[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-234":3,"related-234":86},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":43,"search_phrases":80,"slug":83,"view_count":84,"doi":8,"paper":8,"created_at":85},234,"舜耕粮安农业遥感大模型发布——山东省农科院党委书记梁金光介绍全链条智能监测体系","https:\u002F\u002Fnews.cau.edu.cn\u002Fmtndnew\u002F37a295bf8e3c4e5b92cb8c665bdc8f4f.htm","山东省农业科学院发布舜耕粮安农业遥感大模型。山东省农科院党委书记梁金光介绍,该模型基于20年来积累的2000万份人工样本的海量数据,覆盖山东全域全地貌、全物候周期,构建起耕地智能提取—肥力墒情预测—作物精准识别—长势动态监测—病虫草害预警—作物智能估产全链条智能监测体系,精度高达95%,效率提升超100%。山东省同步推动人工智能+农业行动实施,在寿光推广第七代智能物联网云棚,物联网应用率超85%,劳动生产效率较以往翻倍;在烟台莱山区,浪潮云洲联合中国农业大学打造莱山葡萄种植和酿造大模型,实现水肥精准配施、病虫害智能预警、AI模拟发酵陈酿。",null,"技术的生命力在于解决实际问题。放眼全国，农业面临着劳动力老龄化、气候变化风险加剧等压力，也存在特色产业附加值低、品牌力不强等问题。人工智能的介入推动农业从“靠经验”转向“靠数据”，为端牢“中国饭碗”、塑强农业产业注入确定性。在不少人看来，人工智能的应用推广，恰逢其时。\n\n“山东是农业大省，也是农业产业化发源地，产业规模大、业态全，生产者队伍素质高、接受新事物能力强。与此同时，山东工业基础雄厚，人工智能技术发展迅速。新技术在农业方面的转化推广具有显著的成本和效率优势。”省委党校（山东行政学院）教授、山东乡村振兴研究院院长刘岳认为，山东有着发展“人工智能+农业”的坚实基础，在完整的产业体系、可观市场规模、丰富应用场景等优势加持下，田野阡陌将释放出更多可能。\n\n夏日的鲁北平原，玉米拔节生长，一片生机盎然。在齐河县金穗粮食种植专业合作社的示范田里，一套黑色管网发挥着大作用。“这是我们铺设的水肥一体化设施。每30厘米有一个出水孔，能精准滴灌到玉米根底部位置。相比大水漫灌，它的灌溉速度快3倍，可省水30%，一人一天能管理200亩地。”合作社理事长袁本刚说。依托大数据平台，合作社还可在“云端”实施全程监管，动动手指就能依据检测数据制订分地块水肥管理方案，为各村玉米田定制个性化基肥配方，同步开展测土配方、作物叶绿素检测等服务。\n\n今年山东夏粮逆势丰收，连续4年实现面积、单产、总产“三增”，这离不开水肥一体化技术在大田的推广。数据显示，2025年，全省应用水肥一体化技术的粮油作物面积已达到630万亩。“水肥一体化与减垄增地、‘大小行’密植等结合，加速了良种、良法、良机、良田深度融合，有效提升了农田规模化、标准化种植水平。”袁本刚体会深切，水肥一体化的落地，让丰收有了更充实的底气。\n\n种子是农业的“芯片”，也是保障粮食安全的关键，智能育种已成为育种科研人员聚焦的热点领域。\n\n今年4月，由中国农业科学院作物科学研究所与山东极智生物科技有限公司联合研发的“iWheat小麦智能设计育种平台”发布。对青岛农业大学小麦遗传育种团队来说，iWheat的应用正在帮助其攻克小麦育种“周期长、效率低、成本高”等行业难题。\n\n这一平台整合3万余份小麦种质资源的基因型、442个功能基因、6000余个功能位点及40余万条表型数据，为每一份种质建立起“数字身份证”，实现资源的精准检索与高效利用。“结合快速繁育体系，能将传统8年的育种周期压缩2至3年。”团队负责人张玉梅说，加速新品种的培育进程、降低育种成本，意味着更能提升整个种业行业的创新能力和竞争力，进而赋能小麦产业链上下游实现高质量发展。","大众日报 2026-08-02","2026-08-02T00:00:00Z","报道",10,false,64,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},20,15,14,5,1,"报道山东农业遥感大模型发布，结合水肥一体化与智能育种案例，省级产业进展，信息较充实，但时效稍旧。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","山东省农科院","人工智能+农业","舜耕粮安","农业遥感大模型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":36},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":44,"locked":14,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":50},[49,56,62,69,75],{"code":32,"score":19,"supported":50,"title":51,"abstract":53,"tags":55},true,[52],"遥感",[52,54],"估产",[],{"code":39,"score":57,"supported":50,"title":58,"abstract":60,"tags":61},12,[59],"大模型",[59],[28],{"code":63,"score":64,"supported":50,"title":65,"abstract":66,"tags":68},"B2",3,[],[67],"葡萄",[],{"code":70,"score":64,"supported":50,"title":71,"abstract":72,"tags":74},"I5",[],[73],"物联网",[],{"code":76,"score":21,"supported":14,"title":77,"abstract":78,"tags":79},"I1",[],[],[26],[81,82],"农业遥感大模型 人工智能+农业 山东省农科院 智慧农业","农业遥感大模型 人工智能+农业","农业遥感大模型人工智能+农业山东省农科院智慧农业-234",9,"2026-08-05T23:53:01.179071Z",{"total":87,"page":21,"page_size":87,"items":88},6,[89,200,253,324,403,499],{"id":90,"title":91,"url":92,"summary":93,"summary_zh":94,"content":8,"source_name":95,"source_url":92,"published_at":96,"category":97,"cover_url":8,"hotness":13,"is_selected":14,"score":98,"score_detail":99,"sources":103,"tags":105,"primary_topic":110,"secondary_topics":111,"classification":113,"search_phrases":170,"slug":173,"view_count":174,"doi":175,"paper":176,"created_at":199},5582,"AI-Based RGB Imaging and 14-Channel Multispectral Food Quality Scanner","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85255","Food-quality assessment plays an important role in food safety, agricultural processing, storage, and supply-chain management. Conventional inspection methods depend on visual judgement or laboratory-based testing, which may require considerable time, specialised equipment, and manual effort. Recent developments in computer vision, multispectral sensing, and artificial intelligence (AI) provide opportunities for automated, non-destructive food-quality assessment. This paper reviews the application of RGB imaging, multispectral sensing, machine learning, and deep learning for fruit-ripeness estimation, surfacedefect detection, grain classification, and food-authenticity assessment. The reviewed literature demonstrates that RGB imaging can extract visible features such as colour, shape, and texture, whereas multispectral sensing provides wavelength-dependent information associated with food characteristics. Published studies have reported promising results in tomato-ripeness classification, apple-defect detection, rice-grain analysis, and honey-adulteration screening. Based on these findings, a compact food-quality scanner integrating an RGB camera, a 14-channel multispectral sensor, controlled illumination, and an embedded processing unit is proposed. The review discusses sensor integration, data preprocessing, feature fusion, classification methods, evaluation metrics, and implementation challenges. It also identifies the need for broader datasets, standardised illumination, independent validation, and resource-efficient AI models to improve the reliability of portable food-inspection systems.","食品质量评估在食品安全、农产品加工、储运和供应链管理中发挥着重要作用。传统检测方法依赖人工目视判断或实验室检测，往往需要较长时间、专用设备和人工投入。近年来，计算机视觉、多光谱传感和人工智能（AI）的发展为自动化、无损食品质量评估提供了新的机遇。本文综述了RGB成像、多光谱传感、机器学习和深度学习在果实成熟度估计、表面缺陷检测、谷物分类和食品真实性评估中的应用。所综述的文献表明，RGB成像能够提取颜色、形状和纹理等可见特征，而多光谱传感则可提供与食品特性相关的波长依赖信息。已发表研究在番茄成熟度分类、苹果缺陷检测、稻米籽粒分析和蜂蜜掺假筛查等方面取得了良好结果。基于上述研究结果，本文提出一种集成了RGB相机、14通道多光谱传感器、受控照明和嵌入式处理单元的紧凑型食品质量扫描仪。综述讨论了传感器集成、数据预处理、特征融合、分类方法、评价指标和实现挑战，并指出需要更广泛的数据集、标准化照明、独立验证和资源高效的AI模型，以提高便携式食品检测系统的可靠性。","International Journal for Research in Applied Science and Engineering Technology","2026-10-21T00:00:00Z","论文",65,{"impact":57,"substance":100,"depth":101,"authority":84,"freshness":13,"relevant":21,"comment":102},18,16,"综述性论文，提出集成RGB与14通道多光谱的便携食品质量扫描仪方案，方法框架清晰但缺乏自有实验数据，属细分领域技术进展，可作参考但非重大突破。",[104],{"name":95,"url":92},[26,106,107,108,109],"农业人工智能","无损检测","多光谱成像","食品质量检测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[112],{"code":39,"slug":40,"name":41,"path":42,"parent_code":36},{"status":44,"locked":14,"version":45,"method":46,"evidence":114},{"candidates":115,"agricultural_evidence":50},[116,121,132,140,147,154,160,166],{"code":32,"score":57,"supported":50,"title":117,"abstract":119,"tags":120},[118],"multispectral",[118],[108],{"code":39,"score":13,"supported":50,"title":122,"abstract":123,"tags":131},[],[124,125,126,127,128,129,130],"深度学习","机器学习","计算机视觉","machine learning","deep learning","artificial intelligence","computer vision",[106],{"code":133,"score":134,"supported":50,"title":135,"abstract":136,"tags":139},"E4",7,[],[137,138],"食品安全","food safety",[107],{"code":141,"score":87,"supported":50,"title":142,"abstract":143,"tags":146},"A1",[],[144,145],"稻米","rice",[],{"code":148,"score":87,"supported":50,"title":149,"abstract":150,"tags":153},"B1",[],[151,152],"番茄","tomato",[],{"code":63,"score":87,"supported":50,"title":155,"abstract":156,"tags":159},[],[157,158],"苹果","apple",[],{"code":161,"score":64,"supported":50,"title":162,"abstract":163,"tags":165},"E1",[],[164],"农产品加工",[],{"code":76,"score":21,"supported":14,"title":167,"abstract":168,"tags":169},[],[],[26],[171,172],"RGB成像 多光谱 食品质量","14通道 多光谱 扫描仪","RGB成像多光谱食品质量-5582",0,"10.22214\u002Fijraset.2026.85255",{"doi":175,"openalex_id":177,"authors":178,"venue":95,"cited_by_count":174,"oa_url":92,"card":191,"direction":197,"ingested_from":198},"W7223139905",[179,181,183,185,187,189],{"name":180,"orcid":8},"Eshwari Take",{"name":182,"orcid":8},"Avanish Raut",{"name":184,"orcid":8},"Vedant Joshi",{"name":186,"orcid":8},"Shravani Akolkar",{"name":188,"orcid":8},"R. M. Gharat",{"name":190,"orcid":8},"Shruti Dive",{"tldr":192,"method":193,"finding":194,"direction":195,"opportunity":196},"综述RGB与多光谱成像结合AI的食品品质无损检测，并提出一款集成14通道多光谱传感器的紧凑型扫描仪方","综述RGB成像、多光谱传感与机器学习\u002F深度学习在食品检测中的应用，并提出传感器集","RGB与多光谱融合在番茄成熟度、苹果缺陷、稻米分类和蜂蜜掺假检测中表现良好。","农业人工智能与决策模型","可研究多源光谱特征融合与轻量化模型，构建标准化数据集和便携设备独立验证体系。","数字乡村与农业信息化","openalex","2026-10-22T11:20:48.684398Z",{"id":201,"title":202,"url":203,"summary":204,"summary_zh":205,"content":8,"source_name":206,"source_url":203,"published_at":96,"category":97,"cover_url":8,"hotness":13,"is_selected":14,"score":207,"score_detail":208,"sources":212,"tags":214,"primary_topic":217,"secondary_topics":218,"classification":220,"search_phrases":236,"slug":239,"view_count":174,"doi":240,"paper":241,"created_at":252},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。","Zenodo (CERN European Organization for Nuclear Research)",67,{"impact":209,"substance":17,"depth":210,"authority":57,"freshness":13,"relevant":21,"comment":211},8,17,"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。",[213],{"name":206,"url":203},[26,106,215,52,216],"产量预测","可解释性",{"code":39,"slug":40,"name":41,"path":42,"parent_code":36},[219],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":44,"locked":14,"version":45,"method":46,"evidence":221},{"candidates":222,"agricultural_evidence":50},[223,227,232],{"code":39,"score":57,"supported":50,"title":224,"abstract":225,"tags":226},[130],[126],[106],{"code":32,"score":209,"supported":50,"title":228,"abstract":229,"tags":231},[],[52,230],"remote sensing",[215,52],{"code":76,"score":21,"supported":14,"title":233,"abstract":234,"tags":235},[],[],[26],[237,238],"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":240,"openalex_id":242,"authors":243,"venue":206,"cited_by_count":174,"oa_url":203,"card":246,"direction":250,"ingested_from":198},"W7223114002",[244],{"name":245,"orcid":8},"Kadiatou Barry",{"tldr":247,"method":248,"finding":249,"direction":250,"opportunity":251},"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。","农业遥感与作物表型","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":254,"title":255,"url":256,"summary":257,"summary_zh":258,"content":8,"source_name":259,"source_url":256,"published_at":260,"category":97,"cover_url":8,"hotness":13,"is_selected":14,"score":261,"score_detail":262,"sources":264,"tags":266,"primary_topic":270,"secondary_topics":271,"classification":273,"search_phrases":296,"slug":299,"view_count":21,"doi":300,"paper":301,"created_at":323},5165,"Proximal Remote Sensing of Oil Palm Basal Stem Rot Using Deep Learning Vision Algorithms and Ground-based Images","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.31","Basal Stem Rot (BSR), caused by Ganoderma boninense, threatens oil palm productivity in Southeast Asia.This study develops and benchmarks a low-cost remote sensing framework for BSR severity diagnosis from smartphone-captured RGB trunk images, evaluating two pathways for future field deployment.The first pairs YOLO detection with a Random Forest classifier: YOLO26n gave the best accuracy-to-cost trade-off among three nanovariants for localizing BSR symptoms (mushroom, rot, white-button), and the end-to-end YOLO26n+RF pipeline achieved 0.83 accuracy and macro-F1 of 0.79 across Healthy, Mild, Moderate, and Severe classes.Rot was consistently the hardest symptom to localize, owing to its diffuse, boundary-ambiguous appearance.The second pathway trained four image classifiers (EfficientNet-B0, MobileNetV2, Swin-Tiny, and ConvNeXt-V2-Tiny) directly on severity labels, with ConvNeXt-V2-Tiny performing best (0.83 accuracy, 0.83 macro-F1).Both pathways performed well at severity extremes but struggled with Moderate, reflecting visual overlap between stages.SHAP analysis identified rot-area ratio and fruiting-body count as top predictors.These offline results show accurate BSR diagnosis is potentially achievable from smartphone imagery, laying groundwork for future on-device deployment.","由灵芝（Ganoderma boninense）引起的基茎腐病（Basal Stem Rot, BSR）威胁着东南亚油棕的生产力。本研究开发并基准测试了一个低成本遥感框架，用于从智能手机拍摄的RGB树干图像中诊断基茎腐病的严重程度，并评估了未来田间部署的两条技术路径。第一条路径将YOLO检测与随机森林分类器相结合：在三种纳米变体中，YOLO26n在定位基茎腐病症状（蘑菇、腐烂、白钮）方面实现了最佳的精度-成本权衡，端到端的YOLO26n+RF流程在健康、轻度、中度和重度四个类别上达到了0.83的准确率和0.79的宏F1值。腐烂始终是最难定位的症状，原因在于其弥散且边界模糊的外观。第二条路径直接在严重程度标签上训练了四个图像分类器（EfficientNet-B0、MobileNetV2、Swin-Tiny和ConvNeXt-V2-Tiny），其中ConvNeXt-V2-Tiny表现最佳（准确率0.83，宏F1值0.83）。两条路径在严重程度极端类别上表现良好，但在中度类别上表现欠佳，反映出各阶段之间存在视觉重叠。SHAP分析确定腐烂面积比和子实体数量为最重要的预测因子。这些离线结果表明，利用智能手机图像有望实现准确的基茎腐病诊断，为未来设备端部署奠定了基础。","International journal of intelligent engineering and systems","2026-10-16T00:00:00Z",69,{"impact":57,"substance":17,"depth":101,"authority":57,"freshness":84,"relevant":21,"comment":263},"该研究利用智能手机图像与深度学习实现油棕基腐病严重度诊断，方法新颖、结论可靠，但属细分作物研究，产业影响有限，适合作为技术类精选。",[265],{"name":259,"url":256},[26,267,124,268,269],"农业遥感","油棕","病害诊断",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[272],{"code":39,"slug":40,"name":41,"path":42,"parent_code":36},{"status":44,"locked":14,"version":45,"method":46,"evidence":274},{"candidates":275,"agricultural_evidence":50},[276,280,285,292],{"code":32,"score":18,"supported":50,"title":277,"abstract":278,"tags":279},[230],[52,230],[267],{"code":39,"score":57,"supported":50,"title":281,"abstract":282,"tags":284},[128],[283],"YOLO",[124],{"code":286,"score":87,"supported":50,"title":287,"abstract":288,"tags":291},"B5",[],[289,290],"蘑菇","mushroom",[],{"code":76,"score":21,"supported":14,"title":293,"abstract":294,"tags":295},[],[],[26],[297,298],"油棕 基腐病 遥感","Ganoderma boninense 智能手机 检测","油棕基腐病遥感-5165","10.22266\u002Fijies2026.1130.31",{"doi":300,"openalex_id":302,"authors":303,"venue":259,"cited_by_count":174,"oa_url":256,"card":318,"direction":250,"ingested_from":198},"W7222626135",[304,307,310,312,315],{"name":305,"orcid":306},"Wan Siu Hong","https:\u002F\u002Forcid.org\u002F0000-0002-8254-4962",{"name":308,"orcid":309},"Jonathan Yong Chung Ee","https:\u002F\u002Forcid.org\u002F0000-0003-4079-8005",{"name":311,"orcid":8},"Jin Yuan Chan",{"name":313,"orcid":314},"Mohamad Izzuddin Anuar","https:\u002F\u002Forcid.org\u002F0000-0002-4929-5175",{"name":316,"orcid":317},"Mahmud Iwan Solihin","https:\u002F\u002Forcid.org\u002F0000-0002-5293-7466",{"tldr":319,"method":320,"finding":321,"direction":250,"opportunity":322},"用手机拍摄油棕树干图像，结合深度学习检测与分类，实现基腐病严重度诊断。","YOLO26n+随机森林与四种图像分类器，基于手机RGB图像，SHAP解释。","两条路径准确率均约0.83，中度病级最难区分，腐区比例与子实体数为关键预测因子。","可探索轻量化模型在手机端离线部署，并扩充多地区、多品种数据以提升中度病级辨识。","2026-10-17T23:30:28.307953Z",{"id":325,"title":326,"url":327,"summary":328,"summary_zh":329,"content":8,"source_name":330,"source_url":327,"published_at":331,"category":97,"cover_url":8,"hotness":13,"is_selected":14,"score":332,"score_detail":333,"sources":337,"tags":339,"primary_topic":342,"secondary_topics":343,"classification":351,"search_phrases":377,"slug":380,"view_count":174,"doi":381,"paper":382,"created_at":402},5006,"Mapping Soil Salinity in Arid Agricultural Regions Using Multi-Source Remote Sensing and a Long-Range Dependency-Enhanced Deep Learning Framework","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fland15101966","Soil salinity estimation across arid agricultural regions is challenging due to pronounced environmental heterogeneity and complex dependencies among multi-source variables. This study proposes a Long-Range Dependency-Enhanced Network (LRD-Net) for regional-scale soil salinity estimation in multiple agricultural oasis regions using multi-source remote sensing and environmental covariates. A dataset comprising 180 field samples from three agricultural oasis regions in Xinjiang, China, was constructed with 25 covariates derived from spectral, topographic, climatic, and soil property data. LRD-Net consists of three stages: a multi-scale feature fusion backbone based on depthwise separable convolutions and cross-scale interaction; a Long-Range Dependency Enhancement Module (LDEM) with an asymmetric dual-branch architecture that captures forward and reverse-aware dependencies through reverse alignment and cross-directional fusion; and multi-scale attention refinement with a regression head for continuous salinity estimation. Under the region-stratified random-split evaluation, LRD-Net achieved an R2 of 0.905, an RMSE of 1.207 g·kg−1, and an MAE of 0.868 g·kg−1. Performance decreased under more spatially independent validation, with an R2 of 0.874 under spatial cross-validation and LORO test R2 values ranging from 0.739 to 0.801, indicating that prediction across spatially and geographically independent samples is more challenging than region-stratified random-split evaluation. The proposed framework effectively integrates multi-source information and captures complementary long-range dependencies, providing a potential approach for regional-scale soil salinity estimation within the studied arid agricultural oasis environments and supporting soil salinization monitoring and sustainable land management in the study region.","干旱农业区域土壤盐分估算面临显著的环境异质性和多源变量间复杂依赖关系的挑战。本研究提出了一种长程依赖增强网络（LRD-Net），利用多源遥感与环境协变量对多个农业绿洲区域进行区域尺度土壤盐分估算。研究构建了包含中国新疆三个农业绿洲区域180个野外样本的数据集，并衍生出25个协变量，涵盖光谱、地形、气候和土壤属性数据。LRD-Net由三个阶段组成：基于深度可分离卷积和跨尺度交互的多尺度特征融合骨干网络；具有非对称双分支架构的长程依赖增强模块（LDEM），通过反向对齐和跨方向融合捕获前向与反向感知依赖关系；以及多尺度注意力细化与回归头，用于连续盐分估算。在区域分层随机划分评估下，LRD-Net取得了R²为0.905、RMSE为1.207 g·kg⁻¹、MAE为0.868 g·kg⁻¹的性能。在空间独立性更强的验证下性能有所下降，空间交叉验证R²为0.874，留一区域测试R²范围为0.739至0.801，表明跨空间和地理独立样本的预测比区域分层随机划分评估更具挑战性。所提出的框架有效整合了多源信息并捕获了互补的长程依赖关系，为研究区干旱农业绿洲环境下的区域尺度土壤盐分估算提供了潜在方法，并支持研究区土壤盐渍化监测与可持续土地管理。","Land","2026-10-14T00:00:00Z",72,{"impact":57,"substance":334,"depth":210,"authority":335,"freshness":84,"relevant":21,"comment":336},21,13,"方法新颖、数据扎实的遥感土壤盐渍化估算研究，对干旱区盐碱地监测与治理有参考价值，但属细分领域学术进展，公共影响有限。",[338],{"name":330,"url":327},[26,106,52,340,341],"土壤盐渍化","新疆农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[344,350],{"code":345,"slug":346,"name":347,"path":348,"parent_code":349},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":39,"slug":40,"name":41,"path":42,"parent_code":36},{"status":44,"locked":14,"version":45,"method":46,"evidence":352},{"candidates":353,"agricultural_evidence":50},[354,358,363,367,373],{"code":32,"score":18,"supported":50,"title":355,"abstract":356,"tags":357},[230],[52,230],[52],{"code":345,"score":19,"supported":50,"title":359,"abstract":360,"tags":362},[346],[361,346],"土壤",[],{"code":39,"score":84,"supported":50,"title":364,"abstract":365,"tags":366},[128],[],[106],{"code":368,"score":64,"supported":50,"title":369,"abstract":370,"tags":372},"H7",[],[371],"干旱",[],{"code":76,"score":21,"supported":14,"title":374,"abstract":375,"tags":376},[],[],[26],[378,379],"新疆 农业绿洲 土壤盐渍化 遥感","LRD-Net 土壤盐分 估算","新疆农业绿洲土壤盐渍化遥感-5006","10.3390\u002Fland15101966",{"doi":381,"openalex_id":383,"authors":384,"venue":330,"cited_by_count":174,"oa_url":327,"card":397,"direction":250,"ingested_from":198},"W7221816183",[385,387,390,392,394],{"name":386,"orcid":8},"Mingjie Qian",{"name":388,"orcid":389},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":391,"orcid":8},"Peng Wang",{"name":393,"orcid":8},"Hangyuan Liu",{"name":395,"orcid":396},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":398,"method":399,"finding":400,"direction":250,"opportunity":401},"提出LRD-Net深度学习框架，融合多源遥感与环境协变量，估算新疆干旱绿洲区土壤盐分。","构建180个样点、25个协变量的数据集，设计含长程依赖增强模块的多尺度网络。","区域分层随机划分下R²达0.905，但空间独立验证R²降至0.739-0.874，跨区域预测更难。","可探索跨区域迁移学习与不确定性量化，提升空间独立场景下盐分制图泛化能力。","2026-10-15T23:30:29.667342Z",{"id":404,"title":405,"url":406,"summary":407,"summary_zh":408,"content":8,"source_name":409,"source_url":406,"published_at":331,"category":97,"cover_url":8,"hotness":13,"is_selected":14,"score":410,"score_detail":411,"sources":414,"tags":416,"primary_topic":418,"secondary_topics":419,"classification":426,"search_phrases":471,"slug":474,"view_count":21,"doi":475,"paper":476,"created_at":498},4988,"Hierarchical cross-modal spatiotemporal attention network for crop yield prediction in complex Himalayan agroecosystems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1933033","Introduction Accurate crop yield prediction is essential for precision agriculture, climate-resilient farm management, and timely decision-making. However, yield prediction remains challenging because of complex, nonlinear, and multi-scale interactions among crop physiology, soil conditions, weather variability, and management practices. Conventional statistical, machine learning, and deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, often have limitations in capturing long-range temporal dependencies, hierarchical spatial relationships, heterogeneous data modalities, and predictive uncertainty. Methods This study proposes a Hierarchical Cross-Modal Spatio-Temporal Attention Network (HCM-STAN) for crop yield prediction using a unified attention-based framework for integrating heterogeneous agro-environmental data. The architecture incorporates four principal components: (i) hierarchical spatio-temporal attention operating across tree, block, orchard, and regional scales; (ii) a cross-modal attention module for adaptive fusion of IoT-based soil sensor observations, weather data, plant physiological measurements, and drone-based multispectral imagery; (iii) a soil-aware attention head that explicitly models soil memory, hysteresis effects, and root-zone dynamics; and (iv) an uncertainty-aware prediction module combining Monte Carlo dropout and quantile regression to generate calibrated prediction intervals. The framework was evaluated using a multi-source dataset collected from Himalayan apple orchards during 2023–2026, comprising 1,247 monitored trees across three commercial orchards. Results The proposed HCM-STAN achieved an R 2 of 0.89 for four-week-ahead crop yield prediction, representing a 15.6% improvement over the CNN-LSTM baseline. Furthermore, zero-shot transfer to mango orchards achieved an R 2 of 0.67, corresponding to approximately 75% of the performance obtained under full training. Discussion The results demonstrate that integrating hierarchical spatio-temporal representation learning, cross-modal attention, soil-aware modelling, and uncertainty estimation can effectively address the heterogeneous and dynamic nature of crop yield prediction in complex mountain agroecosystems. The observed zero-shot transfer performance further indicates the potential of HCM-STAN to generalize across crop systems without crop-specific retraining. Overall, the proposed framework provides a promising foundation for reliable, uncertainty-aware yield forecasting and can support precision agriculture, climate-smart farm management, and data-driven decision-making in heterogeneous agroecosystems.","引言 准确的作物产量预测对于精准农业、气候适应性农场管理以及及时决策至关重要。然而，由于作物生理、土壤条件、天气变异和管理措施之间复杂、非线性且多尺度的相互作用，产量预测仍然具有挑战性。传统的统计方法、机器学习以及深度学习方法，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM）网络，在捕捉长程时间依赖关系、层次化空间关系、异构数据模态以及预测不确定性方面往往存在局限。方法 本研究提出了一种用于作物产量预测的层次化跨模态时空注意力网络（HCM-STAN），采用统一的基于注意力的框架来整合异构农业环境数据。该架构包含四个主要组成部分：（i）在树、地块、果园和区域尺度上运行的层次化时空注意力；（ii）用于自适应融合基于物联网的土壤传感器观测、天气数据、植物生理测量和无人机多光谱影像的跨模态注意力模块；（iii）显式建模土壤记忆、滞后效应和根区动态的土壤感知注意力头；（iv）结合蒙特卡洛 dropout 和分位数回归以生成校准预测区间的不确定性感知预测模块。该框架使用2023—2026年在喜马拉雅苹果园采集的多源数据集进行了评估，该数据集包含三个商业果园中1，247棵监测树木。结果 所提出的 HCM-STAN 在提前四周作物产量预测中达到了0.89的 R²，相较于 CNN-LSTM 基线提升了15.6%。此外，零样本迁移至芒果园达到了0.67的 R²，相当于完整训练下所获性能的约75%。讨论 结果表明，整合层次化时空表征学习、跨模态注意力、土壤感知建模和不确定性估计，能够有效应对复杂山地农业生态系统中作物产量预测的异构性和动态性。观察到的零样本迁移性能进一步表明，HCM-STAN 具有在无需作物特定再训练的情况下跨作物系统泛化的潜力。总体而言，该 p","Frontiers in Plant Science",81,{"impact":100,"substance":412,"depth":100,"authority":19,"freshness":84,"relevant":21,"comment":413},22,"提出分层跨模态时空注意力网络，融合物联网土壤传感、气象、生理与无人机多光谱数据，苹果园四周产量预测R²达0.89并实现芒果园零样本迁移，方法新颖、数据扎实，对智慧农业产量预报有参考价值。",[415],{"name":409,"url":406},[26,106,215,417,52],"多模态融合",{"code":39,"slug":40,"name":41,"path":42,"parent_code":36},[420,425],{"code":63,"slug":421,"name":422,"path":423,"parent_code":424},"fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":44,"locked":14,"version":45,"method":46,"evidence":427},{"candidates":428,"agricultural_evidence":50},[429,434,440,445,451,455,460,466],{"code":39,"score":430,"supported":50,"title":431,"abstract":432,"tags":433},11,[],[124,125,127,128],[106,417],{"code":63,"score":84,"supported":50,"title":435,"abstract":436,"tags":439},[],[157,437,438,158],"芒果","orchard",[],{"code":32,"score":209,"supported":50,"title":441,"abstract":442,"tags":444},[],[443,118],"无人机多光谱",[215,52],{"code":76,"score":134,"supported":50,"title":446,"abstract":447,"tags":450},[],[448,449],"精准农业","precision agriculture",[26],{"code":345,"score":87,"supported":50,"title":452,"abstract":453,"tags":454},[],[361,346],[],{"code":70,"score":87,"supported":50,"title":456,"abstract":457,"tags":459},[],[73,458],"IoT",[],{"code":461,"score":64,"supported":50,"title":462,"abstract":463,"tags":465},"H6",[],[464],"农业生态",[],{"code":368,"score":64,"supported":50,"title":467,"abstract":468,"tags":470},[],[469],"气候适应",[],[472,473],"喜马拉雅 苹果园 产量预测","HCM-STAN 作物产量预测","喜马拉雅苹果园产量预测-4988","10.3389\u002Ffpls.2026.1933033",{"doi":475,"openalex_id":477,"authors":478,"venue":409,"cited_by_count":174,"oa_url":406,"card":492,"direction":497,"ingested_from":198},"W7221795850",[479,482,484,486,488,490],{"name":480,"orcid":481},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":483,"orcid":8},"Umarfarooque Momin",{"name":485,"orcid":8},"Sudeep Kumar E",{"name":487,"orcid":8},"Itfaq Ahmad Mir",{"name":489,"orcid":8},"Ab Rouf Khan",{"name":491,"orcid":8},"Ghulam Mohammad Mir",{"tldr":493,"method":494,"finding":495,"direction":195,"opportunity":496},"提出分层跨模态时空注意力网络HCM-STAN，融合多源农业数据预测喜马拉雅山区苹果产量。","用IoT土壤、气象、生理和无人机多光谱数据，结合分层时空与跨模态注意力及不确定性","四周前产量预测R²达0.89，比CNN-LSTM提升15.6%，零样本迁移芒果R²为0.67。","可探索跨作物零样本迁移的领域自适应机制，并验证模型在更多山地农业生态系统的泛化能力。","智慧农业 \u002F 农业物联网","2026-10-15T23:30:08.750140Z",{"id":500,"title":501,"url":502,"summary":503,"summary_zh":504,"content":8,"source_name":505,"source_url":502,"published_at":506,"category":97,"cover_url":8,"hotness":13,"is_selected":14,"score":507,"score_detail":508,"sources":510,"tags":512,"primary_topic":514,"secondary_topics":515,"classification":518,"search_phrases":541,"slug":544,"view_count":174,"doi":545,"paper":546,"created_at":569},4898,"An Interpretable Deep Learning Framework for Spatial Prediction of Soil Salinity Using Multi-Source Remote Sensing and Environmental Data: A Case Study of Cangzhou, Hebei Province, China","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26206465","Soil salinity poses a significant challenge to agricultural productivity and sustainable land management in coastal and semi-arid regions. Soil salinity in coastal agricultural regions is controlled by complex interactions among surface conditions, groundwater processes, soil properties, and terrain characteristics. Accurate spatial prediction requires integrating remote sensing observations with environmental information that represents these processes. This study presents a multi-source deep learning framework that integrates Sentinel-2-derived spectral indices with environmental covariates for regional soil salinity spatial prediction under the environmental conditions of the 2024 sampling period. SHapley Additive exPlanations (SHAP) is employed to quantify the contribution of environmental variables within the prediction framework and improve model interpretability. A convolutional neural network (CNN) incorporating a squeeze-and-excitation (SE) attention mechanism is developed as a nonlinear feature representation framework for integrating heterogeneous predictors, while the Crested Porcupine Optimizer (CPO) is used to optimize model hyperparameters. The proposed framework achieved the highest predictive performance among the benchmark models, with an R2 of 0.785, an RMSE of 0.928, and an MAE of 0.720. Integrating environmental covariates with spectral features further improves the prediction performance, increasing the R2 from 0.701 to 0.785. The results indicate the potential of integrating multi-source environmental information with interpretable deep learning for spatial prediction of near-surface soil salinity under similar coastal agricultural conditions.","土壤盐渍化对沿海和半干旱地区的农业生产力和可持续土地管理构成了重大挑战。沿海农业区域的土壤盐渍化受地表条件、地下水过程、土壤属性和地形特征之间复杂相互作用的控制。准确的空间预测需要将遥感观测与表征这些过程的环境信息相结合。本研究提出了一种多源深度学习框架，该框架将Sentinel-2衍生的光谱指数与环境协变量相结合，用于2024年采样期环境条件下的区域土壤盐渍化空间预测。采用SHapley加法解释（SHAP）方法量化预测框架中环境变量的贡献并提高模型可解释性。开发了一种融合压缩-激励（SE）注意力机制的卷积神经网络（CNN）作为非线性特征表示框架，用于整合异质性预测因子，同时使用冠豪猪优化器（CPO）优化模型超参数。所提出的框架在基准模型中取得了最高的预测性能，R²为0.785，RMSE为0.928，MAE为0.720。将环境协变量与光谱特征相结合进一步提高了预测性能，R²从0.701提升至0.785。结果表明，在类似的沿海农业条件下，将多源环境信息与可解释深度学习相结合用于近地表土壤盐渍化空间预测具有潜力。","Sensors","2026-10-13T00:00:00Z",75,{"impact":101,"substance":334,"depth":210,"authority":335,"freshness":209,"relevant":21,"comment":509},"方法新颖、指标可靠，将多源遥感与可解释深度学习结合用于盐渍化空间预测，对沿海农业区土壤治理有参考价值。",[511],{"name":505,"url":502},[26,267,513,124,340],"可解释AI",{"code":39,"slug":40,"name":41,"path":42,"parent_code":36},[516,517],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":345,"slug":346,"name":347,"path":348,"parent_code":349},{"status":44,"locked":14,"version":45,"method":46,"evidence":519},{"candidates":520,"agricultural_evidence":50},[521,525,529,533,537],{"code":39,"score":101,"supported":50,"title":522,"abstract":523,"tags":524},[128],[124,128],[513,124],{"code":32,"score":18,"supported":50,"title":526,"abstract":527,"tags":528},[230],[52,230],[267],{"code":345,"score":19,"supported":50,"title":530,"abstract":531,"tags":532},[346],[361,346],[],{"code":368,"score":64,"supported":50,"title":534,"abstract":535,"tags":536},[],[371],[],{"code":76,"score":21,"supported":14,"title":538,"abstract":539,"tags":540},[],[],[26],[542,543],"沧州 土壤盐渍化 遥感","Sentinel-2 土壤盐分 预测","沧州土壤盐渍化遥感-4898","10.3390\u002Fs26206465",{"doi":545,"openalex_id":547,"authors":548,"venue":505,"cited_by_count":174,"oa_url":502,"card":564,"direction":250,"ingested_from":198},"W7221715654",[549,552,555,557,560,562],{"name":550,"orcid":551},"Mingyuan Ye","https:\u002F\u002Forcid.org\u002F0009-0001-6434-5505",{"name":553,"orcid":554},"Peng Chen","https:\u002F\u002Forcid.org\u002F0000-0002-2549-6765",{"name":556,"orcid":8},"Junchi Ma",{"name":558,"orcid":559},"Bingxia Liu","https:\u002F\u002Forcid.org\u002F0000-0001-7958-7112",{"name":561,"orcid":8},"Jiahao Qi",{"name":563,"orcid":8},"Yuan Jing",{"tldr":565,"method":566,"finding":567,"direction":250,"opportunity":568},"构建融合多源遥感与环境变量的可解释深度学习框架，预测沧州土壤盐分空间分布。","Sentinel-2光谱指数+环境协变量，CNN-SE注意力，CPO优化超参数，","环境协变量与光谱特征结合将R²从0.701提升至0.785，模型性能最优。","可迁移至其他滨海盐渍区，并探索时序动态预测与多深度土壤盐分协同反演。","2026-10-14T23:30:27.313838Z"]