[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5531":3,"related-5531":70},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":8,"secondary_topics":31,"classification":32,"search_phrases":55,"slug":58,"view_count":59,"doi":8,"paper":60,"created_at":69},5531,"A100：面向农业植物图像分析的混合视觉基础模型","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.22991","研究者在覆盖100余种作物、300万张无标注田间图像上自监督预训练A100，采用CNN与Transformer混合骨干融合局部与全局特征。仅用1%标注数据（约每类284张）作物分类准确率达98.01%，在困难数据集PlantDoc上优于全部基线，并在1%标注条件下比公开农业基础模型高14个百分点以上。预印本，未经同行评审。",null,"arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z","论文",10,false,77,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},22,23,18,8,6,1,"大规模田间图像自监督预训练，少样本分类表现突出，方法新颖且数据规模可观，但属未经同行评审的预印本，权威性有限。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","自监督学习","作物分类","视觉基础模型",[],{"status":33,"locked":13,"version":34,"method":35,"evidence":36},"unclassified","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":53,"reason":54},[38,43,48],{"code":39,"score":21,"supported":13,"title":40,"abstract":41,"tags":42},"I1",[],[],[26],{"code":44,"score":21,"supported":13,"title":45,"abstract":46,"tags":47},"I2",[],[],[27],{"code":49,"score":21,"supported":13,"title":50,"abstract":51,"tags":52},"I3",[],[],[29],true,"缺少足够的主题证据",[56,57],"A100 农业视觉基础模型","PlantDoc 作物分类","A100农业视觉基础模型-5531",0,{"doi":8,"openalex_id":8,"authors":61,"venue":8,"cited_by_count":59,"oa_url":8,"card":62,"direction":66,"ingested_from":68},[],{"tldr":63,"method":64,"finding":65,"direction":66,"opportunity":67},"构建混合视觉基础模型A100，用百万级田间图像自监督预训练实现少标注作物图像分析。","300万张田间图像自监督预训练，CNN与Transformer混合骨干融合局部与","仅用1%标注数据作物分类准确率达98.01%，困难数据集上优于全部基线。","农业人工智能与决策模型","可探索该基础模型向病虫害检测、表型测量等下游任务的少样本迁移与轻量化部署。","agent","2026-10-22T00:07:09.646474Z",{"total":20,"page":21,"page_size":20,"items":71},[72,131,225,311,413,489],{"id":73,"title":74,"url":75,"summary":76,"summary_zh":77,"content":8,"source_name":78,"source_url":75,"published_at":79,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":80,"score_detail":81,"sources":85,"tags":87,"primary_topic":90,"secondary_topics":95,"classification":96,"search_phrases":112,"slug":115,"view_count":59,"doi":116,"paper":117,"created_at":130},5585,"Contrastive Self-Supervised Pretraining for Artificial Intelligence Agriculture Weed Detection Under Label Scarcity: A Computer Transfer-Robustness Evaluation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23543814","Weed detection models for precision agriculture are typically trained on labelled field imagery that is expensive to obtain and geographically narrow, so that a model fitted in one region may fail silently when deployed in another. Contrastive self-supervised pretraining has been proposed as a remedy because it learns representations from unlabelled images, but the conditions under which the resulting representations transfer robustly across domains remain poorly characterised. We define a representation-level robustness functional that separates invariance to nuisance transformations from sensitivity to class-discriminative structure, and we derive a bound on target-domain error in terms of source-domain error, representation stability and a domain-divergence term. The bound implies that contrastive pretraining helps only when the augmentation distribution used during pretraining overlaps with the transformation set that distinguishes source from target domains; otherwise the learned invariances suppress exactly the features the downstream task requires. We operationalise the framework as a transfer-robustness evaluation protocol with three components: a label-budget sweep, a domain-shift ladder and a representation-stability diagnostic. The protocol is specified as a design template rather than executed on new field data, and we report the analytical operating characteristics of the evaluation under a declared variance structure. The main contribution is a precise statement of when contrastive pretraining is expected to improve weed-detection transfer and when it is expected to fail, together with an evaluation design that makes that expectation testable.","精准农业中的杂草检测模型通常基于标注田间影像训练，而这类影像获取成本高且地理覆盖范围狭窄，因此在一个地区拟合的模型部署到另一地区时可能悄然失效。对比自监督预训练被认为是一种补救方案，因为它能够从无标注图像中学习表征，但所得表征在何种条件下能够跨域稳健迁移，目前仍缺乏充分刻画。我们定义了一个表征层面的鲁棒性泛函，将对外扰变换的不变性与对类别判别结构的敏感性区分开来，并推导了目标域误差的上界，该上界由源域误差、表征稳定性和一个域散度项构成。该上界表明，对比预训练只有在预训练所用增强分布与区分源域和目标域的变换集合存在重叠时才有帮助；否则，所学到的不变性恰好会抑制下游任务所需的特征。我们将该框架具体化为一个迁移鲁棒性评估协议，包含三个组成部分：标签预算扫描、域偏移阶梯和表征稳定性诊断。该协议被规定为一种设计模板，而非在新的田间数据上执行，我们在声明的方差结构下报告了该评估的解析运行特性。主要贡献在于精确陈述了对比预训练何时有望改善杂草检测迁移、何时预期会失败，并给出了一种使该预期可检验的评估设计。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",62,{"impact":19,"substance":18,"depth":82,"authority":83,"freshness":12,"relevant":21,"comment":84},17,9,"提出对比自监督预训练在标签稀缺下跨域迁移的可检验评估框架，方法学有新意，但仅为设计模板、未在真实田间数据上验证，属细分领域理论进展。",[86],{"name":78,"url":75},[26,27,28,88,89],"杂草检测","迁移学习",{"code":44,"slug":91,"name":92,"path":93,"parent_code":94},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":97,"locked":13,"version":34,"method":35,"evidence":98},"classified",{"candidates":99,"agricultural_evidence":53},[100,105],{"code":44,"score":12,"supported":53,"title":101,"abstract":103,"tags":104},[102],"artificial intelligence",[],[27,89],{"code":39,"score":106,"supported":53,"title":107,"abstract":108,"tags":111},7,[],[109,110],"精准农业","precision agriculture",[26],[113,114],"对比自监督 杂草检测","杂草检测 迁移鲁棒性","对比自监督杂草检测-5585","10.5281\u002Fzenodo.23543814",{"doi":116,"openalex_id":118,"authors":119,"venue":78,"cited_by_count":59,"oa_url":75,"card":124,"direction":66,"ingested_from":129},"W7223090735",[120,122],{"name":121,"orcid":8},"Abebe Gebremedhin Desta",{"name":123,"orcid":8},"Kebede Mekonnen Tadesse",{"tldr":125,"method":126,"finding":127,"direction":66,"opportunity":128},"提出对比自监督预训练在杂草检测跨域迁移中何时有效的理论框架与评估协议。","定义表示级鲁棒性泛函，推导目标域误差上界，设计含标签预算扫描与域偏移阶梯的评估协","仅当预训练增强分布与源-目标域差异变换集重叠时，对比预训练才有助于迁移，否则会抑制任务所需特征。","可将该理论框架落地为真实田间多区域杂草检测实验，验证增强分布重叠假设并量化迁移失败边界。","openalex","2026-10-22T11:21:00.352502Z",{"id":132,"title":133,"url":134,"summary":135,"summary_zh":136,"content":8,"source_name":137,"source_url":134,"published_at":138,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":139,"score_detail":140,"sources":145,"tags":147,"primary_topic":150,"secondary_topics":155,"classification":160,"search_phrases":189,"slug":192,"view_count":193,"doi":194,"paper":195,"created_at":224},4356,"Dual‐Branch Network With Enhanced Feature Fusion for Improved Rice Classification Accuracy","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fsae2.70218","ABSTRACT Accurate mapping of rice, one of the world's most important food crops, is critical for monitoring its growth, estimating yields, and supporting global food security. Most deep learning methods for crop classification rely on multi‐temporal optical remote sensing data. However, it is difficult to obtain sufficient ground‐truth samples for time‐series deep learning models through conducting large‐scale field surveys, and persistent cloud and rainfall often limit optical observations during the rice‐growing seasons in subtropical regions. Rice classification based solely on time‐series optical images may therefore be less accurate and reliable. Here, we developed two dual‐branch deep learning networks for effective rice identification: one combining a long short‐term memory network running in parallel with a multi‐layer perceptron (LSTM + MLP), and the other replacing the LSTM with a one‐dimensional convolutional neural network (Conv1d + MLP). These models process temporal sequences in parallel with auxiliary data through the MLP, allowing them to automatically extract phenology information while incorporating auxiliary variables such as texture features, digital elevation model (DEM) data, and the standard deviation of the vegetation index time series. We evaluated these models in a representative county in the subtropical region of China, and compared the accuracies with standalone LSTM, Conv1d, MLP, and random forest (RF) models. The results revealed that LSTM + MLP had the highest accuracy, with an F1‐score of 95.5%, which can automatically extract rice growth patterns and successfully identify the key phenological information of flood signals during the rice transplanting period. By incorporating auxiliary variables, the model achieved an average accuracy improvement of 8.1% relative to the models using only temporal features. The proposed method provides a useful approach for rice mapping in subtropical regions.","准确绘制水稻这一全球最重要的粮食作物之一，对于监测其生长、估算产量以及保障全球粮食安全至关重要。大多数作物分类的深度学习方法依赖于多时相光学遥感数据。然而，通过开展大规模实地调查来获取足够的地面真值样本以用于时间序列深度学习模型十分困难，而且亚热带地区水稻生长季期间持续的云层和降雨往往限制了光学观测。因此，仅基于时间序列光学图像的水稻分类可能精度较低且可靠性不足。本研究开发了两种双分支深度学习网络以实现有效的水稻识别：一种将长短期记忆网络与多层感知机并行运行（LSTM + MLP），另一种则用一维卷积神经网络替代LSTM（Conv1d + MLP）。这些模型通过MLP将时间序列与辅助数据并行处理，使其能够自动提取物候信息，同时纳入纹理特征、数字高程模型（DEM）数据以及植被指数时间序列标准差等辅助变量。我们在中国亚热带地区一个代表性县对这些模型进行了评估，并将精度与单独的LSTM、Conv1d、MLP和随机森林（RF）模型进行了比较。结果表明，LSTM + MLP精度最高，F1分数达到95.5%，能够自动提取水稻生长模式，并成功识别水稻移栽期洪水信号的关键物候信息。通过纳入辅助变量，该模型相对于仅使用时间特征的模型平均精度提高了8.1%。所提出的方法为亚热带地区水稻制图提供了一种有效途径。","Journal of Sustainable Agriculture and Environment","2026-10-06T00:00:00Z",75,{"impact":141,"substance":142,"depth":82,"authority":143,"freshness":83,"relevant":21,"comment":144},15,21,13,"提出双分支深度学习网络融合时序与辅助数据，水稻识别F1达95.5%，方法新颖且结论可靠，对亚热带多云雨区作物遥感制图有实用价值。",[146],{"name":137,"url":134},[26,27,148,149,29],"水稻","遥感",{"code":151,"slug":152,"name":148,"path":153,"parent_code":154},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[156],{"code":49,"slug":157,"name":158,"path":159,"parent_code":94},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":97,"locked":13,"version":34,"method":35,"evidence":161},{"candidates":162,"agricultural_evidence":53},[163,167,172,178,185],{"code":151,"score":141,"supported":53,"title":164,"abstract":165,"tags":166},[152],[148,152],[148],{"code":49,"score":19,"supported":53,"title":168,"abstract":169,"tags":171},[],[149,170],"remote sensing",[29,149],{"code":44,"score":106,"supported":53,"title":173,"abstract":174,"tags":177},[],[175,176],"深度学习","deep learning",[27],{"code":179,"score":20,"supported":53,"title":180,"abstract":181,"tags":184},"A8",[],[182,183],"粮食安全","food security",[],{"code":39,"score":21,"supported":13,"title":186,"abstract":187,"tags":188},[],[],[26],[190,191],"水稻 遥感 分类 深度学习","亚热带 水稻 制图","水稻遥感分类深度学习-4356",4,"10.1002\u002Fsae2.70218",{"doi":194,"openalex_id":196,"authors":197,"venue":137,"cited_by_count":59,"oa_url":217,"card":218,"direction":222,"ingested_from":129},"W7220691059",[198,200,203,206,208,211,214],{"name":199,"orcid":8},"Rongfei Ma",{"name":201,"orcid":202},"Wenjiao Shi","https:\u002F\u002Forcid.org\u002F0000-0001-6199-9733",{"name":204,"orcid":205},"Minglei Wang","https:\u002F\u002Forcid.org\u002F0000-0002-4174-9224",{"name":207,"orcid":8},"Xiwei Chen",{"name":209,"orcid":210},"Chenchen Zhang","https:\u002F\u002Forcid.org\u002F0000-0003-0458-6232",{"name":212,"orcid":213},"Baihong Pan","https:\u002F\u002Forcid.org\u002F0009-0004-1100-6798",{"name":215,"orcid":216},"Xiangming Xiao","https:\u002F\u002Forcid.org\u002F0000-0003-0956-7428","https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdfdirect\u002F10.1002\u002Fsae2.70218",{"tldr":219,"method":220,"finding":221,"direction":222,"opportunity":223},"提出双分支深度学习网络融合时序与辅助数据，提升亚热带水稻分类精度。","LSTM\u002FConv1d与MLP并行双分支网络，融合时序植被指数、纹理、DEM等辅","LSTM+MLP模型F1达95.5%，辅助变量使精度平均提升8.1%，能识别插秧期淹水信号。","农业遥感与作物表型","可探索多源遥感与气象数据融合，解决多云雨地区时序缺失下的作物精细制图问题。","2026-10-07T23:30:25.945309Z",{"id":226,"title":227,"url":228,"summary":229,"summary_zh":230,"content":8,"source_name":231,"source_url":228,"published_at":232,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":233,"sources":236,"tags":238,"primary_topic":239,"secondary_topics":240,"classification":241,"search_phrases":284,"slug":287,"view_count":274,"doi":288,"paper":289,"created_at":310},4321,"Improving early season crop type mapping using machine learning algorithms with combined SAR and optical time series","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43621-026-04839-6","Timely and reliable crop type mapping is essential for sustainable agricultural management and food security. This study investigates the potential of integrating multi-temporal Synthetic Aperture Radar (SAR) data from Sentinel-1 and optical imagery from Sentinel-2 for early-season crop classification in Udham Singh Nagar district, Uttarakhand, India. Leveraging the Google Earth Engine (GEE) cloud platform, two ensemble machine learning algorithms, Random Forest (RF) and Gradient Boosted Trees (GBT), were implemented and evaluated for their ability to classify major land cover and crop types using combined SAR-optical datasets acquired during November–December 2022. A total of 1141 ground truth samples were collected through field surveys. The integration of structural (SAR) and spectral (optical) information substantially enhanced classification performance compared with single-sensor approaches. Among the models, GBT achieved the highest accuracy, with an overall accuracy of 93% and a Kappa coefficient of 0.90. Wheat, forest, and water bodies were mapped with high precision (F1 ≥ 0.90), whereas mustard and sugarcane showed lower accuracy due to spectral similarity and limited training data. Feature importance analysis identified late-season SAR (VV, VH) and optical (red-edge and SWIR) bands as the most influential variables. The results demonstrate that the synergy between SAR and optical time-series data, coupled with ensemble machine learning, provides a robust and scalable framework for near real-time crop monitoring. This approach offers valuable insights for precision agriculture and supports data-driven policy planning in India’s agricultural sector.","及时可靠的作物类型制图对可持续农业管理和粮食安全至关重要。本研究探讨了整合Sentinel-1多时相合成孔径雷达（SAR）数据与Sentinel-2光学影像在印度北阿坎德邦乌达姆辛格纳加尔地区进行早季作物分类的潜力。依托Google Earth Engine（GEE）云平台，研究采用随机森林（RF）和梯度提升树（GBT）两种集成机器学习算法，利用2022年11月至12月获取的SAR-光学联合数据集，对主要土地覆盖和作物类型进行分类，并评估其分类能力。通过实地调查共采集1141个地面真实样本。与单一传感器方法相比，结构信息（SAR）与光谱信息（光学）的融合显著提升了分类性能。在各模型中，GBT取得了最高精度，总体精度达93%，Kappa系数为0.90。小麦、森林和水体的制图精度较高（F1 ≥ 0.90），而芥菜和甘蔗因光谱相似及训练数据有限，精度较低。特征重要性分析表明，晚季SAR（VV、VH）和光学（红边和短波红外）波段是最具影响力的变量。结果表明，SAR与光学时间序列数据的协同结合集成机器学习，为近实时作物监测提供了稳健且可扩展的框架。该方法为精准农业提供了有价值的见解，并支持印度农业领域的数据驱动政策规划。","Discover Sustainability","2026-10-05T00:00:00Z",{"impact":234,"substance":142,"depth":18,"authority":143,"freshness":83,"relevant":21,"comment":235},16,"该研究将SAR与光学时序数据结合集成机器学习，实现93%早期作物分类精度，方法可扩展、结论可靠，对农业遥感监测有实质参考价值。",[237],{"name":231,"url":228},[26,27,182,149,29],{"code":44,"slug":91,"name":92,"path":93,"parent_code":94},[],{"status":97,"locked":13,"version":34,"method":35,"evidence":242},{"candidates":243,"agricultural_evidence":53},[244,250,254,258,265,272,279],{"code":44,"score":141,"supported":53,"title":245,"abstract":247,"tags":249},[246],"machine learning",[248,246],"机器学习",[27],{"code":179,"score":106,"supported":53,"title":251,"abstract":252,"tags":253},[],[182,183],[182],{"code":39,"score":106,"supported":53,"title":255,"abstract":256,"tags":257},[],[109,110],[26],{"code":259,"score":20,"supported":53,"title":260,"abstract":261,"tags":264},"A2",[],[262,263],"小麦","wheat",[],{"code":266,"score":20,"supported":53,"title":267,"abstract":268,"tags":271},"A6",[],[269,270],"甘蔗","sugarcane",[],{"code":273,"score":274,"supported":53,"title":275,"abstract":276,"tags":278},"H8",3,[],[277],"可持续农业",[],{"code":49,"score":280,"supported":13,"title":281,"abstract":282,"tags":283},2,[],[],[29,149],[285,286],"Sentinel-1 Sentinel-2 作物分类","Google Earth Engine 机器学习 作物制图","Sentinel-1Sentinel-2作物分类-4321","10.1007\u002Fs43621-026-04839-6",{"doi":288,"openalex_id":290,"authors":291,"venue":231,"cited_by_count":59,"oa_url":228,"card":305,"direction":66,"ingested_from":129},"W7219792303",[292,295,298,300,303],{"name":293,"orcid":294},"Rajeev Ranjan Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-2670-6189",{"name":296,"orcid":297},"Jayanta Das","https:\u002F\u002Forcid.org\u002F0000-0003-0995-9114",{"name":299,"orcid":8},"Jadhav Rajaram Anna",{"name":301,"orcid":302},"Abhishek Danodia","https:\u002F\u002Forcid.org\u002F0000-0002-5724-8790",{"name":304,"orcid":8},"Dipanwita Haldar",{"tldr":306,"method":307,"finding":308,"direction":222,"opportunity":309},"融合Sentinel-1 SAR与Sentinel-2光学时序，用集成机器学习实现印度早季作物类型高","GEE平台，RF与GBT集成学习，1141个地面样本，SAR-光学多时相数据。","GBT精度最高（总体93%，Kappa 0.90），SAR与光学结合显著优于单传感器。","可探索更早物候期、小样本作物（如芥菜、甘蔗）的SAR-光学特征优化与迁移学习。","2026-10-06T23:30:38.288174Z",{"id":312,"title":313,"url":314,"summary":315,"summary_zh":316,"content":8,"source_name":317,"source_url":314,"published_at":318,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":319,"score_detail":320,"sources":323,"tags":325,"primary_topic":328,"secondary_topics":329,"classification":330,"search_phrases":375,"slug":378,"view_count":274,"doi":379,"paper":380,"created_at":412},4091,"Supporting Digital Agriculture Through GeoAI : A Crop Type Dataset of Four Food Basket Crops in Rwanda","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fgdj3.70097","ABSTRACT Agriculture is a major economic activity, contributing approximately 25% of Rwanda's gross domestic product and employing nearly 65% of its population. Recognising its critical role, the Government of Rwanda has prioritised digital agriculture to manage the sector sustainably. Decision support systems based on remote sensing and Geospatial Artificial Intelligence (GeoAI) offer a transformative opportunity to enhance regional food security by providing real‐time data, improving agricultural forecasting and mitigating the impacts of climate variability. However, GeoAI approaches require labelled, ground‐referenced crop type data for model calibration and validation, which is scarce in sub‐Saharan Africa. To address this gap, we collected crop type data across Musanze, Nyabihu, Nyagatare and Ruhango districts of Rwanda between May and June 2025 to support the development of GeoAI crop monitoring approaches. The dataset, collected using KoboToolbox, integrates the Joint Experiment for Crop Assessment and Monitoring guidelines for field data collection and the Food and Agriculture Organisation's indicative crop classification. We targeted four food‐basket crops from Rwanda's Crop Intensification Programme: bean, maize, Irish potato and rice. In total, 2739 GPS‐located points were collected and used to generate 914 crop‐labelled polygons: 112 for beans, 107 for Irish potato, 417 for maize, 34 for rice and 244 for mixed‐crop fields. Polygons were digitised using four cardinal‐direction photographs taken during fieldwork and Planet imagery acquired during the season. Besides crop labels, the point data include detailed agronomic information such as farm management practices, anti‐erosion measures, cropping systems, agroforestry practices (including fruit‐tree presence), administrative units and GPS coordinates. This rich dataset provides robust, nuanced information for crop monitoring, yield estimation and digital agriculture innovation in Rwanda and beyond.","农业是一项主要的经济活动，贡献了卢旺达约25%的国内生产总值，并雇用了近65%的人口。认识到农业的关键作用，卢旺达政府已将数字农业列为优先事项，以实现该部门的可持续管理。基于遥感和地理空间人工智能（GeoAI）的决策支持系统提供了变革性机遇，可通过提供实时数据、改进农业预测和减轻气候变率的影响来增强区域粮食安全。然而，GeoAI方法需要标记的地面参考作物类型数据用于模型校准和验证，而这在撒哈拉以南非洲地区十分稀缺。为填补这一空白，我们于2025年5月至6月期间在卢旺达穆桑泽、尼亚比胡、尼亚加塔雷和鲁汉戈四个地区收集了作物类型数据，以支持GeoAI作物监测方法的开发。该数据集使用KoboToolbox收集，整合了作物评估与监测联合实验的野外数据收集指南以及联合国粮食及农业组织的指示性作物分类。我们针对卢旺达作物集约化计划中的四种粮篮作物：菜豆、玉米、爱尔兰马铃薯和水稻。共收集了2739个GPS定位点，用于生成914个作物标记多边形：112个菜豆、107个爱尔兰马铃薯、417个玉米、34个水稻和244个混合作物田块。多边形利用野外工作中拍摄的四个基本方位照片和当季获取的Planet影像进行数字化。除作物标签外，点位数据还包括详细的农艺信息，如农场管理实践、防侵蚀措施、种植制度、农林业实践（包括果树存在情况）、行政单元和GPS坐标。这一丰富的数据集为卢旺达及其他地区的作物监测、产量估算和数字农业创新提供了稳健而细致的信息。","Geoscience Data Journal","2026-10-01T00:00:00Z",78,{"impact":234,"substance":16,"depth":18,"authority":321,"freshness":19,"relevant":21,"comment":322},14,"基于GeoAI的卢旺达四类主粮作物地面标注数据集，2739个GPS点位、914个作物多边形，数据规模与方法规范性强，对遥感作物监测与数字农业研究有实质参考价值。",[324],{"name":317,"url":314},[326,26,27,327,29],"数字农业","农业遥感",{"code":49,"slug":157,"name":158,"path":159,"parent_code":94},[],{"status":97,"locked":13,"version":34,"method":35,"evidence":331},{"candidates":332,"agricultural_evidence":53},[333,338,342,347,351,358,365,369],{"code":39,"score":234,"supported":53,"title":334,"abstract":336,"tags":337},[335],"digital agriculture",[326,335],[326,26],{"code":49,"score":19,"supported":53,"title":339,"abstract":340,"tags":341},[],[149,170],[29,327],{"code":44,"score":106,"supported":53,"title":343,"abstract":344,"tags":346},[],[102,345],"decision support",[27],{"code":151,"score":20,"supported":53,"title":348,"abstract":349,"tags":350},[],[148,152],[],{"code":352,"score":20,"supported":53,"title":353,"abstract":354,"tags":357},"A3",[],[355,356],"玉米","maize",[],{"code":359,"score":20,"supported":53,"title":360,"abstract":361,"tags":364},"A5",[],[362,363],"马铃薯","potato",[],{"code":179,"score":20,"supported":53,"title":366,"abstract":367,"tags":368},[],[182,183],[],{"code":370,"score":274,"supported":53,"title":371,"abstract":372,"tags":374},"B2",[],[373],"果树",[],[376,377],"卢旺达 作物类型 数据集","GeoAI 作物监测 遥感","卢旺达作物类型数据集-4091","10.1002\u002Fgdj3.70097",{"doi":379,"openalex_id":381,"authors":382,"venue":317,"cited_by_count":59,"oa_url":314,"card":407,"direction":222,"ingested_from":129},"W7215812020",[383,386,388,391,393,395,397,400,402,404],{"name":384,"orcid":385},"Benson Kipkemboi Kenduiywo","https:\u002F\u002Forcid.org\u002F0000-0002-8448-0499",{"name":387,"orcid":8},"Stephen Sande",{"name":389,"orcid":390},"Anastasia Mumbi Wahome","https:\u002F\u002Forcid.org\u002F0000-0002-0471-0697",{"name":392,"orcid":8},"Joseph Chemutt",{"name":394,"orcid":8},"Ange Marie Tesire",{"name":396,"orcid":8},"Samuel Ishimwe",{"name":398,"orcid":399},"Yves Hategekimana","https:\u002F\u002Forcid.org\u002F0000-0002-2430-8072",{"name":401,"orcid":8},"Lilian Ndungu",{"name":403,"orcid":8},"Golo Rademacher",{"name":405,"orcid":406},"Aniruddha Ghosh","https:\u002F\u002Forcid.org\u002F0000-0003-3667-8019",{"tldr":408,"method":409,"finding":410,"direction":222,"opportunity":411},"在卢旺达四区采集四种主粮作物的GPS标注地块数据集，支撑GeoAI作物监测。","KoboToolbox结合JECAM指南与FAO分类，用Planet影像数字化9","获得2739个GPS点与914个作物标注多边形，含农艺管理信息。","可基于该数据集开发小样本\u002F迁移学习作物制图模型，并扩展至更多撒哈拉以南非洲国家。","2026-10-03T23:30:35.255650Z",{"id":414,"title":415,"url":416,"summary":417,"summary_zh":418,"content":8,"source_name":419,"source_url":416,"published_at":420,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":421,"score_detail":422,"sources":424,"tags":426,"primary_topic":428,"secondary_topics":434,"classification":436,"search_phrases":463,"slug":466,"view_count":467,"doi":468,"paper":469,"created_at":488},3829,"Towards accessible smallholder crop classification in the groundnut basin of Senegal","https:\u002F\u002Fdoi.org\u002F10.1088\u002F2976-601x\u002Faea0b8","Abstract Crop type mapping is a critical lever for decision making in smallholder food systems, yet high cost and expertise requirements of developing remote sensing-driven maps as well as need for recurrent data are persistent barriers to incorporating geospatial tools into decision making. To address this gap, we establish a three-part framework to evaluate crop type mapping: (1) performance, (2) temporal transferability, and (3) accessibility. We evaluate geospatial foundation model embeddings (TESSERA and AlphaEarth) against traditional baselines in Senegal’s groundnut basin. We find that the embedding-based approaches, in particular TESSERA, best fulfill these criteria. The TESSERA-based method shows a 78% reduction in both compute compared to a timeseries approach, a reduction in need for custom feature generation, and 28% higher relative accuracy (an absolute improvement of approximately 0.10 weighted F 1) in one crop type classification temporal transfer test. By reducing the reliance on training data, computational resource use, and expertise for data processing, this approach shows potential to contribute to improved smallholder crop type classification.","摘要 作物类型制图是小农粮食系统决策的关键手段，但开发遥感驱动地图的高成本与专业知识要求，以及 recurring 数据的需求，仍是将地理空间工具纳入决策的持续障碍。为弥补这一差距，我们建立了一个三部分框架来评估作物类型制图：（1）性能，（2）时间可迁移性，（3）可及性。我们在塞内加尔花生盆地评估了地理空间基础模型嵌入（TESSERA 和 AlphaEarth）与传统基线方法。我们发现，基于嵌入的方法，尤其是 TESSERA，最能满足这些标准。基于 TESSERA 的方法显示，与时间序列方法相比，计算量减少 78%，对自定义特征生成的需求降低，并且在一项作物类型分类时间迁移测试中相对精度提高 28%（加权 F1 绝对提升约 0.10）。通过减少对训练数据、计算资源使用和数据处理专业知识的依赖，该方法显示出改善小农作物类型分类的潜力。","Environmental Research Food Systems","2026-09-28T00:00:00Z",79,{"impact":18,"substance":16,"depth":18,"authority":143,"freshness":19,"relevant":21,"comment":423},"该研究提出兼顾性能、时序迁移性与可及性的作物分类评估框架，用地理空间基础模型显著降低算力与训练数据依赖，对小农户农业遥感应用具有实质参考价值。",[425],{"name":419,"url":416},[26,27,327,427,29],"小农户",{"code":429,"slug":430,"name":431,"path":432,"parent_code":433},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[435],{"code":49,"slug":157,"name":158,"path":159,"parent_code":94},{"status":97,"locked":13,"version":34,"method":35,"evidence":437},{"candidates":438,"agricultural_evidence":53},[439,445,449,455,459],{"code":429,"score":440,"supported":53,"title":441,"abstract":443,"tags":444},12,[442],"smallholder",[442],[427],{"code":49,"score":19,"supported":53,"title":446,"abstract":447,"tags":448},[],[149,170],[29,327],{"code":450,"score":274,"supported":53,"title":451,"abstract":452,"tags":454},"A4",[],[453],"花生",[],{"code":39,"score":21,"supported":13,"title":456,"abstract":457,"tags":458},[],[],[26],{"code":44,"score":21,"supported":13,"title":460,"abstract":461,"tags":462},[],[],[27],[464,465],"塞内加尔 花生盆地 作物分类","TESSERA 遥感 作物制图","塞内加尔花生盆地作物分类-3829",5,"10.1088\u002F2976-601x\u002Faea0b8",{"doi":468,"openalex_id":470,"authors":471,"venue":419,"cited_by_count":59,"oa_url":481,"card":482,"direction":487,"ingested_from":129},"W7214087594",[472,474,476,478],{"name":473,"orcid":8},"Madeline Lisaius",{"name":475,"orcid":8},"Srinivasan Keshav",{"name":477,"orcid":8},"Andrew Blake",{"name":479,"orcid":480},"Clement Atzberger","https:\u002F\u002Forcid.org\u002F0000-0003-2169-8009","https:\u002F\u002Fiopscience.iop.org\u002Farticle\u002F10.1088\u002F2976-601X\u002Faea0b8\u002Fpdf",{"tldr":483,"method":484,"finding":485,"direction":222,"opportunity":486},"评估地理空间基础模型嵌入在塞内加尔花生盆地小农作物分类中的性能、时序迁移性和可及性。","对比TESSERA和AlphaEarth嵌入与传统基线，用加权F1和计算量评估。","TESSERA嵌入精度相对提高28%，计算量减少78%，且无需自定义特征生成。","可探索基础模型嵌入在更多小农区域和作物类型上的泛化能力及低成本部署方案。","智慧农业 \u002F 农业物联网","2026-09-30T23:30:11.490990Z",{"id":490,"title":491,"url":492,"summary":493,"summary_zh":8,"content":8,"source_name":494,"source_url":492,"published_at":495,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":496,"score_detail":497,"sources":499,"tags":501,"primary_topic":502,"secondary_topics":506,"classification":507,"search_phrases":522,"slug":525,"view_count":193,"doi":526,"paper":527,"created_at":536},3524,"A hybrid PCA and 1D-CNN approach with regional priors for accurate agricultural monitoring: a case study with EuroCropsML","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10449-z","A hybrid PCA and 1D-CNN approach with regional priors for accurate agricultural monitoring: a case study with EuroCropsML。Precision Agriculture","Precision Agriculture","2026-09-25T00:00:00Z",70,{"impact":440,"substance":18,"depth":82,"authority":321,"freshness":83,"relevant":21,"comment":498},"方法类论文，提出PCA与一维CNN结合并引入区域先验，在EuroCropsML数据集上验证，对作物遥感监测有参考价值，但属细分方法进展，公共影响有限。",[500],{"name":494,"url":492},[26,27,327,29],{"code":39,"slug":503,"name":504,"path":505,"parent_code":94},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture",[],{"status":97,"locked":13,"version":34,"method":35,"evidence":508},{"candidates":509,"agricultural_evidence":53},[510,514,518],{"code":39,"score":193,"supported":53,"title":511,"abstract":512,"tags":513},[],[110],[26],{"code":49,"score":280,"supported":13,"title":515,"abstract":516,"tags":517},[],[],[29,327],{"code":44,"score":21,"supported":13,"title":519,"abstract":520,"tags":521},[],[],[27],[523,524],"EuroCropsML 作物分类","PCA 1D-CNN 农业监测","EuroCropsML作物分类-3524","10.1007\u002Fs11119-026-10449-z",{"doi":526,"openalex_id":528,"authors":529,"venue":494,"cited_by_count":59,"oa_url":8,"card":8,"direction":222,"ingested_from":129},"W7214386719",[530,533],{"name":531,"orcid":532},"Nourelhouda Groun","https:\u002F\u002Forcid.org\u002F0000-0002-8099-0627",{"name":534,"orcid":535},"Kheir-eddine Otmani","https:\u002F\u002Forcid.org\u002F0000-0002-7487-0928","2026-09-26T23:30:03.186961Z"]