[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3155":3,"related-3155":110},{"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":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":80,"slug":83,"view_count":75,"doi":84,"paper":85,"created_at":109},3155,"Time Series Extrinsic Regression for Smart Agriculture: Field‐Level Crop Yield Prediction From Multisource Agricultural Time Series","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fqre.70406","ABSTRACT The growing availability of temporal data in agriculture has created new opportunities for data‐driven decision support systems aimed at improving the efficiency, sustainability, and adaptability of agricultural systems. Remote sensing platforms, weather‐related datasets, and field‐management records provide information on crop development and environmental conditions throughout the growing season. In this context, predictive tasks such as crop yield prediction, irrigation requirement assessment, and nutrient demand estimation can be naturally formulated as Time Series Extrinsic Regression (TSER), a supervised learning task in which a continuous target is predicted from one or more time series. This paper presents TSER within the Smart Agriculture domain and investigates its applicability to field‐level crop yield prediction using multisource agricultural time series. The study adopts a field‐based temporal approach where Sentinel‐2 observations are processed to derive vegetation‐index time series, spatially aggregated at parcel level, and integrated with ERA5‐Land weather‐related variables and static vineyard attributes. Representative neural and non‐neural TSER methods are compared under temporal and spatial generalization scenarios. Results show that TSER provides a suitable supervised learning framework for crop yield prediction from heterogeneous agricultural time series. Conditional LSTM achieves the best overall performance under temporal generalization across vintages, while non‐neural methods remain competitive under spatial generalization to unseen vineyard blocks. These findings suggest that TSER can support field‐level predictive modeling in Smart Agriculture, with model choice depending on the target generalization setting, data availability, and operational constraints.","摘要 农业中时间数据的日益丰富为数据驱动的决策支持系统创造了新的机遇，旨在提高农业系统的效率、可持续性和适应性。遥感平台、气象相关数据集和田间管理记录提供了整个生长季作物发育和环境状况的信息。在此背景下，作物产量预测、灌溉需求评估和养分需求估算等预测任务可以自然地表述为时间序列外在回归（TSER），这是一种监督学习任务，即从一个或多个时间序列中预测连续目标变量。本文在智慧农业领域内介绍TSER，并研究其利用多源农业时间序列进行田块级作物产量预测的适用性。本研究采用基于田块的时间方法，对Sentinel-2观测数据进行处理以导出植被指数时间序列，在地块尺度上进行空间聚合，并与ERA5-Land气象相关变量及静态葡萄园属性相整合。在时间泛化和空间泛化情景下，比较了具有代表性的神经与非神经TSER方法。结果表明，TSER为从异质农业时间序列进行作物产量预测提供了一个合适的监督学习框架。条件LSTM在跨年份的时间泛化下取得了最佳整体性能，而非神经方法在向未见葡萄园地块的空间泛化下仍具有竞争力。这些发现表明，TSER能够支持智慧农业中的田块级预测建模，模型选择取决于目标泛化设置、数据可用性和操作约束。",null,"Quality and Reliability Engineering International","2026-09-22T00:00:00Z","论文",10,false,72,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":13,"relevant":21,"comment":22},12,20,17,13,1,"将时间序列外在回归引入田块级产量预测，方法新颖、结论有对比依据，但属学术论文，产业影响有限。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","遥感","作物产量预测","时间序列",{"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",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":47},[44,52,58,66,73],{"code":45,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},"I1",15,true,[49],"smart agriculture",[26,49],[26],{"code":32,"score":53,"supported":47,"title":54,"abstract":55,"tags":57},8,[],[28,56],"remote sensing",[29,28],{"code":59,"score":60,"supported":47,"title":61,"abstract":62,"tags":65},"H3",6,[],[63,64],"灌溉","irrigation",[],{"code":67,"score":68,"supported":47,"title":69,"abstract":70,"tags":72},"I2",4,[],[71],"decision support",[27],{"code":74,"score":75,"supported":47,"title":76,"abstract":77,"tags":79},"B2",3,[],[78],"葡萄",[],[81,82],"Sentinel-2 作物产量预测","TSER 智慧农业","Sentinel-2作物产量预测-3155","10.1002\u002Fqre.70406",{"doi":84,"openalex_id":86,"authors":87,"venue":10,"cited_by_count":100,"oa_url":6,"card":101,"direction":107,"ingested_from":108},"W7213984793",[88,91,94,96,98],{"name":89,"orcid":90},"Amalia Vanacore","https:\u002F\u002Forcid.org\u002F0000-0002-0320-5541",{"name":92,"orcid":93},"Armando Ciardiello","https:\u002F\u002Forcid.org\u002F0009-0005-7272-9663",{"name":95,"orcid":9},"Gennaro Pio Auricchio",{"name":97,"orcid":9},"Luigi Uccello",{"name":99,"orcid":9},"Annalisa Izzo",0,{"tldr":102,"method":103,"finding":104,"direction":105,"opportunity":106},"将田块级作物产量预测建模为时间序列外回归，比较多源农业时间序列上的神经与非神经方法。","Sentinel-2植被指数、ERA5-Land气象与葡萄园静态属性，对比LST","条件LSTM在跨年份时间泛化最优，非神经方法在空间泛化到新地块时仍有竞争力。","农业遥感与作物表型","可探索多作物、多区域下TSER模型迁移性与不确定性量化，及与农事决策系统耦合。","智慧农业 \u002F 农业物联网","openalex","2026-09-22T23:30:10.381662Z",{"total":60,"page":21,"page_size":60,"items":111},[112,224,276,344,418,513],{"id":113,"title":114,"url":115,"summary":116,"summary_zh":117,"content":9,"source_name":118,"source_url":115,"published_at":119,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":120,"score_detail":121,"sources":127,"tags":129,"primary_topic":131,"secondary_topics":135,"classification":142,"search_phrases":198,"slug":201,"view_count":202,"doi":203,"paper":204,"created_at":223},2160,"An Optimized Temporal Attention-based Deep Learning Framwork for Accurate Crop Yield Prediction from Multi-source Agricultural Data","https:\u002F\u002Fdoi.org\u002F10.18805\u002Fag.d-6558","Background: In precision agriculture, crop yield prediction is crucial for supporting effective management of crops, timely settlement of farmers crop insurances, food security planning and serve as decision tool for sustainable agricultural achievements. However, prediction of crop yield is difficult due to the complex interaction behavior among diverse conditions in weather, soil properties, multispectral remote sensing observations and the dynamics in crop growth. Despite existing AI techniques like machine learning and deep learning models outperformed in predicting crop yield, they are often not able to capture the temporal dependencies. Furthermore, determining optimal hyperparameters for model training remains a challenging task, significantly influencing prediction accuracy, model convergence and generalization performance. Methods: To overcome this, the present study aimed to predict the crop yield using temporal attention (TA) based Artificial bee colony (ABC) optimized Bi - LSTM model using multi source agricultural data. The proposed model learns the sequential and temporal dependencies from both past and future time steps simultaneously, from the historical weather variables, soil properties, remote sensing derived normalized difference vegetation indices (NDVI) and historical yield data. The ABC algorithm was employed to automatically optimize the model hyperparameters with minimum run time. Result: The model is trained using district wise rice yield records of Tamil Nadu, historical weather variables, Sentinel-2 derived NDVI and soil properties. The dataset collected for major rice growing districts from 1995 to 2025 (30 years). The model shows the superior performance over conventional methods like random forest, support vector regression, deep neural network, convolutional neural network, long short-term memory models with lesser root mean square error (RMSE = 298.01 kg ha-1) and higher coefficient of determination, R2 (81.76%). Also, the training time of TA - ABC - Bi-LSTM model is comparatively less than the comparative models because of ABC optimization algorithm tuned the best hyperparameters compared to traditional trial and error manual method.","背景：在精准农业中，作物产量预测对于支持有效的作物管理、农民作物保险的及时理赔、粮食安全规划以及作为实现可持续农业的决策工具至关重要。然而，由于天气、土壤属性、多光谱遥感观测等多种条件之间复杂的交互作用以及作物生长的动态变化，作物产量预测仍然困难。尽管现有的机器学习、深度学习等人工智能技术在作物产量预测方面表现优异，但往往无法捕捉时间依赖性。此外，确定模型训练的最优超参数仍是一项具有挑战性的任务，显著影响预测精度、模型收敛性和泛化性能。方法：为解决上述问题，本研究旨在利用基于时间注意力（TA）的人工蜂群（ABC）算法优化的双向长短期记忆（Bi-LSTM）模型，结合多源农业数据预测作物产量。所提出的模型能够同时从历史和未来时间步中学习序列和时间依赖关系，数据来源包括历史气象变量、土壤属性、遥感衍生的归一化植被指数（NDVI）以及历史产量数据。采用ABC算法以最短运行时间自动优化模型超参数。结果：该模型使用泰米尔纳德邦各地区的稻米产量记录、历史气象变量、Sentinel-2衍生的NDVI和土壤属性进行训练。数据集收集了1995年至2025年（30年）主要水稻种植区的数据。该模型相比随机森林、支持向量回归、深度神经网络、卷积神经网络、长短期记忆模型等传统方法表现出更优的性能，均方根误差更低（RMSE = 298.01 kg ha-1），决定系数R²更高（81.76%）。此外，TA-ABC-Bi-LSTM模型的训练时间相比对比模型更短，因为ABC优化算法相比传统的试错手动方法能够调优出最佳超参数。","Agricultural Science Digest - A Research Journal","2026-09-10T00:00:00Z",76,{"impact":122,"substance":123,"depth":124,"authority":17,"freshness":125,"relevant":21,"comment":126},16,21,18,9,"提出时序注意力结合人工蜂群优化的Bi-LSTM产量预测模型，基于30年多源数据取得较高精度，方法新颖且数据规模可观，对精准农业与农业保险决策有参考价值。",[128],{"name":118,"url":115},[26,27,130,28,29],"水稻",{"code":67,"slug":132,"name":133,"path":134,"parent_code":36},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[136,137],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":138,"slug":139,"name":140,"path":141,"parent_code":36},"I6","digital-village","数字乡村与数据要素","\u002Ftopic\u002Fdigital-agriculture\u002Fdigital-village",{"status":39,"locked":14,"version":40,"method":41,"evidence":143},{"candidates":144,"agricultural_evidence":47},[145,153,159,164,171,178,185,192],{"code":67,"score":124,"supported":47,"title":146,"abstract":148,"tags":152},[147],"deep learning",[149,150,151,147],"深度学习","机器学习","machine learning",[27],{"code":32,"score":154,"supported":47,"title":155,"abstract":156,"tags":158},11,[],[28,56,157],"multispectral",[29,28],{"code":138,"score":154,"supported":47,"title":160,"abstract":162,"tags":163},[161],"agricultural data",[161],[],{"code":165,"score":13,"supported":47,"title":166,"abstract":167,"tags":170},"A1",[],[130,168,169],"稻米","rice",[130],{"code":45,"score":172,"supported":47,"title":173,"abstract":174,"tags":177},7,[],[175,176],"精准农业","precision agriculture",[26],{"code":179,"score":60,"supported":47,"title":180,"abstract":181,"tags":184},"A8",[],[182,183],"粮食安全","food security",[],{"code":186,"score":60,"supported":47,"title":187,"abstract":188,"tags":191},"H2",[],[189,190],"土壤","soil",[],{"code":193,"score":75,"supported":47,"title":194,"abstract":195,"tags":197},"H8",[],[196],"可持续农业",[],[199,200],"作物产量预测 农业人工智能 智慧农业 水稻","作物产量预测 农业人工智能","作物产量预测农业人工智能智慧农业水稻-2160",2,"10.18805\u002Fag.d-6558",{"doi":203,"openalex_id":205,"authors":206,"venue":118,"cited_by_count":100,"oa_url":115,"card":217,"direction":105,"ingested_from":108},"W7212119230",[207,209,211,213,215],{"name":208,"orcid":9},"M. Lokeshwari",{"name":210,"orcid":9},"Nivethitha Manavalagan",{"name":212,"orcid":9},"P. Amrutha",{"name":214,"orcid":9},"S. Harinee",{"name":216,"orcid":9},"N.R. Divyasree",{"tldr":218,"method":219,"finding":220,"direction":221,"opportunity":222},"提出TA-ABC-Bi-LSTM模型，用多源农业数据精准预测水稻产量。","基于时间注意力与人工蜂群优化的Bi-LSTM，融合气象、土壤、Sentinel-","模型RMSE为298.01 kg\u002Fha，R²达81.76%，优于RF、SVR、DNN、CNN、LST","农业人工智能与决策模型","可探索轻量化注意力机制与迁移学习，将模型推广至多作物、小样本及实时预测场景。","2026-09-11T23:30:29.551995Z",{"id":225,"title":226,"url":227,"summary":228,"summary_zh":229,"content":9,"source_name":230,"source_url":227,"published_at":231,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":232,"score_detail":233,"sources":235,"tags":237,"primary_topic":240,"secondary_topics":241,"classification":243,"search_phrases":260,"slug":263,"view_count":100,"doi":264,"paper":265,"created_at":275},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)","2026-10-21T00:00:00Z",67,{"impact":53,"substance":18,"depth":19,"authority":17,"freshness":13,"relevant":21,"comment":234},"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。",[236],{"name":230,"url":227},[26,27,238,28,239],"产量预测","可解释性",{"code":67,"slug":132,"name":133,"path":134,"parent_code":36},[242],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":244},{"candidates":245,"agricultural_evidence":47},[246,252,256],{"code":67,"score":17,"supported":47,"title":247,"abstract":249,"tags":251},[248],"computer vision",[250],"计算机视觉",[27],{"code":32,"score":53,"supported":47,"title":253,"abstract":254,"tags":255},[],[28,56],[238,28],{"code":45,"score":21,"supported":14,"title":257,"abstract":258,"tags":259},[],[],[26],[261,262],"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":264,"openalex_id":266,"authors":267,"venue":230,"cited_by_count":100,"oa_url":227,"card":270,"direction":105,"ingested_from":108},"W7223114002",[268],{"name":269,"orcid":9},"Kadiatou Barry",{"tldr":271,"method":272,"finding":273,"direction":105,"opportunity":274},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":277,"title":278,"url":279,"summary":280,"summary_zh":281,"content":9,"source_name":282,"source_url":279,"published_at":283,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":284,"score_detail":285,"sources":288,"tags":290,"primary_topic":291,"secondary_topics":294,"classification":296,"search_phrases":325,"slug":328,"view_count":100,"doi":329,"paper":330,"created_at":343},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z",78,{"impact":124,"substance":286,"depth":124,"authority":17,"freshness":53,"relevant":21,"comment":287},22,"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[289],{"name":282,"url":279},[26,27,130,238,28],{"code":165,"slug":169,"name":130,"path":292,"parent_code":293},"\u002Ftopic\u002Ffield-crops\u002Frice","A",[295],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":297},{"candidates":298,"agricultural_evidence":47},[299,303,307,311,317,321],{"code":165,"score":46,"supported":47,"title":300,"abstract":301,"tags":302},[169],[130,169],[130],{"code":32,"score":53,"supported":47,"title":304,"abstract":305,"tags":306},[],[28,56],[238,28],{"code":179,"score":60,"supported":47,"title":308,"abstract":309,"tags":310},[],[182,183],[],{"code":312,"score":75,"supported":47,"title":313,"abstract":314,"tags":316},"J1",[],[315],"农业规划",[],{"code":45,"score":21,"supported":14,"title":318,"abstract":319,"tags":320},[],[],[26],{"code":67,"score":21,"supported":14,"title":322,"abstract":323,"tags":324},[],[],[27],[326,327],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":329,"openalex_id":331,"authors":332,"venue":282,"cited_by_count":100,"oa_url":279,"card":338,"direction":105,"ingested_from":108},"W7222942064",[333,335],{"name":334,"orcid":9},"Nayana Venkatesh",{"name":336,"orcid":337},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":339,"method":340,"finding":341,"direction":105,"opportunity":342},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","2026-10-20T23:30:19.292634Z",{"id":345,"title":346,"url":347,"summary":348,"summary_zh":349,"content":9,"source_name":350,"source_url":347,"published_at":351,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":352,"sources":354,"tags":356,"primary_topic":359,"secondary_topics":360,"classification":366,"search_phrases":392,"slug":395,"view_count":100,"doi":396,"paper":397,"created_at":417},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",{"impact":17,"substance":123,"depth":19,"authority":20,"freshness":125,"relevant":21,"comment":353},"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。",[355],{"name":350,"url":347},[26,27,28,357,358],"土壤盐渍化","新疆农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[361,365],{"code":186,"slug":190,"name":362,"path":363,"parent_code":364},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":67,"slug":132,"name":133,"path":134,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":367},{"candidates":368,"agricultural_evidence":47},[369,373,378,382,388],{"code":32,"score":46,"supported":47,"title":370,"abstract":371,"tags":372},[56],[28,56],[28],{"code":186,"score":374,"supported":47,"title":375,"abstract":376,"tags":377},14,[190],[189,190],[],{"code":67,"score":125,"supported":47,"title":379,"abstract":380,"tags":381},[147],[],[27],{"code":383,"score":75,"supported":47,"title":384,"abstract":385,"tags":387},"H7",[],[386],"干旱",[],{"code":45,"score":21,"supported":14,"title":389,"abstract":390,"tags":391},[],[],[26],[393,394],"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":396,"openalex_id":398,"authors":399,"venue":350,"cited_by_count":100,"oa_url":347,"card":412,"direction":105,"ingested_from":108},"W7221816183",[400,402,405,407,409],{"name":401,"orcid":9},"Mingjie Qian",{"name":403,"orcid":404},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":406,"orcid":9},"Peng Wang",{"name":408,"orcid":9},"Hangyuan Liu",{"name":410,"orcid":411},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":413,"method":414,"finding":415,"direction":105,"opportunity":416},"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":419,"title":420,"url":421,"summary":422,"summary_zh":423,"content":9,"source_name":424,"source_url":421,"published_at":351,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":425,"score_detail":426,"sources":428,"tags":430,"primary_topic":432,"secondary_topics":433,"classification":440,"search_phrases":486,"slug":489,"view_count":21,"doi":490,"paper":491,"created_at":512},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":124,"substance":286,"depth":124,"authority":374,"freshness":125,"relevant":21,"comment":427},"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。",[429],{"name":424,"url":421},[26,27,238,431,28],"多模态融合",{"code":67,"slug":132,"name":133,"path":134,"parent_code":36},[434,439],{"code":74,"slug":435,"name":436,"path":437,"parent_code":438},"fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":441},{"candidates":442,"agricultural_evidence":47},[443,447,455,460,464,468,475,481],{"code":67,"score":154,"supported":47,"title":444,"abstract":445,"tags":446},[],[149,150,151,147],[27,431],{"code":74,"score":125,"supported":47,"title":448,"abstract":449,"tags":454},[],[450,451,452,453],"苹果","芒果","orchard","apple",[],{"code":32,"score":53,"supported":47,"title":456,"abstract":457,"tags":459},[],[458,157],"无人机多光谱",[238,28],{"code":45,"score":172,"supported":47,"title":461,"abstract":462,"tags":463},[],[175,176],[26],{"code":186,"score":60,"supported":47,"title":465,"abstract":466,"tags":467},[],[189,190],[],{"code":469,"score":60,"supported":47,"title":470,"abstract":471,"tags":474},"I5",[],[472,473],"物联网","IoT",[],{"code":476,"score":75,"supported":47,"title":477,"abstract":478,"tags":480},"H6",[],[479],"农业生态",[],{"code":383,"score":75,"supported":47,"title":482,"abstract":483,"tags":485},[],[484],"气候适应",[],[487,488],"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":490,"openalex_id":492,"authors":493,"venue":424,"cited_by_count":100,"oa_url":421,"card":507,"direction":107,"ingested_from":108},"W7221795850",[494,497,499,501,503,505],{"name":495,"orcid":496},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":498,"orcid":9},"Umarfarooque Momin",{"name":500,"orcid":9},"Sudeep Kumar E",{"name":502,"orcid":9},"Itfaq Ahmad Mir",{"name":504,"orcid":9},"Ab Rouf Khan",{"name":506,"orcid":9},"Ghulam Mohammad Mir",{"tldr":508,"method":509,"finding":510,"direction":221,"opportunity":511},"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。","2026-10-15T23:30:08.750140Z",{"id":514,"title":515,"url":516,"summary":517,"summary_zh":518,"content":9,"source_name":230,"source_url":516,"published_at":519,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":520,"score_detail":521,"sources":523,"tags":525,"primary_topic":528,"secondary_topics":529,"classification":530,"search_phrases":558,"slug":561,"view_count":21,"doi":562,"paper":563,"created_at":575},4799,"Applications of Neutrosophic Topology in the Indian Context: A Review and Emerging Research Directions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23318355","AbstractNeutrosophic topology is an extension of classical topology designed to represent informationcharacterized by truth, indeterminacy, and falsity simultaneously. Unlike classical mathematicalmodels, which generally assume that an element either belongs or does not belong to a set,neutrosophic approaches permit the coexistence of partial truth, uncertainty, and contradiction. Thisfeature makes neutrosophic topology potentially useful for modelling complex systems in whichinformation is incomplete, inconsistent, imprecise, or dynamically changing. India, with its largeand heterogeneous population, geographically diverse environment, rapidly expanding digitalinfrastructure, and complex decision-making systems, provides several important contexts in whichsuch mathematical frameworks may be investigated. This article reviews the development ofneutrosophic topology and examines its potential and emerging applications in the Indian context.Particular attention is given to geographical information systems, medical diagnosis, data mining,decision-making, smart-city management, environmental monitoring, agricultural informationsystems, transportation networks, and information systems. Existing Indian contributionsdemonstrate that neutrosophic topological structures are increasingly being studied in connectionwith data analysis and decision problems. The article also identifies limitations in current research,particularly the gap between theoretical topological constructions and validated real-world datasets.Finally, several future research directions are proposed, including integration with geographicinformation systems, artificial intelligence, Internet-of-Things data, remote sensing, healthcareanalytics, and multi-criteria decision-making. The study concludes that neutrosophic topology offersa promising mathematical framework for representing uncertainty and inconsistency in Indian socio-technical and environmental systems, provided that future research emphasizes empirical validation and computational implementation. Keywords: Neutrosophic topology; neutrosophic sets; uncertainty; indeterminacy; fuzzy topology; GIS; decision making; data mining; India; mathematical modelling.","摘要：中智拓扑学（Neutrosophic topology）是经典拓扑学的扩展，旨在同时表示由真、不确定和假所刻画的信息。与通常假设元素要么属于某集合、要么不属于某集合的经典数学模型不同，中智方法允许部分真、不确定性和矛盾同时存在。这一特性使中智拓扑学在建模信息不完整、不一致、不精确或动态变化的复杂系统方面具有潜在价值。印度拥有庞大且异质的人口、地理多样的环境、快速扩展的数字基础设施以及复杂的决策系统，为研究此类数学框架提供了若干重要场景。本文综述了中智拓扑学的发展，并考察其在印度语境下的潜力和新兴应用。特别关注地理信息系统、医学诊断、数据挖掘、决策、智慧城市管理、环境监测、农业信息系统、交通网络和信息系统等领域。印度已有的研究成果表明，中智拓扑结构正日益被用于数据分析和决策问题的研究。本文还指出了当前研究的局限性，尤其是理论拓扑构造与经过验证的现实世界数据集之间的差距。最后，提出了若干未来研究方向，包括与地理信息系统、人工智能、物联网数据、遥感、医疗分析和多准则决策的整合。研究认为，中智拓扑学为表示印度社会技术系统和环境系统中的不确定性与不一致性提供了一个有前景的数学框架，前提是未来研究应重视实证验证和计算实现。关键词：中智拓扑学；中智集；不确定性；不确定；模糊拓扑学；地理信息系统；决策；数据挖掘；印度；数学建模。","2026-10-12T00:00:00Z",57,{"impact":53,"substance":374,"depth":46,"authority":17,"freshness":53,"relevant":21,"comment":522},"综述性论文，将中智拓扑引入印度农业信息系统、遥感与决策场景，理论价值明确但缺乏实证数据，属细分领域参考。",[524],{"name":230,"url":516},[26,27,526,28,527],"农业信息化","决策支持",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":531},{"candidates":532,"agricultural_evidence":47},[533,537,544,550,554],{"code":32,"score":172,"supported":47,"title":534,"abstract":535,"tags":536},[],[28,56],[28],{"code":538,"score":60,"supported":47,"title":539,"abstract":540,"tags":543},"I4",[],[541,542],"地理信息","GIS",[],{"code":67,"score":545,"supported":47,"title":546,"abstract":547,"tags":549},5,[],[548],"artificial intelligence",[27,527],{"code":469,"score":75,"supported":47,"title":551,"abstract":552,"tags":553},[],[472],[],{"code":45,"score":202,"supported":14,"title":555,"abstract":556,"tags":557},[],[],[526,26],[559,560],"中智拓扑 农业信息系统","农业人工智能 农业信息化 决策支持 智慧农业","中智拓扑农业信息系统-4799","10.5281\u002Fzenodo.23318355",{"doi":562,"openalex_id":564,"authors":565,"venue":230,"cited_by_count":100,"oa_url":516,"card":570,"direction":107,"ingested_from":108},"W7221514584",[566,568],{"name":567,"orcid":9},"N. Raksha Ben",{"name":569,"orcid":9},"G. Helen Rajapushpam",{"tldr":571,"method":572,"finding":573,"direction":221,"opportunity":574},"综述中智拓扑在印度多领域的应用潜力，并指出理论与实证数据脱节的局限。","文献综述，梳理中智拓扑在GIS、决策、农业信息系统等场景的应用。","中智拓扑能刻画不确定性，但缺乏真实数据验证与计算实现。","可将中智拓扑与农业物联网、遥感数据结合，构建可验证的不确定性决策模型。","2026-10-13T23:30:08.455353Z"]