[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1995":3,"related-1995":71},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":8,"secondary_topics":28,"classification":29,"search_phrases":56,"slug":59,"view_count":20,"doi":60,"paper":61,"created_at":70},1995,"Develop a methodology for mapping and characterization of salt-affected soils in coastal and inland plains of Gujarat state (India) using remote sensing, field, and laboratory soil studies","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10587263\u002Fv1","Develop a methodology for mapping and characterization of salt-affected soils in coastal and inland plains of Gujarat state (India) using remote sensing, field, and laboratory soil studies。Research Square",null,"Research Square","2026-09-08T00:00:00Z","论文",10,false,65,{"impact":16,"substance":17,"depth":18,"authority":12,"freshness":19,"relevant":20,"comment":21},15,20,18,2,1,"研究提出利用遥感与实地调查绘制古吉拉特邦盐渍土方法，对农业可持续有参考价值，但时效性较低。",[23],{"name":9,"url":6},[25,26,27],"农业遥感","印度农业","土壤盐渍化",[],{"status":30,"locked":13,"version":31,"method":32,"evidence":33},"needs_review","2026-10-22.2","rules",{"candidates":34,"agricultural_evidence":13,"reason":55},[35,43,50],{"code":36,"score":37,"supported":38,"title":39,"abstract":41,"tags":42},"I3",12,true,[40],"remote sensing",[40],[25],{"code":44,"score":45,"supported":38,"title":46,"abstract":48,"tags":49},"H2",11,[47],"soil",[47],[],{"code":51,"score":20,"supported":13,"title":52,"abstract":53,"tags":54},"J3",[],[],[26],"农业相关性需要复核",[57,58],"土壤盐渍化 农业遥感 印度农业","土壤盐渍化 农业遥感","土壤盐渍化农业遥感印度农业-1995","10.21203\u002Frs.3.rs-10587263\u002Fv1",{"doi":60,"openalex_id":62,"authors":63,"venue":9,"cited_by_count":67,"oa_url":6,"card":8,"direction":68,"ingested_from":69},"W7211936547",[64],{"name":65,"orcid":66},"A.K. Mandal","https:\u002F\u002Forcid.org\u002F0000-0002-0769-6886",0,"农业遥感与作物表型","openalex","2026-09-09T23:30:22.356239Z",{"total":72,"page":20,"page_size":72,"items":73},6,[74,172,246,325,419,527],{"id":75,"title":76,"url":77,"summary":78,"summary_zh":79,"content":8,"source_name":80,"source_url":77,"published_at":81,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":82,"score_detail":83,"sources":90,"tags":92,"primary_topic":96,"secondary_topics":102,"classification":111,"search_phrases":143,"slug":146,"view_count":67,"doi":147,"paper":148,"created_at":171},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":84,"substance":85,"depth":86,"authority":87,"freshness":88,"relevant":20,"comment":89},16,21,17,13,8,"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。",[91],{"name":80,"url":77},[93,25,94,95,27],"智慧农业","可解释AI","深度学习",{"code":97,"slug":98,"name":99,"path":100,"parent_code":101},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[103,107],{"code":36,"slug":104,"name":105,"path":106,"parent_code":101},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"code":44,"slug":47,"name":108,"path":109,"parent_code":110},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":112,"locked":13,"version":31,"method":32,"evidence":113},"classified",{"candidates":114,"agricultural_evidence":38},[115,120,125,131,138],{"code":97,"score":84,"supported":38,"title":116,"abstract":118,"tags":119},[117],"deep learning",[95,117],[94,95],{"code":36,"score":16,"supported":38,"title":121,"abstract":122,"tags":124},[40],[123,40],"遥感",[25],{"code":44,"score":126,"supported":38,"title":127,"abstract":128,"tags":130},14,[47],[129,47],"土壤",[],{"code":132,"score":133,"supported":38,"title":134,"abstract":135,"tags":137},"H7",3,[],[136],"干旱",[],{"code":139,"score":20,"supported":13,"title":140,"abstract":141,"tags":142},"I1",[],[],[93],[144,145],"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":147,"openalex_id":149,"authors":150,"venue":80,"cited_by_count":67,"oa_url":77,"card":166,"direction":68,"ingested_from":69},"W7221715654",[151,154,157,159,162,164],{"name":152,"orcid":153},"Mingyuan Ye","https:\u002F\u002Forcid.org\u002F0009-0001-6434-5505",{"name":155,"orcid":156},"Peng Chen","https:\u002F\u002Forcid.org\u002F0000-0002-2549-6765",{"name":158,"orcid":8},"Junchi Ma",{"name":160,"orcid":161},"Bingxia Liu","https:\u002F\u002Forcid.org\u002F0000-0001-7958-7112",{"name":163,"orcid":8},"Jiahao Qi",{"name":165,"orcid":8},"Yuan Jing",{"tldr":167,"method":168,"finding":169,"direction":68,"opportunity":170},"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",{"id":173,"title":174,"url":175,"summary":176,"summary_zh":177,"content":8,"source_name":178,"source_url":179,"published_at":180,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":181,"score_detail":182,"sources":184,"tags":186,"primary_topic":190,"secondary_topics":191,"classification":197,"search_phrases":226,"slug":229,"view_count":230,"doi":231,"paper":232,"created_at":245},3187,"Spatio-temporal analysis of Land Use and Land Cover (LULC) change using high resolution satellite data: A case study of Nagaon, Assam","https:\u002F\u002Fdoi.org\u002F10.31018\u002Fjans.v18i3.7774","Geographic information systems (GIS) coupled with satellite remote sensing (RS) have had a significant impact on the assessment and mapping of land surface dynamics, specifically the analysis of land-use land-cover (LULC) change. This study uses high-resolution multispectral LISS-IV (Linear Imaging Self-Scanning Sensor-IV) imagery with a 5.8-meter resolution to evaluate LULC trends in the Nagaon district of Assam between 2015 and 2024. Land use classes in a variety of categories, including vegetation, water bodies, agricultural land, built-up areas, scrubland, sandbars, tea plantations, and trees outside forests (TOF), were identified applying the maximum likelihood classification algorithm. Overall, The accuracy was 85.7% in 2015 and 90.3% in 2024, with respective Kappa Coefficients of 0.836 and 0.889, respectively. The results showed that between 2015 and 2024, the areas of tea plantations, natural vegetation, scrubland, and agricultural land fell by 0.26%, 6.14%, 0.26%, and 9.83%, respectively. Conversely, the waterbody, sandbar, built-up, and TOF have all increased by 0.29%, 0.91%, 0.82%, and 14.46%, respectively. This noticeable shift from conventional agricultural and natural vegetation landscapes toward tree-based systems and urban expansion on the study area, emphasize on matters concerning climate stress, declining soil fertility, economic benefits, policy support, and the need for resilient livelihoods.","地理信息系统（GIS）与卫星遥感（RS）相结合，对地表动态的评估与制图产生了显著影响，尤其是土地利用与土地覆盖（LULC）变化分析。本研究利用分辨率为5.8米的高分辨率多光谱LISS-IV（线性成像自扫描传感器-IV）影像，评估了阿萨姆邦纳冈县2015年至2024年间的LULC变化趋势。采用最大似然分类算法，识别了植被、水体、农地、建设用地、灌丛地、沙洲、茶园及林外树木（TOF）等多种土地利用类别。总体而言，2015年分类精度为85.7%，2024年为90.3%，Kappa系数分别为0.836和0.889。结果表明，2015年至2024年间，茶园、自然植被、灌丛地和农地面积分别减少了0.26%、6.14%、0.26%和9.83%。相反，水体、沙洲、建设用地和TOF分别增加了0.29%、0.91%、0.82%和14.46%。研究区从传统农业和自然植被景观向林基系统和城市扩张的显著转变，凸显了气候胁迫、土壤肥力下降、经济效益、政策支持以及韧性生计需求等相关问题。","Journal of Applied and Natural Science","https:\u002F\u002Fjournals.ansfoundation.org\u002Findex.php\u002Fjans\u002Farticle\u002Fview\u002F7774","2026-09-20T00:00:00Z",62,{"impact":88,"substance":18,"depth":16,"authority":87,"freshness":88,"relevant":20,"comment":183},"基于高分辨率遥感的区域土地利用变化实证研究，方法规范、数据翔实，对农业遥感监测有参考价值，但属地方性案例，公共影响有限。",[185],{"name":178,"url":179},[25,187,188,26,189],"遥感监测","土地利用","植被覆盖",{"code":36,"slug":104,"name":105,"path":106,"parent_code":101},[192],{"code":193,"slug":194,"name":195,"path":196,"parent_code":101},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"status":112,"locked":13,"version":31,"method":32,"evidence":198},{"candidates":199,"agricultural_evidence":38},[200,205,213,217,222],{"code":36,"score":37,"supported":38,"title":201,"abstract":202,"tags":204},[],[123,40,203],"multispectral",[25,189,187],{"code":193,"score":206,"supported":38,"title":207,"abstract":208,"tags":212},9,[],[209,210,211],"地理信息","GIS","geographic information",[],{"code":44,"score":72,"supported":38,"title":214,"abstract":215,"tags":216},[],[129,47],[],{"code":218,"score":20,"supported":13,"title":219,"abstract":220,"tags":221},"H6",[],[],[188],{"code":51,"score":20,"supported":13,"title":223,"abstract":224,"tags":225},[],[],[26],[227,228],"Nagaon Assam LULC 遥感","LISS-IV 土地利用变化","NagaonAssamLULC遥感-3187",5,"10.31018\u002Fjans.v18i3.7774",{"doi":231,"openalex_id":233,"authors":234,"venue":178,"cited_by_count":67,"oa_url":179,"card":240,"direction":68,"ingested_from":69},"W7213942371",[235,237],{"name":236,"orcid":8},"J. C. Das",{"name":238,"orcid":239},"Prodyut Bhattacharya","https:\u002F\u002Forcid.org\u002F0000-0002-4294-5585",{"tldr":241,"method":242,"finding":243,"direction":68,"opportunity":244},"利用高分辨率卫星影像分析印度阿萨姆邦纳冈地区2015-2024年土地利用\u002F覆盖变化。","LISS-IV 5.8米多光谱影像，最大似然分类，精度与Kappa系数评估。","农业用地和自然植被分别减少9.83%和6.14%，而林外树木和建设用地分别增加14.46%和0.82","可结合时序高分辨率影像与农户调查，探究林外树木扩张对农业韧性和碳汇的驱动机制。","2026-09-22T23:30:25.539323Z",{"id":247,"title":248,"url":249,"summary":250,"summary_zh":251,"content":8,"source_name":252,"source_url":249,"published_at":253,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":254,"score_detail":255,"sources":258,"tags":260,"primary_topic":264,"secondary_topics":265,"classification":266,"search_phrases":287,"slug":290,"view_count":67,"doi":291,"paper":292,"created_at":324},5576,"Land cover change and soil salinization in Mozambique: A counterfactual analysis over two decades (2001−2022)","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.catena.2026.110691","Soil salinization is a major issue that constrains the sustainable development of agriculture in arid, semi-arid, and coastal lowland areas. It is of great importance for regional land management and climate adaptation to clarify the influence of land cover change on soil salinization. This study aims to quantitatively assess the contribution of land cover change to soil salinization in Mozambique, where both rapid land cover transformation and salinization issues are evident. Firstly, we integrated soil profile electrical conductivity (EC) data, Landsat time-series remote sensing imagery, TerraClimate meteorological data, and the 30 m resolution land cover data, to construct a remote sensing-based EC inversion model for Mozambique. Secondly, we applied a spatially and environmentally constrained counterfactual matching method to quantitatively identify the contributions of different land cover changes on soil salinization trends. Our results reveal that: (1) the spatial distribution of soil salinization in Mozambique exhibits distinct a clear association with proximity to water bodies, with high EC areas primarily concentrated around Lake Malawi in the north and in the coastal regions of Greater Maputo in the south. (2) 26.98% of Mozambique's territory showed a trend of intensifying soil salinization, while 10.88% exhibited a decreasing trend. Areas with intensifying trends are primarily concentrated in the central alluvial plains, localized agricultural development zones, and coastal lowlands. (3) Urbanization was significantly associated with an increasing salinization trend after false discovery rate correction, suggesting that the expansion of impervious surfaces, changes in drainage patterns, and soil compaction may exacerbate localized salt accumulation. Agricultural expansion showed a negative trend difference, consistent with the potential influence of crop cover, tillage, and wet-season leaching, although this association was not significant after false discovery rate correction. The effects of ecological restoration and other factors were not statistically significant. In addition to elucidating the heterogeneous impacts of land cover changes in Mozambique on soil salinization trends, this study also provides methodological guidance and a scientific basis for monitoring\u002Fmanaging soil salinity risks in other coastal lowlands.","土壤盐渍化是制约干旱、半干旱及沿海低地地区农业可持续发展的主要问题。阐明土地覆盖变化对土壤盐渍化的影响，对区域土地管理和气候适应具有重要意义。本研究旨在定量评估土地覆盖变化对莫桑比克土壤盐渍化的贡献，该国土地覆盖转型迅速且盐渍化问题突出。首先，我们整合了土壤剖面电导率（EC）数据、Landsat时间序列遥感影像、TerraClimate气象数据以及30 m分辨率土地覆盖数据，构建了基于遥感的莫桑比克EC反演模型。其次，我们采用空间与环境约束的反事实匹配方法，定量识别不同土地覆盖变化对土壤盐渍化趋势的贡献。研究结果表明：（1）莫桑比克土壤盐渍化的空间分布与水体邻近性呈现明显的关联，高EC区域主要集中于北部的马拉维湖周边以及南部大马普托沿海地区。（2）莫桑比克26.98%的国土面积呈现土壤盐渍化加剧趋势，而10.88%呈现减轻趋势。加剧趋势区域主要集中于中部冲积平原、局部农业开发区及沿海低地。（3）经错误发现率校正后，城市化与盐渍化加剧趋势显著相关，表明不透水面扩张、排水格局改变及土壤压实可能加剧局部盐分累积。农业扩张呈现负向趋势差异，与作物覆盖、耕作及湿季淋洗的潜在影响一致，但该关联经错误发现率校正后不显著。生态恢复及其他因素的影响在统计上不显著。本研究不仅阐明了莫桑比克土地覆盖变化对土壤盐渍化趋势的异质性影响，还为其他沿海低地土壤盐渍化风险的监测与管理提供了方法学指导和科学依据。","CATENA","2026-10-20T00:00:00Z",79,{"impact":84,"substance":256,"depth":18,"authority":126,"freshness":206,"relevant":20,"comment":257},22,"该研究基于遥感与反事实匹配方法，定量评估土地覆盖变化对盐渍化的贡献，方法新颖、结论可靠，对沿海低地盐渍化监测具有参考价值，但属境外区域研究，国内政策与产业影响有限。",[259],{"name":252,"url":249},[187,261,27,262,263],"莫桑比克","土地覆盖变化","盐分反演",{"code":44,"slug":47,"name":108,"path":109,"parent_code":110},[],{"status":112,"locked":13,"version":31,"method":32,"evidence":267},{"candidates":268,"agricultural_evidence":38},[269,273,278,283],{"code":44,"score":126,"supported":38,"title":270,"abstract":271,"tags":272},[47],[129,47],[],{"code":36,"score":274,"supported":38,"title":275,"abstract":276,"tags":277},7,[],[123,40],[187],{"code":132,"score":72,"supported":38,"title":279,"abstract":280,"tags":282},[],[281,136],"气候适应",[],{"code":218,"score":20,"supported":13,"title":284,"abstract":285,"tags":286},[],[],[262],[288,289],"莫桑比克 土壤盐渍化 遥感","土地覆盖变化 盐渍化 反事实分析","莫桑比克土壤盐渍化遥感-5576","10.1016\u002Fj.catena.2026.110691",{"doi":291,"openalex_id":293,"authors":294,"venue":252,"cited_by_count":67,"oa_url":249,"card":319,"direction":68,"ingested_from":69},"W7223069171",[295,297,299,301,304,306,309,312,314,316],{"name":296,"orcid":8},"Yue Li",{"name":298,"orcid":8},"Mengfei Shi",{"name":300,"orcid":8},"Fei Zhang",{"name":302,"orcid":303},"Brian Alan Johnson","https:\u002F\u002Forcid.org\u002F0000-0003-1911-3585",{"name":305,"orcid":8},"Gowhar Meraj",{"name":307,"orcid":308},"Jaime Carlos Macuácua","https:\u002F\u002Forcid.org\u002F0000-0002-4822-6098",{"name":310,"orcid":311},"Pankaj Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-5264-3951",{"name":313,"orcid":8},"Yuanfang Chai",{"name":315,"orcid":8},"Hongtao Xu",{"name":317,"orcid":318},"Xu Ma","https:\u002F\u002Forcid.org\u002F0000-0003-0644-7498",{"tldr":320,"method":321,"finding":322,"direction":68,"opportunity":323},"量化莫桑比克2001-2022年土地覆盖变化对土壤盐渍化的贡献。","融合EC剖面、Landsat时序与气候数据反演EC，并用空间环境约束的反事实匹配","26.98%区域盐渍化加剧；城市化显著关联盐渍化上升，农业扩张关联不显著。","可将反事实匹配框架迁移至其他滨海低地，并引入作物类型与灌溉制度细化农业扩张的盐渍化效应。","2026-10-22T11:20:42.713789Z",{"id":326,"title":327,"url":328,"summary":329,"summary_zh":330,"content":8,"source_name":331,"source_url":328,"published_at":332,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":333,"score_detail":334,"sources":336,"tags":338,"primary_topic":342,"secondary_topics":348,"classification":356,"search_phrases":387,"slug":390,"view_count":67,"doi":391,"paper":392,"created_at":418},5573,"Improving alfalfa nitrogen estimation with canopy structural priors from DSSAT–PROSAIL and UAV hyperspectral data","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eja.2026.128375","Accurate estimation of nitrogen (N) concentration in alfalfa ( Medicago sativa L .) supports forage quality assessment and harvest scheduling. Empirical remote sensing models often overfit because of confounding effects of three-dimensional canopy structure. Incorporating structural parameters can stabilize biochemical inversions, but concurrent in situ morphological measurements are difficult to acquire at scale. We developed the Morphology-Aware Latent Embedding Network (MALENet), a hybrid framework integrating physiological and morphological mechanisms with hyperspectral data. The Decision Support System for Agrotechnology Transfer (DSSAT), coupled with the PROSAIL radiative transfer model, generated a structurally rich synthetic hyperspectral prior. A convolutional neural network (CNN) with a Squeeze-and-Excitation (SE) attention mechanism, was pre-trained on these data to distill ecophysiological knowledge into a dense latent representation. This mechanistically derived embedding was then fused with empirical hyperspectral measurements collected under diverse field conditions. Evaluation using multi-year field quadrats in the Hexi Corridor showed improved predictive performance ( R² = 0.71, RMSE = 0.30%) relative to conventional machine learning and deep learning models (LASSO-ANN: R² = 0.61; CNN: R² = 0.66). Feature attribution indicated that MALENet used near-infrared multiple scattering (58.3% attribution) as a structural proxy to calibrate nitrogen concentration retrieval against the confounding effects of canopy architecture. Despite constraints imposed by sample size and PROSAIL's 1D canopy assumption, these findings demonstrate the potential of physically guided deep learning to use structural information for agricultural trait retrieval in precision forage management.","准确估算紫花苜蓿（Medicago sativa L.）的氮浓度有助于饲草品质评估和收获期安排。经验性遥感模型常因三维冠层结构的混杂效应而出现过拟合。引入结构参数可以稳定生化反演，但同步开展原位形态学测量难以大规模获取。我们开发了形态感知潜在嵌入网络（Morphology-Aware Latent Embedding Network，MALENet），这是一个将生理与形态机制同高光谱数据相结合的混合框架。农业技术转移决策支持系统（Decision Support System for Agrotechnology Transfer，DSSAT）与PROSAIL辐射传输模型耦合，生成了结构信息丰富的合成高光谱先验数据。在此基础上，预训练了一个带有挤压—激励（Squeeze-and-Excitation，SE）注意力机制的卷积神经网络（convolutional neural network，CNN），将生态生理学知识提炼为稠密潜在表征。随后，将这一机制性导出的嵌入与在不同田间条件下采集的经验性高光谱测量数据相融合。利用河西走廊多年田间样方进行的评估显示，相较于传统机器学习和深度学习模型（LASSO-ANN：R² = 0.61；CNN：R² = 0.66），预测性能有所提升（R² = 0.71，RMSE = 0.30%）。特征归因表明，MALENet利用近红外多次散射（归因占比58.3%）作为结构代理，以校准氮浓度反演，抵御冠层结构的混杂效应。尽管受样本量和PROSAIL一维冠层假设的限制，这些发现表明，物理引导的深度学习有潜力利用结构信息，在精准饲草管理中进行农业性状反演。","European Journal of Agronomy","2026-10-21T00:00:00Z",80,{"impact":84,"substance":256,"depth":18,"authority":126,"freshness":12,"relevant":20,"comment":335},"该研究将作物模型与辐射传输模型耦合生成结构先验，并结合无人机高光谱数据反演苜蓿氮素，方法新颖、田间验证扎实，对精准饲草管理有参考价值，值得进入每日精选。",[337],{"name":331,"url":328},[93,339,25,340,341],"农业人工智能","氮素监测","紫花苜蓿",{"code":343,"slug":344,"name":345,"path":346,"parent_code":347},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[349,350],{"code":36,"slug":104,"name":105,"path":106,"parent_code":101},{"code":351,"slug":352,"name":353,"path":354,"parent_code":355},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":112,"locked":13,"version":31,"method":32,"evidence":357},{"candidates":358,"agricultural_evidence":38},[359,364,370,376,383],{"code":36,"score":18,"supported":38,"title":360,"abstract":362,"tags":363},[361],"hyperspectral",[123,40,361],[25],{"code":343,"score":16,"supported":38,"title":365,"abstract":367,"tags":369},[366],"alfalfa",[368,366],"苜蓿",[341],{"code":351,"score":12,"supported":38,"title":371,"abstract":372,"tags":375},[],[373,368,374],"饲草","forage",[341],{"code":97,"score":12,"supported":38,"title":377,"abstract":378,"tags":382},[],[95,379,380,117,381],"机器学习","machine learning","decision support",[339],{"code":139,"score":20,"supported":13,"title":384,"abstract":385,"tags":386},[],[],[93],[388,389],"DSSAT PROSAIL 苜蓿 氮素","无人机 高光谱 苜蓿","DSSATPROSAIL苜蓿氮素-5573","10.1016\u002Fj.eja.2026.128375",{"doi":391,"openalex_id":393,"authors":394,"venue":331,"cited_by_count":67,"oa_url":328,"card":413,"direction":68,"ingested_from":69},"W7223154576",[395,397,399,401,403,406,408,411],{"name":396,"orcid":8},"Shuai Fu",{"name":398,"orcid":8},"Yunhao Li",{"name":400,"orcid":8},"Chunli Miao",{"name":402,"orcid":8},"Jie Liu",{"name":404,"orcid":405},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":407,"orcid":8},"Yongjia Hu",{"name":409,"orcid":410},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":412,"orcid":8},"吴彩霞",{"tldr":414,"method":415,"finding":416,"direction":68,"opportunity":417},"构建MALENet融合DSSAT-PROSAIL结构先验与无人机高光谱，提升苜蓿氮浓度估算精度。","DSSAT耦合PROSAIL生成合成高光谱先验，预训练CNN-SE网络，再融合田","MALENet精度优于传统机器学习和深度学习模型，R²达0.71，近红外多次散射作为结构代理贡献58","可探索将作物模型结构先验迁移至其他牧草或作物生化参数反演，并缓解PROSAIL一维冠层假设局限。","2026-10-22T11:20:39.622844Z",{"id":420,"title":421,"url":422,"summary":423,"summary_zh":424,"content":8,"source_name":425,"source_url":422,"published_at":332,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":426,"score_detail":427,"sources":429,"tags":431,"primary_topic":436,"secondary_topics":440,"classification":441,"search_phrases":479,"slug":482,"view_count":67,"doi":483,"paper":484,"created_at":526},5550,"Integrated effects of fermented organic manure on soil fertility, productivity, and economic performance of the rice–wheat cropping system in Uttar Pradesh","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1968370","The rice–wheat cropping system (RWCS) is a major cereal-based production system in Uttar Pradesh, India, where sustaining crop productivity and soil fertility under intensive cultivation is a major challenge. This study evaluated the field-level performance of fermented organic manure (FOM) integrated with inorganic fertilizers in terms of crop productivity, selected soil fertility indicators, and economic returns during 2025–2026. A total of 224 frontline demonstrations (FLDs) were conducted through 25 Krishi Vigyan Kendras (KVKs) across Uttar Pradesh. The analysis included demonstrations with sufficiently complete and consistent field-level records, comprising 40 rice and 110 wheat demonstrations under farmers’ field conditions and 6 rice and 11 wheat demonstrations at KVK instructional farms. Seven nutrient management treatments were evaluated at KVK farms, compared with three treatments under farmers’ field conditions. Crop performance, post-harvest soil fertility indicators, and economic returns were assessed. The treatment combining 100% recommended inorganic fertilizers with 125% FOM (T₃) recorded the highest numerical means for most growth and yield attributes and grain yield in both crops. Compared with 100% recommended inorganic fertilizers alone, T₃ increased grain yield by 6.4–7.3% in rice and 10.8–12.7% in wheat. FOM-integrated treatments also showed higher numerical values of soil organic carbon (SOC) and available nitrogen, phosphorus, and potassium after the rice–wheat cropping cycle. Under T₃, SOC increased from 0.271% to 0.304% at KVK instructional farms and from 0.447% to 0.515% under farmers’ field conditions. Although T₃ generally recorded the highest numerical gross returns, the additional costs of FOM reduced net returns and benefit–cost (B) ratios in several cases. Under farmers’ field conditions, inorganic fertilizers alone recorded higher numerical net returns and B ratios for both crops. The findings indicate that integrating FOM with recommended inorganic fertilizers was associated with improved crop productivity and selected soil fertility indicators under the demonstrated rice–wheat systems. However, the economic advantage depended on the costs of FOM production, transportation, and application. As the demonstrations were participatory and lacked formal plot-level randomization and inferential statistical testing, the observed differences represent descriptive numerical responses rather than statistically established treatment effects. Further controlled trials and cost optimization are needed to establish the agronomic and economic viability of FOM-integrated nutrient management.","稻麦种植制度（RWCS）是印度北方邦以谷类作物为主的重要生产体系，在集约化种植下维持作物生产力与土壤肥力是该体系面临的主要挑战。本研究评估了发酵有机肥（FOM）与无机肥料配合施用在2025—2026年度对作物生产力、选定土壤肥力指标及经济效益的田间表现。研究通过北方邦25个农业科技推广中心（KVKs）开展了224项前线示范（FLDs）。分析纳入了田间记录足够完整且一致的示范，包括农民田块条件下的40项水稻和110项小麦示范，以及KVK教学农场的6项水稻和11项小麦示范。在KVK农场评估了7个养分管理处理，并与农民田块条件下的3个处理进行比较。评估了作物表现、收获后土壤肥力指标及经济效益。100%推荐无机肥料配合125% FOM的处理（T₃）在两种作物的多数生长和产量性状及籽粒产量上记录了最高的数值均值。与单施100%推荐无机肥料相比，T₃使水稻籽粒产量提高6.4%—7.3%，小麦提高10.8%—12.7%。整合FOM的处理在稻麦轮作周期后也表现出较高的土壤有机碳（SOC）及有效氮、磷、钾数值。在T₃处理下，KVK教学农场的SOC从0.271%提高到0.304%，农民田块条件下从0.447%提高到0.515%。尽管T₃总体上记录了最高的数值总收益，但FOM的额外成本在多种情况下降低了净收益和效益成本比（B）。在农民田块条件下，单施无机肥料在两种作物上均记录了较高的数值净收益和B比。研究结果表明，在示范的稻麦系统中，FOM与推荐无机肥料配合施用与作物生产力及选定土壤肥力指标的改善相关。然而，经济优势取决于FOM的生产、运输和施用成本。由于示范为参与式，缺乏正式的田块水平随机化和推断性统计检验，观察到的差异代表描述性数值响应，而非统计学上确立的处理","Frontiers in Sustainable Food Systems",71,{"impact":84,"substance":18,"depth":16,"authority":87,"freshness":206,"relevant":20,"comment":428},"基于224个前线示范的实地数据，结论有参考价值，但缺乏随机化与统计检验，且为印度区域研究，属细分领域进展。",[430],{"name":425,"url":422},[432,433,434,26,435],"有机肥","土壤肥力","养分管理","水稻小麦轮作",{"code":347,"slug":437,"name":438,"path":439,"parent_code":8},"field-crops","大田作物","\u002Ftopic\u002Ffield-crops",[],{"status":442,"locked":13,"version":31,"method":32,"evidence":443},"partial",{"candidates":444,"agricultural_evidence":38,"reason":478},[445,449,456,463,469,474],{"code":44,"score":16,"supported":38,"title":446,"abstract":447,"tags":448},[47],[129,47],[433],{"code":450,"score":126,"supported":38,"title":451,"abstract":453,"tags":455},"A1",[452],"rice",[454,452],"水稻",[],{"code":457,"score":126,"supported":38,"title":458,"abstract":460,"tags":462},"A2",[459],"wheat",[461,459],"小麦",[],{"code":464,"score":88,"supported":38,"title":465,"abstract":466,"tags":468},"F3",[],[467,434],"肥料",[434,432],{"code":343,"score":133,"supported":38,"title":470,"abstract":471,"tags":473},[],[472],"轮作",[],{"code":51,"score":20,"supported":13,"title":475,"abstract":476,"tags":477},[],[],[26],"一级领域明确，二级方向需要细分",[480,481],"发酵有机肥 稻麦轮作","Uttar Pradesh 稻麦系统","发酵有机肥稻麦轮作-5550","10.3389\u002Ffsufs.2026.1968370",{"doi":483,"openalex_id":485,"authors":486,"venue":425,"cited_by_count":67,"oa_url":519,"card":520,"direction":524,"ingested_from":69},"W7223144837",[487,489,492,493,496,499,501,502,504,507,509,512,514,516],{"name":488,"orcid":8},"Raghwendra Singh",{"name":490,"orcid":491},"Ajay Kumar Singh","https:\u002F\u002Forcid.org\u002F0000-0002-8743-6477",{"name":490,"orcid":491},{"name":494,"orcid":495},"Preeti P. Yadav","https:\u002F\u002Forcid.org\u002F0000-0001-7843-9783",{"name":497,"orcid":498},"Seema Yadav","https:\u002F\u002Forcid.org\u002F0000-0002-9773-6641",{"name":500,"orcid":8},"Abhishek Singh",{"name":500,"orcid":8},{"name":503,"orcid":8},"Saurabh Raj Pandey",{"name":505,"orcid":506},"Vinod Kumar Singh","https:\u002F\u002Forcid.org\u002F0009-0004-2583-6565",{"name":508,"orcid":8},"Narendra Raghubanshi",{"name":510,"orcid":511},"Yash Pal Singh","https:\u002F\u002Forcid.org\u002F0000-0001-8345-9084",{"name":513,"orcid":8},"Mahesh Kumar",{"name":515,"orcid":8},"Shivangi Singh",{"name":517,"orcid":518},"Reena Kumari","https:\u002F\u002Forcid.org\u002F0000-0002-1101-5473","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1968370\u002Fpdf",{"tldr":521,"method":522,"finding":523,"direction":524,"opportunity":525},"评估发酵有机肥配施化肥对稻麦轮作产量、土壤肥力与经济收益的综合影响。","印度北方邦224个农户与KVK示范基地田间示范，比较7种养分管理处理。","全量化肥配125%发酵有机肥增产稻6.4-7.3%、麦10.8-12.7%并提升有机碳，但净收益常因","农业绿色发展与碳","可研究有机肥成本分摊与碳交易补偿机制，量化其经济可行性与土壤固碳协同效益。","2026-10-22T11:20:16.098808Z",{"id":528,"title":529,"url":530,"summary":531,"summary_zh":8,"content":8,"source_name":532,"source_url":8,"published_at":332,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":533,"score_detail":534,"sources":536,"tags":538,"primary_topic":542,"secondary_topics":544,"classification":550,"search_phrases":570,"slug":573,"view_count":20,"doi":8,"paper":574,"created_at":582},5535,"基于无人机多光谱图像与VGG21模型的小麦渍害调控效果识别","https:\u002F\u002Ffinance.sina.cn\u002F2026-10-16\u002Fdetail-inivmprm8363597.d.html","江苏省农科院农业信息研究所联合中国农科院环发所与湖北省农科院粮作所，在小麦拔节至抽穗、抽穗至灌浆两个阶段设置对照、渍水胁迫、硅肥与氨基酸调控试验，用大疆精灵4采集冠层多光谱影像。VGG21模型对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","智慧农业（中英文）2026-10-21",82,{"impact":18,"substance":256,"depth":18,"authority":126,"freshness":12,"relevant":20,"comment":535},"省级科研机构联合攻关，方法新颖、数据扎实，对渍害遥感识别与调控评估有实质参考价值，值得入选。",[537],{"name":532,"url":530},[93,25,539,540,541],"作物表型","无人机多光谱","小麦渍害",{"code":457,"slug":459,"name":461,"path":543,"parent_code":347},"\u002Ftopic\u002Ffield-crops\u002Fwheat",[545,546],{"code":36,"slug":104,"name":105,"path":106,"parent_code":101},{"code":132,"slug":547,"name":548,"path":549,"parent_code":110},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate",{"status":112,"locked":13,"version":31,"method":32,"evidence":551},{"candidates":552,"agricultural_evidence":38},[553,557,561,566],{"code":457,"score":45,"supported":38,"title":554,"abstract":555,"tags":556},[461],[461],[],{"code":36,"score":45,"supported":38,"title":558,"abstract":559,"tags":560},[540],[],[539,25,540],{"code":132,"score":88,"supported":38,"title":562,"abstract":564,"tags":565},[563],"渍害",[],[],{"code":139,"score":20,"supported":13,"title":567,"abstract":568,"tags":569},[],[],[93],[571,572],"江苏省农科院 小麦渍害 多光谱","VGG21 小麦 硅肥调控","江苏省农科院小麦渍害多光谱-5535",{"doi":8,"openalex_id":8,"authors":575,"venue":8,"cited_by_count":67,"oa_url":8,"card":576,"direction":68,"ingested_from":581},[],{"tldr":577,"method":578,"finding":579,"direction":68,"opportunity":580},"用无人机多光谱图像和VGG21模型识别小麦渍害后硅肥与氨基酸调控效果。","大疆精灵4采集冠层多光谱影像，构建VGG21深度学习分类模型。","VGG21对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","可扩展多生育期、多调控组合与轻量化模型，探索渍害胁迫等级与调控效果的同步识别。","agent","2026-10-22T00:07:10.070916Z"]