[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1530":3,"related-1530":85},{"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":29,"classification":30,"search_phrases":52,"slug":55,"view_count":56,"doi":57,"paper":58,"created_at":84},1530,"Using a planted tree biodiversity experiment to evaluate imaging spectroscopy for species classification","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rse.2026.115644","Using a planted tree biodiversity experiment to evaluate imaging spectroscopy for species classification。Remote Sensing of Environment",null,"Remote Sensing of Environment","2026-09-02T00:00:00Z","论文",10,false,79,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,14,7,1,"利用种植实验评估成像光谱在树种分类中的潜力，方法新颖，数据详实，对精准林业和生物多样性监测有参考价值。",[23],{"name":9,"url":6},[25,26,27,28],"农业遥感","生物多样性","树种分类","成像光谱",[],{"status":31,"locked":13,"version":32,"method":33,"evidence":34},"needs_review","2026-10-22.2","rules",{"candidates":35,"agricultural_evidence":13,"reason":51},[36,44],{"code":37,"score":38,"supported":39,"title":40,"abstract":42,"tags":43},"H6",12,true,[41],"biodiversity",[41],[26],{"code":45,"score":46,"supported":39,"title":47,"abstract":48,"tags":50},"I3",4,[],[49],"remote sensing",[25],"农业相关性需要复核",[53,54],"生物多样性 农业遥感 成像光谱 树种分类","生物多样性 农业遥感","生物多样性农业遥感成像光谱树种分类-1530",2,"10.1016\u002Fj.rse.2026.115644",{"doi":57,"openalex_id":59,"authors":60,"venue":9,"cited_by_count":80,"oa_url":81,"card":8,"direction":82,"ingested_from":83},"W7139975496",[61,64,67,69,71,73,75,77],{"name":62,"orcid":63},"Sofia J. van Moorsel","https:\u002F\u002Forcid.org\u002F0000-0003-1947-8971",{"name":65,"orcid":66},"Bernhard Schmid","https:\u002F\u002Forcid.org\u002F0000-0002-8430-3214",{"name":68,"orcid":8},"Michael Niederberger",{"name":70,"orcid":8},"Jeremiah Huggel",{"name":72,"orcid":8},"Michael Scherer-Lorenzen",{"name":74,"orcid":8},"U. Rascher",{"name":76,"orcid":8},"Alexander Damm",{"name":78,"orcid":79},"Meredith C. Schuman","https:\u002F\u002Forcid.org\u002F0000-0003-3159-3534",0,"https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F20\u002F2026.03.20.713086.full.pdf","农业遥感与作物表型","openalex","2026-09-03T23:30:29.967794Z",{"total":86,"page":20,"page_size":86,"items":87},6,[88,195,258,338,388,455],{"id":89,"title":90,"url":91,"summary":92,"summary_zh":93,"content":8,"source_name":94,"source_url":91,"published_at":95,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":96,"score_detail":97,"sources":100,"tags":102,"primary_topic":107,"secondary_topics":113,"classification":125,"search_phrases":163,"slug":166,"view_count":80,"doi":167,"paper":168,"created_at":194},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":98,"substance":17,"depth":16,"authority":18,"freshness":12,"relevant":20,"comment":99},16,"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。",[101],{"name":94,"url":91},[103,104,25,105,106],"智慧农业","农业人工智能","氮素监测","紫花苜蓿",{"code":108,"slug":109,"name":110,"path":111,"parent_code":112},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[114,119],{"code":45,"slug":115,"name":116,"path":117,"parent_code":118},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"code":120,"slug":121,"name":122,"path":123,"parent_code":124},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":126,"locked":13,"version":32,"method":33,"evidence":127},"classified",{"candidates":128,"agricultural_evidence":39},[129,135,142,148,158],{"code":45,"score":16,"supported":39,"title":130,"abstract":132,"tags":134},[131],"hyperspectral",[133,49,131],"遥感",[25],{"code":108,"score":136,"supported":39,"title":137,"abstract":139,"tags":141},15,[138],"alfalfa",[140,138],"苜蓿",[106],{"code":120,"score":12,"supported":39,"title":143,"abstract":144,"tags":147},[],[145,140,146],"饲草","forage",[106],{"code":149,"score":12,"supported":39,"title":150,"abstract":151,"tags":157},"I2",[],[152,153,154,155,156],"深度学习","机器学习","machine learning","deep learning","decision support",[104],{"code":159,"score":20,"supported":13,"title":160,"abstract":161,"tags":162},"I1",[],[],[103],[164,165],"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":167,"openalex_id":169,"authors":170,"venue":94,"cited_by_count":80,"oa_url":91,"card":189,"direction":82,"ingested_from":83},"W7223154576",[171,173,175,177,179,182,184,187],{"name":172,"orcid":8},"Shuai Fu",{"name":174,"orcid":8},"Yunhao Li",{"name":176,"orcid":8},"Chunli Miao",{"name":178,"orcid":8},"Jie Liu",{"name":180,"orcid":181},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":183,"orcid":8},"Yongjia Hu",{"name":185,"orcid":186},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":188,"orcid":8},"吴彩霞",{"tldr":190,"method":191,"finding":192,"direction":82,"opportunity":193},"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":196,"title":197,"url":198,"summary":199,"summary_zh":8,"content":8,"source_name":200,"source_url":8,"published_at":95,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":201,"score_detail":202,"sources":204,"tags":206,"primary_topic":210,"secondary_topics":215,"classification":223,"search_phrases":245,"slug":248,"view_count":20,"doi":8,"paper":249,"created_at":257},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":16,"substance":17,"depth":16,"authority":18,"freshness":12,"relevant":20,"comment":203},"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。",[205],{"name":200,"url":198},[103,25,207,208,209],"作物表型","无人机多光谱","小麦渍害",{"code":211,"slug":212,"name":213,"path":214,"parent_code":112},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat",[216,217],{"code":45,"slug":115,"name":116,"path":117,"parent_code":118},{"code":218,"slug":219,"name":220,"path":221,"parent_code":222},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":126,"locked":13,"version":32,"method":33,"evidence":224},{"candidates":225,"agricultural_evidence":39},[226,231,235,241],{"code":211,"score":227,"supported":39,"title":228,"abstract":229,"tags":230},11,[213],[213],[],{"code":45,"score":227,"supported":39,"title":232,"abstract":233,"tags":234},[208],[],[207,25,208],{"code":218,"score":236,"supported":39,"title":237,"abstract":239,"tags":240},8,[238],"渍害",[],[],{"code":159,"score":20,"supported":13,"title":242,"abstract":243,"tags":244},[],[],[103],[246,247],"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":250,"venue":8,"cited_by_count":80,"oa_url":8,"card":251,"direction":82,"ingested_from":256},[],{"tldr":252,"method":253,"finding":254,"direction":82,"opportunity":255},"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",{"id":259,"title":260,"url":261,"summary":262,"summary_zh":263,"content":8,"source_name":264,"source_url":261,"published_at":265,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":266,"score_detail":267,"sources":271,"tags":273,"primary_topic":277,"secondary_topics":282,"classification":283,"search_phrases":302,"slug":305,"view_count":80,"doi":306,"paper":307,"created_at":337},5399,"Spatial Heterogeneity and Nonlinear Environmental Associations of Positive Climatic Moisture Deficit with Implications for Sustainable Water Resource Assessment: A Case Study of Anyang","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu182010595","Positive climatic moisture deficit (CMD+) characterizes the seasonal imbalance between precipitation supply and atmospheric water demand, yet its spatial heterogeneity and associations with environmental and human-related factors remain insufficiently understood. Taking Anyang, China, as a case study, we calculated annual CMD+ for 2000–2020 using 1 km monthly precipitation and potential evapotranspiration data and applied an extreme gradient boosting (XGBoost)–SHapley Additive exPlanations (SHAP) framework to the corresponding long-term mean fields to examine climatological spatial heterogeneity. Five predictors were considered, including elevation, normalized difference vegetation index (NDVI), irrigation fraction, built-up fraction, and population density. Nested spatial-block cross-validation showed good model generalization. Long-term mean CMD+ was generally lower in the western mountainous area and higher across the central and eastern plains. The digital elevation model (DEM) accounted for 66.10% of the normalized mean absolute SHAP importance, followed by NDVI (13.47%) and irrigation fraction (9.72%). A DEM-excluded sensitivity model retained a spatial cross-validated R2 of 0.781, compared with 0.898 for the full model. SHAP dependence analysis revealed pronounced nonlinear responses, with primary local model response transition points at approximately 297.1 m for DEM, 0.812 for NDVI, and 23.1% for irrigation fraction. The strongest pairwise SHAP interaction occurred between NDVI and irrigation fraction, accounting for 21.87% of total pairwise interaction strength. These results show that the spatial heterogeneity of CMD+ in Anyang is closely associated with topographic background, while vegetation status and irrigated agriculture provide additional nonlinear and interactive explanatory information. The identified spatial patterns and model-response transitions provide spatial information for understanding regional climatic moisture deficits and for subsequent sustainable water resource assessment.","正向气候水分亏缺（CMD+）刻画了降水供给与大气水分需求之间的季节性失衡，但其空间异质性及其与环境因素和人为因素的关联仍缺乏充分认识。以中国安阳为案例区，本研究利用1 km月降水量与潜在蒸散量数据计算了2000—2020年的年CMD+，并将极端梯度提升（XGBoost）—SHapley加性解释（SHAP）框架应用于相应的长期均值场，以考察气候态空间异质性。研究考虑了5个预测因子，包括高程、归一化植被指数（NDVI）、灌溉面积比例、建成区比例和人口密度。嵌套空间分块交叉验证表明模型具有良好的泛化能力。长期平均CMD+总体表现为西部山区较低、中部和东部平原较高。数字高程模型（DEM）占归一化平均绝对SHAP重要性的66.10%，其次为NDVI（13.47%）和灌溉面积比例（9.72%）。剔除DEM的敏感性模型保持了0.781的空间交叉验证R²，而完整模型为0.898。SHAP依赖分析揭示了显著的非线性响应，主要局部模型响应转变点分别约为DEM 297.1 m、NDVI 0.812和灌溉面积比例23.1%。最强的成对SHAP交互作用出现在NDVI与灌溉面积比例之间，占总成对交互强度的21.87%。结果表明，安阳CMD+的空间异质性与地形背景密切相关，而植被状况和灌溉农业提供了额外的非线性和交互解释信息。所识别的空间格局和模型响应转变点为理解区域气候水分亏缺及后续可持续水资源评估提供了空间信息。","Sustainability","2026-10-19T00:00:00Z",64,{"impact":236,"substance":16,"depth":98,"authority":268,"freshness":269,"relevant":20,"comment":270},13,9,"以安阳为案例，用遥感与XGBoost-SHAP揭示气候水分亏缺的空间异质性，方法有新意、结论可靠，但属区域案例研究，公共影响有限。",[272],{"name":264,"url":261},[25,153,274,275,276],"灌溉管理","水资源评估","气候干旱",{"code":278,"slug":279,"name":280,"path":281,"parent_code":222},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",[],{"status":126,"locked":13,"version":32,"method":33,"evidence":284},{"candidates":285,"agricultural_evidence":39},[286,294,298],{"code":278,"score":16,"supported":39,"title":287,"abstract":289,"tags":293},[288],"water resource",[290,291,279,288,292],"灌溉","水资源","evapotranspiration",[274],{"code":149,"score":20,"supported":13,"title":295,"abstract":296,"tags":297},[],[],[153],{"code":45,"score":20,"supported":13,"title":299,"abstract":300,"tags":301},[],[],[25],[303,304],"安阳 气候水分亏缺 遥感","XGBoost SHAP 水资源评估","安阳气候水分亏缺遥感-5399","10.3390\u002Fsu182010595",{"doi":306,"openalex_id":308,"authors":309,"venue":264,"cited_by_count":80,"oa_url":261,"card":331,"direction":336,"ingested_from":83},"W7222973420",[310,312,315,318,321,323,325,327,329],{"name":311,"orcid":8},"Yan Li",{"name":313,"orcid":314},"Xiaohua Yang","https:\u002F\u002Forcid.org\u002F0000-0001-8387-5213",{"name":316,"orcid":317},"Dehui Bian","https:\u002F\u002Forcid.org\u002F0000-0001-6921-1875",{"name":319,"orcid":320},"Qi Wang","https:\u002F\u002Forcid.org\u002F0000-0002-3156-9246",{"name":322,"orcid":8},"Lequn Gu",{"name":324,"orcid":8},"Ailing Zhang",{"name":326,"orcid":8},"Wei Gao",{"name":328,"orcid":8},"Wenjie Qi",{"name":330,"orcid":8},"Yayun Ma",{"tldr":332,"method":333,"finding":334,"direction":82,"opportunity":335},"以安阳为例，用XGBoost-SHAP分析2000—2020年气候水分亏缺的空间异质性及其环境关联。","1 km月降水与潜在蒸散数据计算CMD+，结合XGBoost-SHAP与嵌套空间","CMD+西部山区低、中东部平原高；高程贡献66.1%，NDVI与灌溉比例呈显著非线性交互。","可引入多源遥感与作物种植结构，探究CMD+非线性阈值对灌溉需水与水资源配置的传导机制。","数字乡村与农业信息化","2026-10-20T23:30:23.927575Z",{"id":339,"title":340,"url":341,"summary":342,"summary_zh":8,"content":8,"source_name":343,"source_url":8,"published_at":344,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":345,"score_detail":346,"sources":350,"tags":352,"primary_topic":353,"secondary_topics":354,"classification":357,"search_phrases":376,"slug":379,"view_count":80,"doi":8,"paper":380,"created_at":387},5296,"雷添杰研究员团队《基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别》","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-10-16\u002Fdoc-inivmprm8363597.shtml","《智慧农业(中英文)》2026年第8卷第4期刊载梁万杰、刘晓君、雷添杰等论文,在小麦拔节—抽穗和抽穗—灌浆两个生长阶段进行对照、渍水胁迫、硅肥调控、氨基酸调控控制试验;利用大疆精灵4多光谱无人机采集小麦冠层多光谱图像建立数据集,基于VGG21模型构建识别模型,发现硅肥调控样本识别性能最好,识别精度最高,具良好鲁棒性和可扩展性,可为小麦渍害综合防控提供理论与技术支持。","智慧农业(中英文)(2026,8(4))","2026-10-16T00:00:00Z",76,{"impact":98,"substance":347,"depth":348,"authority":18,"freshness":236,"relevant":20,"comment":349},21,17,"核心期刊论文，方法新颖、结论可靠，对小麦渍害防控有实用价值，值得进入每日精选。",[351],{"name":343,"url":341},[103,25,207,208,209],{"code":211,"slug":212,"name":213,"path":214,"parent_code":112},[355,356],{"code":218,"slug":219,"name":220,"path":221,"parent_code":222},{"code":45,"slug":115,"name":116,"path":117,"parent_code":118},{"status":126,"locked":13,"version":32,"method":33,"evidence":358},{"candidates":359,"agricultural_evidence":39},[360,364,368,372],{"code":211,"score":227,"supported":39,"title":361,"abstract":362,"tags":363},[213],[213],[],{"code":218,"score":227,"supported":39,"title":365,"abstract":366,"tags":367},[238],[238],[],{"code":45,"score":227,"supported":39,"title":369,"abstract":370,"tags":371},[208],[],[207,25,208],{"code":159,"score":46,"supported":39,"title":373,"abstract":374,"tags":375},[],[103],[103],[377,378],"雷添杰 小麦渍害 无人机多光谱","VGG21 小麦渍害 识别模型","雷添杰小麦渍害无人机多光谱-5296",{"doi":8,"openalex_id":8,"authors":381,"venue":8,"cited_by_count":80,"oa_url":8,"card":382,"direction":82,"ingested_from":256},[],{"tldr":383,"method":384,"finding":385,"direction":82,"opportunity":386},"用无人机多光谱图像和VGG21模型识别小麦渍害调控效果。","大疆精灵4采集冠层多光谱图像，构建VGG21识别模型。","硅肥调控样本识别性能最好、精度最高，模型鲁棒可扩展。","可探索多生育期多光谱特征与不同调控措施的耦合机制，并扩展到其他作物渍害监测。","2026-10-19T00:07:48.071055Z",{"id":389,"title":390,"url":391,"summary":392,"summary_zh":8,"content":393,"source_name":394,"source_url":8,"published_at":395,"category":396,"cover_url":8,"hotness":12,"is_selected":13,"score":397,"score_detail":398,"sources":401,"tags":403,"primary_topic":408,"secondary_topics":414,"classification":421,"search_phrases":450,"slug":453,"view_count":80,"doi":8,"paper":8,"created_at":454},5281,"省农科院植保所江油武都\"三水\"绿色融合样板田连续10余年综合治理 稻鱼鸭共生","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7696132538393215528","10月12日江油市武都镇阳亭坝金黄稻田迎来丰收,四川省农科院植保所研究员姬红丽蹲在田埂查叶背(无病斑),亩产干谷不低于1300斤;自2013年起省农科院植保所在此实施\"农田有害生物综合治理课题\"持续10余年,通过田埂种植甜荞、蔷薇、紫云英、二月兰、香根草等蜜源植物为天敌提供庇护所,基地稻田麦田天敌种群数量达农户常规田块的10倍以上。","视频加载中...\n\n川观新闻记者 张彧希 四川农村日报记者 徐灿红 洪瑜\n\n10月12日，江油市武都镇阳亭坝，秋风掠过，稻田翻起金色波浪。\n\n四川省农业科学院植物保护研究所研究员姬红丽蹲在田埂上，拔起一株水稻查看叶背——干干净净，没有病斑。“亩产干谷不会低于1300斤。”再过一两天，这里就要开镰。\n\n这片稻田不普通。自2013年起，省农科院植保所在此实施“农田有害生物综合治理课题”，持续10余年。曾经抛荒的土地，如今稻穗丰盈、游鱼戏水、白鹭翩跹，成为国内率先实现水稻、水产、水禽“三水”绿色融合的样板田。\n\n曾经令人头痛的有害生物，是如何被“赶出”这片田的？\n\n![Image 1](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-axegupay5k\u002F0236314001894642bb5bcf371554180b~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1792973320&x-signature=XhegSE7aGrMWXTC4o0zuZt8sDFo%3D)\n俯瞰基地。\n\n**第一招：良种打底，病害止步田外**\n\n“三水”融合，第一关是选品种。“不光看产量和米质，更看重抗病性。”姬红丽说。西南稻区主要病害有稻瘟病、纹枯病、稻曲病，农户常规靠打药防病，但基地全生育期几乎不施化学杀菌剂，底气来自多抗性品种。\n\n连续十多年，团队每年从市场主流品种中筛选多抗性优异品种，在江油基地展示。“江油气候利于多种病害发生，对品种抗性要求更高，也更容易筛出好品种。”姬红丽说。\n\n今年基地集中示范川康优2115、品香优607等优质水稻，在稻瘟、稻曲等病害抗性上表现优异。品种自身抗性强，病害起不来，化学农药自然省了。\n\n品种抗性究竟如何？种子企业也很关心。四川金色绿丹种业有限公司川北区域经理陈胜龙沿试验田看了几遍：“没找到稻瘟病、稻曲病症状，叶片干净，秆壮穗大，产量很乐观。”\n\n**第二招：田埂布阵，天敌与“陷阱”控虫**\n\n![Image 2](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002Facfcb249e48cd472f480260e5551bb65~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1792973320&x-signature=B1pojs4Mx2mcaw2GJlWWImuIBDk%3D)\n田埂上种的甜荞。\n\n病害靠品种扛，虫害靠天敌控。不足半米宽的田埂，像一座迷你花园：甜荞开白花，蔷薇正艳，菜粉蝶、蜜蜂穿梭其间。\n\n![Image 3](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002F85a45dc6b1fa07d071fd5c3d1578c4f2~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1792973320&x-signature=oCp5UghEu2I%2BkG6F5S36WgQDGUA%3D)\n田埂上种的蔷薇。\n\n“这些都是蜜源植物，是精心选的‘生态卫士’。”姬红丽说。稻麦轮作茬口期，田里没有庄稼，自然天敌没处安身，蜜源植物便补上空当，提供花粉、花蜜和庇护所。\n\n目前田埂还种了紫云英、二月兰，基地稻田麦田里的天敌种群数量，达到农户常规自防田块的10倍以上，全是自然天敌，没有人工投放。\n\n记者发现，田埂上还种着一人高的香根草。姬红丽介绍，这是从泰国引进的“陷阱植物”：气味吸引二化螟产卵，但含有毒活性物质，不适合幼虫发育，孵化幼虫大多低龄死亡，无法发育为成虫。一代代下来，基地二化螟数量越来越低。\n\n效果有数据支撑：水稻螟虫、麦蚜虫连续八年没达到化学防治用药阈值；蜘蛛、青蛙、田螺、泥鳅、黄鳝、蛇、野鸭、翠鸟等指示生物相继回归，并向周边农田扩散。“插秧时，当地村民都来抓黄鳝，知道我们不用药，黄鳝比别处多。”姬红丽笑着说。\n\n**第三招：生态当家，少打药照样高产**\n\n开农资店的罗勇，生意不如以前，但他却为啥挺开心？\n\n罗勇原是当地农资店主，卖农药化肥。“那会儿种植户见虫就打药，我生意也好。”但姬红丽团队来了之后，带来一个新理念：生态当家，少打药照样高产。\n\n“一开始我不信。”姬红丽团队带着罗勇一次次下田示范，请他到基地看效果。“后来发现人家不打药，虫子比我的还少，稻子还壮。”\n\n罗勇动了心，一边开农资店，一边承包土地。如今种植已发展到400多亩。“跟着团队学病虫害防治，品种从他们筛出的抗病品种里选，少打药减少人工，一亩地省100多块钱，产量基本不受影响。”他估计，今年亩产干谷能到1300至1400斤，在武都镇算高的。\n\n自己尝到甜头，罗勇又向周边大户推广：“少打药不是不管，是要靠品种抗病、靠天敌控虫。”如今，武都镇大户基本减少了打药次数，但产量没降。","今日头条川观新闻(2026-10-13)","2026-10-13T00:00:00Z","报道",69,{"impact":16,"substance":399,"depth":348,"authority":12,"freshness":46,"relevant":20,"comment":400},20,"连续十余年综合治理的实证报道，数据与多方信源扎实，具行业示范价值，但时效偏旧。",[402],{"name":394,"url":391},[404,405,26,406,407],"绿色防控","农药减量","生态农业","稻鱼鸭共生",{"code":409,"slug":410,"name":411,"path":412,"parent_code":413},"D3","integrated-aquaculture","稻渔种养与生态渔业","\u002Ftopic\u002Faquaculture\u002Fintegrated-aquaculture","D",[415],{"code":416,"slug":417,"name":418,"path":419,"parent_code":420},"F4","crop-protection","农药与绿色防控","\u002Ftopic\u002Finputs-equipment\u002Fcrop-protection","F",{"status":126,"locked":13,"version":32,"method":33,"evidence":422},{"candidates":423,"agricultural_evidence":39},[424,429,434,441,446],{"code":416,"score":268,"supported":39,"title":425,"abstract":427,"tags":428},[426],"植保",[426],[405,404],{"code":409,"score":236,"supported":39,"title":430,"abstract":432,"tags":433},[431],"稻鱼",[],[],{"code":435,"score":436,"supported":39,"title":437,"abstract":438,"tags":440},"A1",3,[],[439],"稻田",[],{"code":442,"score":56,"supported":13,"title":443,"abstract":444,"tags":445},"H8",[],[],[406,404],{"code":37,"score":20,"supported":13,"title":447,"abstract":448,"tags":449},[],[],[26],[451,452],"四川省农科院 植保所 江油 稻鱼鸭","三水融合 绿色防控 样板田","四川省农科院植保所江油稻鱼鸭-5281","2026-10-19T00:07:41.376347Z",{"id":456,"title":457,"url":458,"summary":459,"summary_zh":460,"content":8,"source_name":461,"source_url":458,"published_at":344,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":397,"score_detail":462,"sources":464,"tags":466,"primary_topic":469,"secondary_topics":470,"classification":475,"search_phrases":498,"slug":501,"view_count":20,"doi":502,"paper":503,"created_at":525},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",{"impact":38,"substance":399,"depth":98,"authority":38,"freshness":269,"relevant":20,"comment":463},"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。",[465],{"name":461,"url":458},[103,25,152,467,468],"油棕","病害诊断",{"code":45,"slug":115,"name":116,"path":117,"parent_code":118},[471],{"code":149,"slug":472,"name":473,"path":474,"parent_code":118},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":126,"locked":13,"version":32,"method":33,"evidence":476},{"candidates":477,"agricultural_evidence":39},[478,482,487,494],{"code":45,"score":136,"supported":39,"title":479,"abstract":480,"tags":481},[49],[133,49],[25],{"code":149,"score":38,"supported":39,"title":483,"abstract":484,"tags":486},[155],[485],"YOLO",[152],{"code":488,"score":86,"supported":39,"title":489,"abstract":490,"tags":493},"B5",[],[491,492],"蘑菇","mushroom",[],{"code":159,"score":20,"supported":13,"title":495,"abstract":496,"tags":497},[],[],[103],[499,500],"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":502,"openalex_id":504,"authors":505,"venue":461,"cited_by_count":80,"oa_url":458,"card":520,"direction":82,"ingested_from":83},"W7222626135",[506,509,512,514,517],{"name":507,"orcid":508},"Wan Siu Hong","https:\u002F\u002Forcid.org\u002F0000-0002-8254-4962",{"name":510,"orcid":511},"Jonathan Yong Chung Ee","https:\u002F\u002Forcid.org\u002F0000-0003-4079-8005",{"name":513,"orcid":8},"Jin Yuan Chan",{"name":515,"orcid":516},"Mohamad Izzuddin Anuar","https:\u002F\u002Forcid.org\u002F0000-0002-4929-5175",{"name":518,"orcid":519},"Mahmud Iwan Solihin","https:\u002F\u002Forcid.org\u002F0000-0002-5293-7466",{"tldr":521,"method":522,"finding":523,"direction":82,"opportunity":524},"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"]