[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3070":3,"related-3070":46},{"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":18,"tags":20,"search_phrases":24,"slug":27,"view_count":15,"doi":28,"paper":29,"created_at":45},3070,"Deep neural network-driven adaptive fusion recognition method for radar-optical heterogeneous remote sensing imagery","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-70090-8","Abstract The fusion of radar and optical remote sensing imagery presents significant challenges due to fundamental differences in imaging mechanisms and feature representations. This paper proposes an adaptive fusion recognition framework based on deep neural networks for heterogeneous radar-optical imagery. The framework comprises three core components: a heterogeneous feature extraction and alignment module that projects SAR and optical features into a shared semantic space through contrastive learning, a cross-modal adaptive fusion mechanism employing dual-attention architecture with dynamic weight generation to enable context-sensitive modality integration, and an end-to-end recognition network that jointly optimizes all processing stages. To probe the framework from multiple angles, we ran a comprehensive experimental campaign on the SEN1-2 benchmark, which spans head-to-head comparisons against ten representative fusion baselines, ablations isolating each module as well as the GLCM texture branch, a sensitivity sweep over the contrastive temperature parameter, stress tests under additive speckle noise and single-modality missing scenarios, and an efficiency audit reporting parameter count and inference latency. The proposed method reaches 91.38% overall accuracy with a Kappa coefficient of 0.892 and macro F1 score of 90.45%, surpassing competitive baselines while holding inference cost to 11.4 ms per sample. Ablation studies confirm the effectiveness of each component, with feature alignment contributing 3.45% accuracy improvement and the complete adaptive fusion mechanism providing additional 5.46% gains over baseline concatenation. The dynamic weighting strategy exhibits robust performance under degraded input conditions by automatically adjusting modality contributions based on estimated reliability.","摘要 雷达与光学遥感影像的融合面临显著挑战，根源在于二者成像机理与特征表示存在本质差异。本文提出了一种基于深度神经网络的异源雷达—光学影像自适应融合识别框架。该框架包含三个核心组件：异源特征提取与对齐模块，通过对比学习将合成孔径雷达（SAR）与光学特征投影至共享语义空间；跨模态自适应融合机制，采用双注意力架构与动态权重生成，实现上下文敏感模态集成；以及端到端识别网络，联合优化所有处理阶段。为从多角度探究该框架，我们在SEN1-2基准上开展了系统性实验，包括与十种代表性融合基线的直接对比、分别隔离各模块及GLCM纹理分支的消融实验、对比温度参数的敏感性扫描、加性散斑噪声与单模态缺失场景下的压力测试，以及报告参数量与推理延迟的效率审计。所提方法总体精度达91.38%，Kappa系数为0.892，宏F1分数为90.45%，在超越竞争性基线的同时将推理开销控制在每样本11.4 ms。消融研究证实了各组成部分的有效性，其中特征对齐贡献了3.45%的精度提升，完整的自适应融合机制在基线拼接基础上额外带来5.46%的增益。动态加权策略在退化输入条件下通过基于估计可靠性自动调整模态贡献，表现出稳健的性能。",null,"Scientific Reports","2026-09-19T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"雷达与光学异构遥感影像融合识别方法研究，属遥感与深度学习交叉领域，与三农、农业信息化无直接关联，不纳入每日精选。",[19],{"name":10,"url":6},[21,22,23],"农业人工智能","遥感","雷达光学融合",[25,26],"SEN1-2 雷达光学 融合识别","农业人工智能 雷达光学融合 遥感","SEN1-2雷达光学融合识别-3070","10.1038\u002Fs41598-026-70090-8",{"doi":28,"openalex_id":30,"authors":31,"venue":10,"cited_by_count":15,"oa_url":37,"card":38,"direction":42,"ingested_from":44},"W7213614235",[32,34],{"name":33,"orcid":9},"Binlu Liu",{"name":35,"orcid":36},"Zijing Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-1935-7048","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-70090-8_reference.pdf",{"tldr":39,"method":40,"finding":41,"direction":42,"opportunity":43},"提出深度神经网络自适应融合框架，实现雷达与光学异构遥感影像的高精度识别。","基于对比学习特征对齐、双注意力动态权重融合，在SEN1-2数据集上端到端训练。","总体精度91.38%，Kappa 0.892，特征对齐与自适应融合分别提升3.45%和5.46%。","农业遥感与作物表型","可探索该融合框架在农业地块分类、作物长势监测及多模态缺失场景下的迁移应用。","openalex","2026-09-21T23:30:24.192758Z",{"total":47,"page":48,"page_size":47,"items":49},6,1,[50,101,139,196,226,269],{"id":51,"title":52,"url":53,"summary":54,"summary_zh":55,"content":9,"source_name":56,"source_url":53,"published_at":57,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":58,"score_detail":59,"sources":65,"tags":67,"search_phrases":71,"slug":74,"view_count":15,"doi":75,"paper":76,"created_at":100},3076,"Research on the Inversion Method of Total Phosphorus Concentration in Water Bodies Based on PSO-Adam-BP Neural Network Model","https:\u002F\u002Fdoi.org\u002F10.15244\u002Fpjoes\u002F220960","This study investigated Baiyangdian Lake in the Xiong’an New Area to invert total phosphorus (TP) concentrations using Sentinel-2 multispectral imagery and in situ measurements, aiming to support water-quality assessment and eutrophication management. Based on the multispectral remote sensing data of Sentinel-2 and measured total phosphorus data of water bodies, the study used specific feature combinations such as NDTI, B5, B11-B12 difference, and sensitive combination bands of measured data as model inputs to construct a PSO-Adam-BP neural network machine learning model for total phosphorus concentration inversion. Compared with the traditional BP and PSO-BP baseline models, the proposed framework significantly improved the accuracy of the model, with an R2 value reaching 0.9351. Moreover, it successfully reduced the average relative error by up to 53.5%, from 4.80% to 2.24%, and decreased the maximum relative error by up to 31.7%, from 11.21% to 7.66%, demonstrating the model’s highly robust and precise inversion performance. This study provides a new method for water quality detection in Baiyangdian Lake and is of great significance to the protection and development of the water environment in Xiong’an New Area.","本研究以雄安新区白洋淀为研究对象，利用Sentinel-2多光谱影像和实地测量数据反演总磷（TP）浓度，旨在为水质评价和富营养化管理提供支持。基于Sentinel-2多光谱遥感数据和白洋淀水体总磷实测数据，研究采用NDTI、B5、B11-B12差值等特征组合及实测数据的敏感组合波段作为模型输入，构建了PSO-Adam-BP神经网络机器学习模型用于总磷浓度反演。与传统BP和PSO-BP基准模型相比，所提出的框架显著提高了模型精度，R²值达到0.9351。此外，该模型成功将平均相对误差最多降低53.5%，从4.80%降至2.24%，并将最大相对误差最多降低31.7%，从11.21%降至7.66%，展现出高度稳健且精确的反演性能。本研究为白洋淀水质检测提供了新方法，对雄安新区水环境保护与开发具有重要意义。","Polish Journal of Environmental Studies","2026-09-18T00:00:00Z",72,{"impact":60,"substance":61,"depth":62,"authority":63,"freshness":47,"relevant":48,"comment":64},15,21,17,13,"基于Sentinel-2与PSO-Adam-BP模型实现白洋淀总磷浓度高精度反演，方法新颖、数据可靠，对雄安水环境智慧监测有实用价值。",[66],{"name":56,"url":53},[21,68,22,69,70],"机器学习","水质监测","白洋淀",[72,73],"白洋淀 总磷 遥感反演","Sentinel-2 水质 反演","白洋淀总磷遥感反演-3076","10.15244\u002Fpjoes\u002F220960",{"doi":75,"openalex_id":77,"authors":78,"venue":56,"cited_by_count":15,"oa_url":94,"card":95,"direction":42,"ingested_from":44},"W7213537374",[79,81,83,86,89,91],{"name":80,"orcid":9},"Guanxing Wang",{"name":82,"orcid":9},"Cui Jia",{"name":84,"orcid":85},"Linghan Gao","https:\u002F\u002Forcid.org\u002F0000-0002-8537-8787",{"name":87,"orcid":88},"Shan An","https:\u002F\u002Forcid.org\u002F0000-0001-7796-6952",{"name":90,"orcid":9},"Jia Xi",{"name":92,"orcid":93},"Yaxue Liu","https:\u002F\u002Forcid.org\u002F0009-0006-9025-8030","https:\u002F\u002Fwww.pjoes.com\u002Fpdf-220960-145347?filename=Research-on-the-Inversion.pdf",{"tldr":96,"method":97,"finding":98,"direction":42,"opportunity":99},"用PSO-Adam-BP神经网络结合Sentinel-2影像反演白洋淀总磷浓度。","Sentinel-2多光谱与实测数据，NDTI等特征组合，PSO-Adam-BP","R²达0.9351，平均相对误差由4.80%降至2.24%，精度显著优于BP与PSO-BP。","可迁移至其他内陆水体与多参数水质反演，探索时序泛化与跨区域迁移能力。","2026-09-21T23:30:25.856035Z",{"id":102,"title":103,"url":104,"summary":105,"summary_zh":106,"content":9,"source_name":107,"source_url":104,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":58,"score_detail":108,"sources":112,"tags":114,"search_phrases":118,"slug":121,"view_count":15,"doi":122,"paper":123,"created_at":138},3009,"AgriMAC: An Attention Based Multimodal Deep Clustering Framework for Rice Health Assessment","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1031.06","Rice is Indonesia's staple crop, yet its productivity has declined in recent years because pest and disease outbreaks remain difficult to detect at an early stage.Existing precision agriculture approaches commonly process Internet of Things (IoT) sensor data and remote sensing imagery independently and often rely on supervised learning, requiring large amounts of labeled data.Meanwhile, multispectral drone imagery producing the Normalized Difference Vegetation Index (NDVI) provides richer information on crop physiological conditions than RGB-based vegetation indices.This study proposes Agricultural Multimodal Attention Clustering (AgriMAC), an unsupervised framework that integrates UAV derived NDVI imagery, 7-in-1 IoT soil sensor measurements, and historical weather data from the Open-Meteo API for rice field condition monitoring.Each modality is encoded using a dedicated autoencoder and fused through an entropy-regularized attention mechanism before Deep Embedded Clustering is performed.To reduce the influence of crop growth stage, the IoT representation is residualized using growth-phase statistics estimated exclusively from the training fold, enabling the discovered clusters to represent within-phase agronomic conditions rather than crop age.Experiments conducted under a grouped leave-one-field-out protocol produced a Silhouette Score of 0.465 ± 0.048, a Davies Bouldin Index of 0.807 ± 0.036, and a Calinski Harabasz Index of 195 ± 27.The learned groups also showed low normalized mutual information with growth phase (0.079 ± 0.043) and near chance phase decodability (balanced accuracy = 0.554 ± 0.042), indicating that they are only weakly associated with crop growth stage.The learned attention weights identified IoT soil measurements (0.570 ± 0.024) as the dominant modality, while NDVI imagery (0.210 ± 0.014) and weather information (0.220 ± 0.014) provided complementary spatial and temporal context.Overall, AgriMAC provides an interpretable and leakage-aware framework for multimodal clustering of rice field conditions.Although its clustering performance is comparable to that of a capacity-matched IoT-only model, it additionally quantifies the contribution of each sensing modality through attention weights and explicitly mitigates the growth-phase confound, making it suitable for field level agronomic condition monitoring and spatial decision support in precision agriculture.","水稻是印度尼西亚的主要作物，但近年来其生产力有所下降，因为病虫害暴发在早期阶段仍难以检测。现有的精准农业方法通常独立处理物联网（IoT）传感器数据和遥感影像，且往往依赖监督学习，需要大量标注数据。与此同时，生成归一化植被指数（NDVI）的多光谱无人机影像比基于RGB的植被指数能提供更丰富的作物生理状况信息。本研究提出农业多模态注意力聚类（AgriMAC），这是一个无监督框架，整合了无人机获取的NDVI影像、七合一IoT土壤传感器测量数据以及来自Open-Meteo API的历史天气数据，用于稻田状况监测。每种模态均使用专用自编码器进行编码，并通过熵正则化注意力机制进行融合，随后执行深度嵌入聚类。为减少作物生长阶段的影响，IoT表征利用仅从训练折估计的生长阶段统计量进行残差化处理，使发现的聚类能够表征阶段内的农艺状况而非作物年龄。在分组留一田块协议下进行的实验产生了0.465 ± 0.048的轮廓系数、0.807 ± 0.036的Davies-Bouldin指数和195 ± 27的Calinski-Harabasz指数。学习到的分组还显示出与生长阶段的低归一化互信息（0.079 ± 0.043）以及接近随机的阶段可解码性（平衡准确率 = 0.554 ± 0.042），表明它们与作物生长阶段仅存在弱关联。学习到的注意力权重将IoT土壤测量（0.570 ± 0.024）识别为主导模态，而NDVI影像（0.210 ± 0.014）和天气信息（0.220 ± 0.014）则提供了互补的空间和时间背景。总体而言，AgriMAC为稻田状况的多模态聚类提供了一个可解释且感知数据泄漏的框架。尽管其聚类性能与容量匹配的仅IoT模型相当，但它还通过注意力权重量化了每种传感模态的贡献，并明确减轻了生长阶段混杂因素，使其适用于田块级农艺状况监测和精准农业中的空间决策支持。","International journal of intelligent engineering and systems",{"impact":109,"substance":61,"depth":62,"authority":63,"freshness":110,"relevant":48,"comment":111},12,9,"提出无监督多模态注意力聚类框架，融合无人机NDVI、IoT土壤与气象数据评估水稻健康，方法新颖且实验严谨，对精准农业田间监测有参考价值。",[113],{"name":107,"url":104},[115,21,116,117,22],"智慧农业","水稻","多模态融合",[119,120],"AgriMAC 水稻 多模态聚类","无人机 NDVI 水稻 病害监测","AgriMAC水稻多模态聚类-3009","10.22266\u002Fijies2026.1031.06",{"doi":122,"openalex_id":124,"authors":125,"venue":107,"cited_by_count":15,"oa_url":104,"card":132,"direction":136,"ingested_from":44},"W7213619014",[126,128,130],{"name":127,"orcid":9},"Nurfadhilah Mardianti Andini",{"name":129,"orcid":9},"Mike Yuliana",{"name":131,"orcid":9},"Moch. Zen Samsono Hadi",{"tldr":133,"method":134,"finding":135,"direction":136,"opportunity":137},"提出无监督多模态聚类框架AgriMAC，融合无人机NDVI、IoT土壤与气象数据评估水稻健康。","各模态自编码器编码，熵正则注意力融合，深度嵌入聚类，按生长阶段残差化。","聚类性能与仅IoT模型相当，但注意力权重可解释模态贡献并弱化生长阶段混淆。","智慧农业 \u002F 农业物联网","可探索注意力融合机制在更多作物与传感器组合下的泛化性，并引入时序动态聚类。","2026-09-20T23:30:08.419613Z",{"id":140,"title":141,"url":142,"summary":143,"summary_zh":144,"content":9,"source_name":145,"source_url":142,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":146,"score_detail":147,"sources":152,"tags":154,"search_phrases":157,"slug":160,"view_count":15,"doi":161,"paper":162,"created_at":195},3006,"Explainable spectral–image fusion multi-task learning for maize canopy biochemical and structural trait retrieval","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112450","Accurate and interpretable estimation of multiple maize canopy traits is important for proximal crop monitoring and high-throughput phenotyping. This study developed a spectral–image fusion multi-task learning framework (MM-MTL) for the simultaneous retrieval of chlorophyll index (Chl index), leaf area index (LAI), nitrogen balance index (NBI), and anthocyanin index (Anth index). Proximal hyperspectral observations were collected using a Specim IQ camera covering 400–1000 nm with 204 spectral bands. For each observation, an ROI-mean spectral vector was extracted to retain fine-grained canopy reflectance information, while a co-registered pseudo-RGB image derived from visible bands of the same hyperspectral cube preserved two-dimensional canopy structure and visible appearance. MM-MTL integrates spectral and image feature extraction, task-specific fusion, and uncertainty-weighted multi-task learning to jointly estimate the four traits. A total of 1,023 valid samples collected from nine field campaigns across the 2024 and 2025 growing seasons were used for model development and evaluation. Under plot-grouped five-fold cross-validation, MM-MTL achieved R 2 values of 0.872, 0.885, 0.722, and 0.807 for Chl index, LAI, NBI, and Anth index, respectively, and consistently outperformed the single-task, single-representation, and conventional regression baselines. Performance decreased under more challenging generalization settings, with R 2 values ranging from 0.543 to 0.680 under leave-one-campaign-out validation and from 0.425 to 0.640 under bidirectional cross-year validation. Ablation and post-hoc analyses further showed that preserving image spatial organization improved prediction, while task-wise routing, input-representation masking, wavelength perturbation, and cross-fold stability analyses revealed trait-dependent use of spectral and spatial information. These results demonstrate that complementary spectral and spatial representations derived from the same hyperspectral observation can improve multi-trait maize canopy retrieval, while transfer across acquisition campaigns, years, and field environments remains an important direction for further improvement.","准确且可解释地估算多个玉米冠层性状，对于近地作物监测和高通量表型分析具有重要意义。本研究开发了一种光谱—图像融合多任务学习框架（MM-MTL），用于同时反演叶绿素指数（Chl index）、叶面积指数（LAI）、氮平衡指数（NBI）和花青素指数（Anth index）。近地高光谱观测使用Specim IQ相机采集，覆盖400–1000 nm，共204个光谱波段。对于每次观测，提取ROI均值光谱向量以保留细粒度冠层反射率信息，同时从同一高光谱立方体的可见光波段生成配准的伪RGB图像，以保留二维冠层结构和可见外观。MM-MTL集成了光谱与图像特征提取、任务特定融合以及不确定性加权多任务学习，以联合估算这四种性状。研究使用2024年和2025年生长季9次田间试验采集的共计1,023个有效样本进行模型开发与评估。在按小区分组的五折交叉验证下，MM-MTL对Chl index、LAI、NBI和Anth index的R²分别为0.872、0.885、0.722和0.807，且持续优于单任务、单表征和传统回归基线。在更具挑战性的泛化设置下，模型性能有所下降，留一试验验证的R²范围为0.543–0.680，双向跨年验证的R²范围为0.425–0.640。消融分析和事后分析进一步表明，保留图像空间组织可提升预测性能，而任务路由、输入表征掩蔽、波长扰动和跨折稳定性分析揭示了光谱与空间信息的性状依赖性利用方式。这些结果表明，从同一高光谱观测中提取的互补光谱与空间表征可改善多性状玉米冠层反演，而跨采集试验、年份和田间环境的迁移仍是未来改进的重要方向。","Computers and Electronics in Agriculture",81,{"impact":148,"substance":149,"depth":148,"authority":150,"freshness":110,"relevant":48,"comment":151},18,22,14,"提出光谱-图像融合多任务学习框架，1023份样本跨两年验证，方法新颖且结论可靠，对作物高通量表型研究有实质参考价值。",[153],{"name":145,"url":142},[115,21,155,22,156],"玉米","高通量表型",[158,159],"玉米冠层 多任务学习 高光谱","Specim IQ 玉米 表型","玉米冠层多任务学习高光谱-3006","10.1016\u002Fj.compag.2026.112450",{"doi":161,"openalex_id":163,"authors":164,"venue":145,"cited_by_count":15,"oa_url":142,"card":190,"direction":42,"ingested_from":44},"W7213658705",[165,167,169,171,173,176,178,181,183,185,187],{"name":166,"orcid":9},"Penglei Zhang",{"name":168,"orcid":9},"Tianbo Hao",{"name":170,"orcid":9},"Zhuoyuan Zhao",{"name":172,"orcid":9},"Hong Sun",{"name":174,"orcid":175},"Yelu Zeng","https:\u002F\u002Forcid.org\u002F0000-0003-4267-1841",{"name":177,"orcid":9},"Zheng Cui",{"name":179,"orcid":180},"Ta Na","https:\u002F\u002Forcid.org\u002F0000-0002-1348-5655",{"name":182,"orcid":9},"Lang Qiao",{"name":184,"orcid":9},"Durval Dourado Neto",{"name":186,"orcid":9},"Feng Yang",{"name":188,"orcid":189},"Jingzhu Wu","https:\u002F\u002Forcid.org\u002F0000-0002-8386-1038",{"tldr":191,"method":192,"finding":193,"direction":42,"opportunity":194},"提出光谱-图像融合多任务学习框架，同时反演玉米冠层四个生化与结构性状。","Specim IQ高光谱与伪RGB融合，不确定性加权多任务学习，1023样本交叉","融合模型精度优于单任务基线，但跨年份与跨环境泛化性能明显下降。","可研究跨年份\u002F跨环境域适应与迁移学习，提升多性状反演泛化能力。","2026-09-20T23:30:01.739142Z",{"id":197,"title":198,"url":199,"summary":200,"summary_zh":9,"content":9,"source_name":201,"source_url":9,"published_at":202,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":203,"score_detail":204,"sources":208,"tags":210,"search_phrases":213,"slug":216,"view_count":15,"doi":9,"paper":217,"created_at":225},2999,"基于改进DeepLabv3+的高标准农田田间道路提取与结构指标量化框架","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F18\u002F1986","沈阳农业大学刘永生等开发了基于MobileNetV2改进DeepLabv3+的高标准农田田间道路提取轻量化框架，集成Normalization-based Attention Module与Content-Aware ReAssembly of FEatures。三次随机种子训练平均mIoU 93.34%、mPA 96.75%、精度98.90%，模型参数6.14M、推理速度17.04 FPS；沥青、混凝土、砾石道路宽度预测R²分别为0.650、0.486、0.662，宽度MAE 0.130\u002F0.140\u002F0.100 m。第二验证区域连通性指数从0.4682提升至0.4795，支持高标准农田田间道路高效、可量化、可追溯的验收检查。","MDPI Agriculture 16(18):1986","2026-09-16T00:00:00Z",77,{"impact":205,"substance":149,"depth":148,"authority":63,"freshness":206,"relevant":48,"comment":207},16,8,"方法有创新、指标详实，对高标准农田道路验收有实用价值，但属细分技术论文，影响面有限。",[209],{"name":201,"url":199},[115,21,211,22,212],"高标准农田","田间道路",[214,215],"沈阳农业大学 高标准农田 道路提取","DeepLabv3 田间道路 遥感","沈阳农业大学高标准农田道路提取-2999",{"doi":9,"openalex_id":9,"authors":218,"venue":9,"cited_by_count":15,"oa_url":9,"card":219,"direction":42,"ingested_from":224},[],{"tldr":220,"method":221,"finding":222,"direction":42,"opportunity":223},"提出改进DeepLabv3+轻量框架，提取高标准农田田间道路并量化结构指标。","MobileNetV2+NAM+CARAFE改进DeepLabv3+，多区域遥感","mIoU 93.34%，道路宽度预测R²最高0.662，连通性指数提升至0.4795。","可拓展至多作物、多地形道路提取，并结合时序遥感实现道路损毁动态监测。","agent","2026-09-20T00:03:08.023498Z",{"id":227,"title":228,"url":229,"summary":230,"summary_zh":231,"content":9,"source_name":232,"source_url":229,"published_at":57,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":233,"score_detail":234,"sources":236,"tags":238,"search_phrases":241,"slug":244,"view_count":15,"doi":245,"paper":246,"created_at":268},2956,"Integrating AI and Earth Observation Data for Disaster Risk Reduction","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs12524-026-02595-8","Integrating AI and Earth Observation Data for Disaster Risk Reduction。Journal of the Indian Society of Remote Sensing","将人工智能与地球观测数据相结合以降低灾害风险。《印度遥感学会杂志》","Journal of the Indian Society of Remote Sensing",62,{"impact":109,"substance":150,"depth":60,"authority":63,"freshness":206,"relevant":48,"comment":235},"AI与地球观测融合用于灾害风险降低的学术论文，与农业信息化相关但偏通用防灾，产业落地价值有限。",[237],{"name":232,"url":229},[21,239,22,240],"防灾减灾","地球观测",[242,243],"AI 地球观测 灾害风险","农业人工智能 地球观测 防灾减灾 遥感","AI地球观测灾害风险-2956","10.1007\u002Fs12524-026-02595-8",{"doi":245,"openalex_id":247,"authors":248,"venue":232,"cited_by_count":15,"oa_url":261,"card":262,"direction":267,"ingested_from":44},"W7213552966",[249,252,255,258],{"name":250,"orcid":251},"Surajit Ghosh","https:\u002F\u002Forcid.org\u002F0000-0002-3928-2135",{"name":253,"orcid":254},"Md. Munsur Rahman","https:\u002F\u002Forcid.org\u002F0000-0002-9922-0374",{"name":256,"orcid":257},"Fasikaw A. Zimale","https:\u002F\u002Forcid.org\u002F0000-0001-9778-2712",{"name":259,"orcid":260},"Rajib Shaw","https:\u002F\u002Forcid.org\u002F0000-0003-3153-1800","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs12524-026-02595-8.pdf",{"tldr":263,"method":264,"finding":265,"direction":42,"opportunity":266},"综述AI与地球观测数据融合用于灾害风险减少的研究进展。","综述AI与地球观测数据融合方法。","AI与地球观测融合可提升灾害风险监测与评估能力。","可探索AI与遥感融合在农业灾害风险预警与保险中的具体应用。","数字乡村与农业信息化","2026-09-19T23:30:40.818538Z",{"id":270,"title":271,"url":272,"summary":273,"summary_zh":274,"content":9,"source_name":275,"source_url":272,"published_at":57,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":276,"score_detail":277,"sources":279,"tags":281,"search_phrases":284,"slug":287,"view_count":15,"doi":288,"paper":289,"created_at":299},2948,"Machine learning and remote sensing for smallholder precision agriculture in Ethiopia","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43621-026-04538-2","While machine learning (ML) and remote sensing (RS) are frequently heralded as the definitive solutions for agricultural resilience in Sub-Saharan Africa, a profound ‘implementation gap’ persists between laboratory-validated computational maturity and field-level utility for smallholder farmers. This systematic review, conducted under preferred reporting items for systematic reviews and meta-analyses (PRISMA) 2020 guidelines, critically analyzes why sophisticated models optimized for large-scale monocultures fail within the fragmented, intercropped landscapes of Ethiopia. By synthesizing empirical evidence across four domains—in-season crop yield forecasting, digital soil mapping, real-time biotic stress detection, and agro-meteorological modeling—the review uncover a fundamental scale mismatch between coarse-resolution satellite observations and sub-hectare micro-plots. The critique identifies localized data scarcity, hardware constraints, and the ‘last-mile’ connectivity divide as the primary friction points obstructing the transition from macro-level pixels to actionable, site-specific agricultural intelligence. Moving beyond simple summary, the study propose a strategic roadmap centered on decentralized edge computing, tinyML optimizations, and a restructuring of extension services to integrate digital intelligence into daily smallholder decision-making. These structural shifts are essential to bridge the digital divide and secure Ethiopia’s national food security against escalating climate variability. This review foregrounds the significance of digital agriculture within the context of the sustainable development goals (SDGs), specifically addressing SDG 2 (zero hunger) and SDG 13 (climate action) by enhancing crop productivity and building resilience in smallholder systems.","尽管机器学习（ML）与遥感（RS）常被标榜为撒哈拉以南非洲农业韧性的终极解决方案，但实验室验证的计算成熟度与小农户田间实用性之间仍存在深刻的“实施鸿沟”。本系统综述依据系统综述和荟萃分析首选报告条目（PRISMA）2020指南开展，批判性地分析了为何针对大规模单一种植优化的复杂模型在埃塞俄比亚碎片化、间作化的景观中失效。通过综合四个领域的实证证据——季内作物产量预测、数字土壤制图、实时生物胁迫检测和农业气象建模——本综述揭示了粗分辨率卫星观测与亚公顷微地块之间的根本性尺度错配。该批判性分析将局部数据稀缺、硬件约束和“最后一公里”连接鸿沟确定为阻碍从宏观像元向可操作、因地制宜的农业智能转化的主要摩擦点。本研究超越简单的总结，提出了一条以去中心化边缘计算、tinyML优化和推广服务体系重构为核心的战略路线图，旨在将数字智能融入小农户的日常决策。这些结构性转变对于弥合数字鸿沟、保障埃塞俄比亚在日益加剧的气候变率下的国家粮食安全至关重要。本综述凸显了数字农业在可持续发展目标（SDGs）背景下的重要意义，特别是通过提升作物生产力和增强小农系统韧性来回应SDG 2（零饥饿）和SDG 13（气候行动）。","Discover Sustainability",79,{"impact":148,"substance":61,"depth":148,"authority":63,"freshness":110,"relevant":48,"comment":278},"系统综述揭示机器学习与遥感在小农场景的落地鸿沟，并提出边缘计算与tinyML路线图，对数字农业与SDG研究有参考价值。",[280],{"name":275,"url":272},[115,21,282,283,22],"小农户","数字鸿沟",[285,286],"埃塞俄比亚 小农户 精准农业","机器学习 遥感 小农","埃塞俄比亚小农户精准农业-2948","10.1007\u002Fs43621-026-04538-2",{"doi":288,"openalex_id":290,"authors":291,"venue":275,"cited_by_count":15,"oa_url":272,"card":294,"direction":42,"ingested_from":44},"W7213562005",[292],{"name":293,"orcid":9},"Abrha Asefa",{"tldr":295,"method":296,"finding":297,"direction":42,"opportunity":298},"系统综述埃塞俄比亚小农精准农业中机器学习和遥感的应用鸿沟与出路。","PRISMA 2020 系统综述，综合四领域实证证据。","粗分辨率卫星与亚公顷微地块尺度不匹配，数据稀缺和连接鸿沟阻碍落地。","面向碎片化间作小农的 tinyML 边缘计算与本地化数据采集，是填补落地鸿沟的关键方向。","2026-09-19T23:30:33.334404Z"]