"doi":9,"paper":124,"created_at":133},3125,"Full-Season Agentic Farm System FAIRY: Event-Driven Multi-Agent Orchestration for Soybean Production（FAIRY 全季节智能体农场系统：大豆生产的事件驱动多智能体编排）","https:\u002F\u002Faiagentstore.ai\u002Fai-agent-news\u002Ftopic\u002Fagriculture-food\u002F2026-08-11","哈尔滨工业大学研究人员发布并部署全栈、事件驱动的智能体引擎 FAIRY 于中国运行中的大豆研究农场。FAIRY 集成传感器、无人机、卫星植被产品、机械 API、作物过程模型与多智能体编排层，执行起垄→播种→灌溉→病虫害防治→收获→干燥→存储工作流，并在 64 垄研究场上跨 100 个全季节场景评估 9 个智能体控制器。这是智能体系统能够在大农业时间尺度和延迟结果下进行推理的最清晰演示之一，将农业中的智能体工作从实验室演示推进到全过程评估。同期 arXiv 推出 HarvestBench 基准将 LLM 驱动智能体置于农场网格世界（拖拉机面临动物选择绕行或碾压），结果显示模型差异巨大、对道德简报高度敏感、避免意愿具有可衡量的价格弹性。","Harbin Institute of Technology \u002F arXiv","2026-09-18T00:00:00Z",true,89,{"impact":109,"substance":110,"depth":111,"authority":112,"freshness":74,"relevant":22,"comment":113},24,23,19,14,"哈工大在真实大豆农场部署全季节事件驱动多智能体系统并配套 HarvestBench 基准，是农业智能体从演示走向全过程评估的标志性进展，专业深度与信息增量俱佳。",[115],{"name":104,"url":102},[27,117,79,28,118,119],"无人农场","多智能体","大豆生产",[121,122],"哈工大 FAIRY 大豆","HarvestBench 智能体 农场","哈工大FAIRY大豆-3125",{"doi":9,"openalex_id":9,"authors":125,"venue":9,"cited_by_count":36,"oa_url":9,"card":126,"direction":130,"ingested_from":132},[],{"tldr":127,"method":128,"finding":129,"direction":130,"opportunity":131},"部署全季节事件驱动多智能体系统FAIRY，在大豆农场完成从起垄到存储的全流程评估。","集成传感器、无人机、卫星、作物模型与机械API，用9个智能体控制器在64垄100","智能体系统能在大农业时间尺度下推理，模型差异大且对道德简报敏感。","农业人工智能与决策模型","可研究多智能体在长周期、延迟反馈农业任务中的鲁棒性与伦理约束机制。","agent","2026-09-22T00:05:38.611717Z",{"id":135,"title":136,"url":137,"summary":138,"summary_zh":9,"content":9,"source_name":139,"source_url":9,"published_at":140,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":141,"score_detail":142,"sources":146,"tags":148,"search_phrases":152,"slug":155,"view_count":36,"doi":9,"paper":156,"created_at":163},3121,"Optimization of Farmland Management Zoning in the Black Soil Region: A Climate Adaptability Assessment Considering Crop Growth Response and Topographic Characteristics（黑土区农田管理分区优化：考虑作物生长响应与地形特征的气候适应性评估）","https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F18\u002F18\u002F3260","吉林农业大学 Han Yongqi 等联合中科院东北地理与农业生态研究所、东北农业大学在《Remote Sensing》18(18): 3260 发表论文（2026-09-21 发表）。针对精准农业管理分区对单日期影像依赖难以捕捉年际作物环境变化问题，研究评估 29 个特征组合（融合 Sentinel-2 多光谱、PCA、NDVI 和 DEM 数据）在黑土区友谊农场干旱、湿润和融合场景下的气候适应性。实施异构空间注意力网络（HSAN）和 K-means 聚类，以变异系数（CV）评估稳定性与适应性。结果显示 HSAN 在多源融合下优于 K-means，CV 分别为 11.303-14.774% 与 14.823-16.011%；多期 NDVI 数据是主导因素，相对 CV 减少 34.850-53.701%；DEM 贡献有限；PCA 增强稳定性；多期融合在极端气候年份提升分区生态一致性与适用性。","MDPI Remote Sensing","2026-09-21T00:00:00Z",79,{"impact":143,"substance":144,"depth":72,"authority":112,"freshness":13,"relevant":22,"comment":145},15,22,"黑土区精准农业管理分区研究，方法新颖、数据扎实，对农业遥感应用有参考价值。",[147],{"name":139,"url":137},[27,149,150,30,151],"精准农业","黑土区","管理分区",[153,154],"黑土区 管理分区 遥感","Sentinel-2 黑土区 气候适应性","黑土区管理分区遥感-3121",{"doi":9,"openalex_id":9,"authors":157,"venue":9,"cited_by_count":36,"oa_url":9,"card":158,"direction":54,"ingested_from":132},[],{"tldr":159,"method":160,"finding":161,"direction":54,"opportunity":162},"评估黑土区多源遥感特征组合在干旱湿润场景下的农田管理分区气候适应性。","融合Sentinel-2多光谱、NDVI、PCA与DEM，用HSAN和K-mea","HSAN优于K-means，多期NDVI主导稳定性提升，DEM贡献有限，PCA增强稳定性。","可探索多期时序特征与深度聚类在极端气候下的跨区域迁移及分区决策落地。","2026-09-22T00:05:38.189091Z",{"id":165,"title":166,"url":167,"summary":168,"summary_zh":169,"content":9,"source_name":170,"source_url":167,"published_at":140,"category":12,"cover_url":9,"hotness":171,"is_selected":14,"score":172,"score_detail":173,"sources":175,"tags":179,"search_phrases":183,"slug":186,"view_count":36,"doi":187,"paper":188,"created_at":206},3068,"MAPPING LAND USE OF BENUE STATE UNIVERSITY, MAKURDI MAIN CAMPUS, BENUE STATE, NIGERIA USING GEOSPATIAL TECHNIQUES","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22865603","This study examined the spatial distribution and extent of land use types within Benue State University (BSU), Makurdi Main Campus, using Geographic Information System (GIS) and remote sensing techniques. Satellite imagery obtained from the National Space Research and Development Agency (NASRDA) was processed and analyzed in ArcGIS 10.8. Land use classification was achieved through on-screen digitization supported by intensive field survey and ground-truthing. The results reveal a heterogeneous land use structure with a total mapped area of 166.69 hectares. Agricultural land use dominates with 20.35%, followed by residential (15.24%) and forest cover (12.29%). Environmentally sensitive land uses, including forestry, green areas, and marshlands, collectively account for 29.18% of the total mapped area, indicating significant ecological value. Institutional land uses (administrative, educational, and religious) account for 15.50%, while commercial and mixed uses constitute 9.29%. The findings highlight a semi-urban institutional landscape undergoing gradual transformation, with increasing development pressures. The study demonstrates the effectiveness of GIS in land use planning and recommends sustainable land management strategies to balance development with environmental conservation.","本研究利用地理信息系统（GIS）和遥感技术，考察了马库尔迪贝努埃州立大学（BSU）主校区内土地利用类型的空间分布与范围。研究对来自国家空间研究与发展局（NASRDA）的卫星影像在ArcGIS 10.8中进行了处理与分析。土地利用分类通过屏幕数字化完成，并辅以密集的实地调查与地面验证。结果显示，该区域土地利用结构具有异质性，总制图面积为166.69公顷。农业用地占主导地位，为20.35%，其次为住宅用地（15.24%）和林地覆盖（12.29%）。环境敏感型土地利用类型，包括林业用地、绿地和沼泽地，合计占总制图面积的29.18%，表明其具有显著的生态价值。机构用地（行政、教育和宗教）占15.50%，而商业和混合用途占9.29%。研究结果凸显出一个正处于逐步转型中的半城市机构景观，其面临日益增大的开发压力。本研究证明了GIS在土地利用规划中的有效性，并建议采取可持续土地管理策略，以平衡开发与环境保护。","Zenodo (CERN European Organization for Nuclear Research)",25,56,{"impact":60,"substance":73,"depth":20,"authority":17,"freshness":74,"relevant":22,"comment":174},"基于GIS与遥感的校园土地利用分类研究，方法规范、数据具体，但属尼日利亚个案，对国内三农与农业信息化参考价值有限。",[176,177],{"name":170,"url":167},{"name":170,"url":178},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22865602",[30,31,180,181,182],"GIS","土地分类","校园规划",[184,185],"土地分类 土地利用 校园规划 遥感","土地分类 土地利用","土地分类土地利用校园规划遥感-3068","10.5281\u002Fzenodo.22865603",{"doi":187,"openalex_id":189,"authors":190,"venue":170,"cited_by_count":36,"oa_url":167,"card":201,"direction":54,"ingested_from":57},"W7213752705",[191,193,195,197,199],{"name":192,"orcid":9},"Alex S. Ortese",{"name":194,"orcid":9},"Innocent E. Bello",{"name":196,"orcid":9},"I. K. SAMAILA",{"name":198,"orcid":9},"M. ALKALI",{"name":200,"orcid":9},"A. Mahmud",{"tldr":202,"method":203,"finding":204,"direction":54,"opportunity":205},"用GIS和遥感技术绘制尼日利亚贝努埃州立大学主校区土地利用分布图。","NASRDA卫星影像，ArcGIS 10.8屏幕数字化，结合实地调查与地面验证。","农业用地占20.35%居首，环境敏感用地共占29.18%，校园呈半城市化转型压力。","可延伸至校园及城郊农业用地动态监测与生态敏感区保护规划研究。","2026-09-21T23:30:23.914355Z",{"id":208,"title":209,"url":210,"summary":211,"summary_zh":9,"content":9,"source_name":212,"source_url":210,"published_at":213,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":214,"score_detail":215,"sources":217,"tags":219,"search_phrases":222,"slug":225,"view_count":36,"doi":226,"paper":227,"created_at":230},3066,"山东省智慧农业发展的影响因素研究","https:\u002F\u002Fdoi.org\u002F10.64216\u002F3080-1486.26.10.012","山东省智慧农业发展的影响因素研究。社会经济导刊","社会经济导刊","2026-09-20T00:00:00Z",40,{"impact":21,"substance":60,"depth":21,"authority":13,"freshness":21,"relevant":22,"comment":216},"省级期刊论文，主题相关但摘要信息量极少，缺乏方法与数据细节，仅具参考价值。",[218],{"name":212,"url":210},[220,27,29,221],"数字乡村","山东农业",[223,224],"山东 智慧农业 影响因素","农业信息化 山东农业 数字乡村 智慧农业","山东智慧农业影响因素-3066","10.64216\u002F3080-1486.26.10.012",{"doi":226,"openalex_id":228,"authors":229,"venue":212,"cited_by_count":36,"oa_url":9,"card":9,"direction":56,"ingested_from":57},"W7213767051",[],"2026-09-21T23:30:16.624592Z",{"id":232,"title":233,"url":234,"summary":235,"summary_zh":236,"content":9,"source_name":237,"source_url":234,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":238,"score_detail":239,"sources":241,"tags":243,"search_phrases":246,"slug":249,"view_count":36,"doi":250,"paper":251,"created_at":283},3014,"Detecting diurnal dynamics of cotton leaf inclination angle under water-salt stress","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rse.2026.115674","Leaf inclination angle (LIA) dynamics act as a rapid response mechanism to abiotic stress, regulating canopy energy balance and water use efficiency. While the adaptive value of diurnal LIA plasticity (e.g., paraheliotropism) is well-recognized in ecology, most current remote sensing algorithms and ecosystem models still treat canopy architecture as static and neglect stress-induced geometric adjustments. Furthermore, the diurnal dynamics of LIA under combined abiotic stresses, such as concurrent water deficit and salinity, still remain poorly understood. Recent advances in unmanned aerial vehicle (UAV) photogrammetry offer a promising approach for capturing LIA dynamics at high spatial and temporal resolution. However, accurately resolving fine scale, dynamic leaf movements in real environments using UAVs remains challenging. To address these gaps, we developed the Constraint-Assisted Point cloud fusion for Leaf scale Analysis (CAPLA), an integrated UAV analytical workflow that combines deep learning with Structure from Motion (SfM). CAPLA employs 2D semantic masks to strictly constrain 3D mesh reconstruction, effectively mitigating motion-induced artifacts. Independent validation against 19 plot level mean leaf angle (MLA) observations collected at 9:30 am and 12:00 pm yielded an R 2 of 0.89 and an RMSE of 0.9°, supporting plot level MLA estimation under the validated acquisition conditions. CAPLA was subsequently applied across five observation times to characterize diurnal canopy structural dynamics. Importantly, repeated measures analysis of the high frequency observations revealed significant effects of irrigation, salinity, and observation time on MLA, together with a significant irrigation × time interaction ( P = 0.0109), indicating that diurnal MLA trajectories differed among irrigation levels. In contrast, neither the irrigation × salinity interaction ( P = 0.8800) nor the irrigation × salinity × time interaction ( P = 0.9086) was significant. Descriptive differences in within-day variability were nevertheless observed among individual treatment combinations, highlighting the value of time-resolved structural monitoring for characterizing canopy responses to combined water and salinity stresses. These findings highlight the complex structural plasticity of canopies under interacting stresses, emphasizing the critical need to transition from static canopy assumptions to dynamic structural monitoring for improving ecosystem models and precision agriculture.","叶片倾角（LIA）动态变化是植物对非生物胁迫的快速响应机制，调控冠层能量平衡与水分利用效率。尽管昼夜LIA可塑性（如避日运动）的适应价值在生态学中已得到广泛认可，但当前大多数遥感算法和生态系统模型仍将冠层结构视为静态，忽略了胁迫诱导的几何调整。此外，在水分亏缺与盐分胁迫等复合非生物胁迫条件下，LIA的昼夜动态变化仍知之甚少。近年来无人机（UAV）摄影测量技术的进展为在高时空分辨率下捕捉LIA动态提供了有前景的方法。然而，利用无人机在真实环境中精确解析精细尺度的动态叶片运动仍具挑战性。为弥补上述不足，我们开发了约束辅助点云融合叶片尺度分析流程（CAPLA），这是一种集成了深度学习与运动恢复结构（SfM）的无人机综合分析工作流。CAPLA利用二维语义掩膜严格约束三维网格重建，有效减轻了运动诱导的伪影。基于上午9：30和中午12：00采集的19个样地水平平均叶倾角（MLA）观测值进行独立验证，结果R²为0.89，RMSE为0.9°，支持在验证采集条件下进行样地水平MLA估算。随后将CAPLA应用于五个观测时段以表征冠层结构的昼夜动态变化。重要的是，对高频观测的重复测量分析揭示了灌溉、盐分和观测时间对MLA的显著影响，以及显著的灌溉×时间交互效应（P = 0.0109），表明不同灌溉水平下MLA的昼夜变化轨迹存在差异。相比之下，灌溉×盐分交互效应（P = 0.8800）和灌溉×盐分×时间交互效应（P = 0.9086）均不显著。尽管如此，在各处理组合之间仍观察到日内变异性的描述性差异，凸显了时间分辨结构监测在表征冠层对水分与盐分复合胁迫响应方面的价值。这些发现揭示了冠层在交互胁迫下的复杂结构可塑性，强调亟需从静态冠层假设转向动态结构监测，以改进生态系统模型和精准农业。","Remote Sensing of Environment",84,{"impact":72,"substance":110,"depth":111,"authority":143,"freshness":74,"relevant":22,"comment":240},"该研究提出CAPLA无人机点云融合方法，实现水盐胁迫下棉花叶倾角昼夜动态的高精度监测，方法新颖、数据可靠，对作物表型与精准农业有实质参考价值。",[242],{"name":237,"url":234},[27,28,244,149,245],"棉花","无人机遥感",[247,248],"无人机 棉花 叶倾角 水盐胁迫","CAPLA 冠层结构 动态监测","无人机棉花叶倾角水盐胁迫-3014","10.1016\u002Fj.rse.2026.115674",{"doi":250,"openalex_id":252,"authors":253,"venue":237,"cited_by_count":36,"oa_url":234,"card":278,"direction":54,"ingested_from":57},"W7213661690",[254,257,259,261,263,265,268,271,273,276],{"name":255,"orcid":256},"Qing Li","https:\u002F\u002Forcid.org\u002F0009-0004-4580-7761",{"name":258,"orcid":9},"Dalei Hao",{"name":260,"orcid":9},"Jan Pisek",{"name":262,"orcid":9},"Zicheng Ji",{"name":264,"orcid":9},"Yanan Wei",{"name":266,"orcid":267},"Youngryel Ryu","https:\u002F\u002Forcid.org\u002F0000-0001-6238-2479",{"name":269,"orcid":270},"Jiarui Xu","https:\u002F\u002Forcid.org\u002F0000-0003-4925-2770",{"name":272,"orcid":9},"Yangmin Feng",{"name":274,"orcid":275},"Shaozhong Kang","https:\u002F\u002Forcid.org\u002F0000-0002-8019-2537",{"name":277,"orcid":9},"Yelu Zeng",{"tldr":279,"method":280,"finding":281,"direction":54,"opportunity":282},"提出CAPLA无人机点云融合方法，监测水盐胁迫下棉花叶倾角昼夜动态。","结合深度学习与SfM，用2D语义掩膜约束3D网格重建，无人机高频观测。","灌溉、盐分和时间显著影响叶倾角，灌溉×时间交互显著，昼夜轨迹因灌溉而异。","可将动态叶倾角参数化嵌入作物模型，提升水盐胁迫下冠层结构与蒸散模拟精度。","2026-09-20T23:30:21.262698Z"]