[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2492":3,"related-2492":96},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":36,"classification":43,"search_phrases":79,"slug":82,"view_count":83,"doi":84,"paper":85,"created_at":95},2492,"BiFormer-Enhanced YOLOv11n for Accurate Maize Ear Detection in Seed Production Fields(玉米穗识别 BiF-YOLO)","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16181780","青岛农业大学机电工程学院 2026 年 9 月 10 日在《Agronomy》(Section Precision and Digital Agriculture)发表。提出 BiF-YOLO 模型基于 YOLOv11n 和 BiFormer 架构,三项目标性增强策略:①在特征提取网络嵌入 C3k2_AdditiveBlock 模块以增强田间被遮挡和小型玉米穗的识别能力;②构建 C2BRA 双层路由注意力机制(Cross-stage partial 2 Bottleneck with Residual Attention)以抑制背景干扰;③采用 ShapeIoU 损失函数。从胶州和张掖种子生产田采集玉米穗图像。BiF-YOLO 模型有效适应复杂田间作业场景,为制种玉米收获机的实时识别与产量估计提供技术支撑。",null,"MDPI Agronomy 2026-09-10","2026-09-09T16:00:00Z","论文",10,false,74,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},16,21,17,13,7,1,"面向制种玉米收获的轻量化检测模型改进，方法有针对性增强且数据来自真实制种田，对智能农机与产量估计有实用价值，但属细分技术进展，影响面有限。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","种业振兴","玉米","目标检测",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},"A3","maize","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[37],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":44,"locked":13,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":51},[49,55,60,67,74],{"code":32,"score":50,"supported":51,"title":52,"abstract":53,"tags":54},20,true,[29,33],[29],[29],{"code":38,"score":19,"supported":51,"title":56,"abstract":58,"tags":59},[57],"YOLO",[57],[27,30],{"code":61,"score":62,"supported":51,"title":63,"abstract":64,"tags":66},"I1",4,[],[65],"digital agriculture",[26],{"code":68,"score":69,"supported":51,"title":70,"abstract":71,"tags":73},"A7",3,[],[72],"间作",[],{"code":75,"score":21,"supported":13,"title":76,"abstract":77,"tags":78},"F1",[],[],[28],[80,81],"农业人工智能 智慧农业 目标检测 种业振兴","农业人工智能 智慧农业","农业人工智能智慧农业目标检测种业振兴-2492",2,"10.3390\u002Fagronomy16181780",{"doi":84,"openalex_id":8,"authors":86,"venue":8,"cited_by_count":87,"oa_url":8,"card":88,"direction":92,"ingested_from":94},[],0,{"tldr":89,"method":90,"finding":91,"direction":92,"opportunity":93},"提出BiF-YOLO模型，在制种田实现玉米穗精准检测。","基于YOLOv11n，融合BiFormer、C3k2_AdditiveBlock","BiF-YOLO有效适应复杂田间场景，提升遮挡和小目标玉米穗检测精度。","农业人工智能与决策模型","可探索轻量化模型在收获机边缘设备上的实时部署与产量估计集成。","agent","2026-09-15T00:04:27.207493Z",{"total":97,"page":21,"page_size":97,"items":98},6,[99,164,254,316,402,467],{"id":100,"title":101,"url":102,"summary":103,"summary_zh":104,"content":8,"source_name":105,"source_url":102,"published_at":106,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":107,"score_detail":108,"sources":114,"tags":116,"primary_topic":119,"secondary_topics":120,"classification":122,"search_phrases":143,"slug":146,"view_count":87,"doi":147,"paper":148,"created_at":163},4759,"Machine Learning-based Prediction of SVI Parameter in Maize: A Comparative Study and Feature Importance Analysis","https:\u002F\u002Fdoi.org\u002F10.24925\u002Fturjaf.v14i10.2870-2879.9043","Background: Accurate estimation of seedling vigor indices (SVI) is critical for monitoring plant health and predicting yields in precision agriculture. This study comparatively evaluates the performance of different machine learning algorithms in estimating the SVI parameter. Methods: Germination data were collected from 39 maize genotypes under three different salinity conditions (0 mM, 100 mM, and 200 mM NaCl), including the parameters Gmax, MGT, GI, SL, RL, SdL, SMR, RMR, and SVI. The dataset was preprocessed through normalization to the [0–1] range. The SVI parameter was estimated using four different machine learning methods: Random Forest, CatBoost, LightGBM, and Support Vector Regression (SVR). To evaluate the performance of the models, both 10-fold cross-validation and 80%–20% hold-out validation techniques were employed. The model performance was examined using RMSE, MSE, MAE, and R² metrics. Results: The findings show that all models have a high explanatory power in the training dataset. Specifically, the CatBoost model showed the highest success in the training phase (R²=0.9962), whereas the SVR model achieved the highest generalization performance on the test dataset (R²=0.9712, RMSE=0.0582). Feature importance analysis results revealed that the 'App' parameter had the highest impact on the target variable in most models, but different structural interactions were prominent in the LightGBM model. The results demonstrate that machine learning techniques provide high accuracy in SVI estimation and that the tendency towards overfitting is limited. Conclusions: In conclusion, this study confirms that machine learning techniques are powerful and reliable tools for estimating spectral indices in precision agriculture applications. The integration of SVR and ensemble-based models into agricultural decision support systems is expected to significantly contribute to optimizing resource use and improving yield predictions.","背景：准确估计幼苗活力指数（SVI）对于精准农业中监测植物健康和预测产量至关重要。本研究比较评估了不同机器学习算法在估计SVI参数方面的性能。方法：从39个玉米基因型在三种不同盐度条件（0 mM、100 mM和200 mM NaCl）下收集发芽数据，包括Gmax、MGT、GI、SL、RL、SdL、SMR、RMR和SVI等参数。数据集通过归一化至[0–1]范围进行预处理。采用四种不同的机器学习方法估计SVI参数：随机森林、CatBoost、LightGBM和支持向量回归（SVR）。为评估模型性能，采用了10折交叉验证和80%–20%留出验证技术。使用RMSE、MSE、MAE和R²指标检验模型性能。结果：研究结果表明，所有模型在训练数据集中均具有较高的解释力。具体而言，CatBoost模型在训练阶段表现出最高的成功率（R²=0.9962），而SVR模型在测试数据集上取得了最高的泛化性能（R²=0.9712，RMSE=0.0582）。特征重要性分析结果显示，在大多数模型中，“App”参数对目标变量的影响最大，但在LightGBM模型中不同的结构交互作用更为突出。结果表明，机器学习技术在SVI估计中提供了高精度，且过拟合倾向有限。结论：总之，本研究证实机器学习技术是精准农业应用中估计光谱指数的强大而可靠的工具。将SVR和基于集成的模型整合到农业决策支持系统中，预计将显著有助于优化资源利用和改善产量预测。","Turkish Journal of Agriculture - Food Science and Technology","2026-10-11T00:00:00Z",63,{"impact":109,"substance":110,"depth":16,"authority":111,"freshness":112,"relevant":21,"comment":113},8,18,12,9,"方法对比扎实、结论可靠，但属细分领域论文，产业影响有限，适合主题聚合而非头条精选。",[115],{"name":105,"url":102},[26,27,117,29,118],"机器学习","耐盐育种",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[121],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":13,"version":45,"method":46,"evidence":123},{"candidates":124,"agricultural_evidence":51},[125,132,137],{"code":38,"score":126,"supported":51,"title":127,"abstract":129,"tags":131},19,[128],"machine learning",[117,128,130],"decision support",[27,117],{"code":32,"score":133,"supported":51,"title":134,"abstract":135,"tags":136},15,[33],[29,33],[29],{"code":61,"score":20,"supported":51,"title":138,"abstract":139,"tags":142},[],[140,141],"精准农业","precision agriculture",[26],[144,145],"玉米 SVI 机器学习","玉米 耐盐 幼苗活力指数","玉米SVI机器学习-4759","10.24925\u002Fturjaf.v14i10.2870-2879.9043",{"doi":147,"openalex_id":149,"authors":150,"venue":105,"cited_by_count":87,"oa_url":102,"card":157,"direction":92,"ingested_from":162},"W7221462188",[151,154],{"name":152,"orcid":153},"Mustafa Turan Arslan","https:\u002F\u002Forcid.org\u002F0000-0001-5498-6571",{"name":155,"orcid":156},"Gülay Zülkadir","https:\u002F\u002Forcid.org\u002F0000-0003-3488-4011",{"tldr":158,"method":159,"finding":160,"direction":92,"opportunity":161},"用四种机器学习模型基于39个玉米基因型盐胁迫发芽数据预测幼苗活力指数SVI。","39个玉米基因型在三种盐浓度下的发芽数据，归一化后用RF、CatBoost、Li","SVR泛化最优（R²=0.9712），CatBoost训练拟合最高；App参数对SVI影响最大。","可扩展到多作物多胁迫环境，结合光谱或图像表型数据提升SVI预测的田间适用性。","openalex","2026-10-12T23:30:44.762497Z",{"id":165,"title":166,"url":167,"summary":168,"summary_zh":169,"content":8,"source_name":170,"source_url":167,"published_at":171,"category":11,"cover_url":8,"hotness":12,"is_selected":51,"score":172,"score_detail":173,"sources":177,"tags":179,"primary_topic":182,"secondary_topics":183,"classification":185,"search_phrases":214,"slug":217,"view_count":218,"doi":219,"paper":220,"created_at":253},3842,"Raspberry Pi Lightweight Deep Learning Models Deployed for Corn Growth Stage Classification Using PhenoCam Images","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193337","Identifying crop growth stages is essential for comprehensive assessment that facilitates timely and precise agronomic management. However, conventional field-based manual scouting is labor-intensive, time-consuming, and lacks scalability. Digital field images with advanced models deployed on portable edge-computing devices offer an alternative solution for real-time crop monitoring and decision support. Therefore, in this study, the standard 8 corn growth stages were defined as 8 classes based on distinct visual canopy appearance patterns observed in PhenoCam (near-surface [proximal] remote sensing network camera) imagery collected from 10 PhenoCam sites. These classes do not correspond directly to standard agronomic vegetation and reproductive growth stages. For modeling, four lightweight deep learning (DL) models, ELiteCrop0, ELiteCrop1, ELiteCrop4, and MobNetCropV2, were developed and evaluated across five image vertical clipping levels (0–40%) using a supercomputer (NDSU CCAST). The optimized model was subsequently deployed on a single-board Raspberry Pi 5 computer for edge inference. Model training accounted for the majority of the total CPU time, exceeding 97%, while the testing times ranged from 0.01–0.12 min, enabling real-time applications. Among the models, ELiteCrop0 achieved the most balanced performance with a confusion-matrix diagonal ratio (CMDR) of 0.93, followed by ELiteCrop1 (CMDR = 0.92). Overall, model performance decreased with increasing vertical clipping; therefore, a moderate image clipping (0–10%) was recommended for improved computational efficiency. Analysis with a supercomputer produced an intrasite (same training sites) accuracy of 0.90–0.93 (Raspberry Pi: 0.78–0.81) and an intersite (unseen test sites) accuracy of 0.48–0.50 (Raspberry Pi: 0.41–0.43), indicating challenges with model generalization. Raspberry Pi processed ≈ 1000 images\u002Fmin at 68 °C, with a PhenoCam:Raspberry Pi processing ratio of 1:2500 at 50% capacity over an 8 h day. Overall, this study presents a scalable and cost-effective solution for real-time corn growth stage monitoring in precision agriculture, which could be extended to other crops.","识别作物生长阶段对于全面评估、促进及时精准的农艺管理至关重要。然而，传统的田间人工巡查劳动强度大、耗时且缺乏可扩展性。部署在便携式边缘计算设备上的数字田间图像与先进模型为实时作物监测和决策支持提供了替代方案。因此，本研究基于从10个PhenoCam（近地面[近端]遥感网络相机）站点采集的影像中观察到的不同冠层视觉外观模式，将标准的8个玉米生长阶段定义为8个类别。这些类别并不直接对应于标准的农艺营养生长和生殖生长阶段。在建模方面，开发了四种轻量级深度学习（DL）模型——ELiteCrop0、ELiteCrop1、ELiteCrop4和MobNetCropV2，并利用超级计算机（NDSU CCAST）在五种图像垂直裁剪水平（0–40%）下进行了评估。随后，优化后的模型被部署到单板Raspberry Pi 5计算机上进行边缘推理。模型训练占总CPU时间的大部分，超过97%，而测试时间为0.01–0.12分钟，支持实时应用。在各模型中，ELiteCrop0实现了最均衡的性能，混淆矩阵对角线比率（CMDR）为0.93，其次是ELiteCrop1（CMDR = 0.92）。总体而言，模型性能随垂直裁剪比例的增加而下降；因此，建议采用适度的图像裁剪（0–10%）以提高计算效率。使用超级计算机的分析得出站内（相同训练站点）准确率为0.90–0.93（Raspberry Pi：0.78–0.81），站间（未见测试站点）准确率为0.48–0.50（Raspberry Pi：0.41–0.43），表明模型泛化面临挑战。Raspberry Pi在68 °C下处理约1000张图像\u002F分钟，在8小时工作日50%容量下，PhenoCam与Raspberry Pi的处理比为1:2500。总体而言，本研究为精准农业中的实时玉米生长阶段监测提供了一种可扩展且经济高效的解决方案，并可扩展至其他作物。","Remote Sensing","2026-09-29T00:00:00Z",81,{"impact":110,"substance":174,"depth":110,"authority":175,"freshness":112,"relevant":21,"comment":176},22,14,"该研究将轻量深度学习模型部署于树莓派实现玉米生育期实时识别，方法新颖、数据扎实，对精准农业边缘监测有参考价值。",[178],{"name":170,"url":167},[26,27,180,29,181],"边缘计算","遥感",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[184],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":13,"version":45,"method":46,"evidence":186},{"candidates":187,"agricultural_evidence":51},[188,194,199,203,209],{"code":38,"score":110,"supported":51,"title":189,"abstract":191,"tags":193},[190],"deep learning",[192,190,130],"深度学习",[27],{"code":32,"score":133,"supported":51,"title":195,"abstract":197,"tags":198},[196],"corn",[29,196],[29],{"code":61,"score":20,"supported":51,"title":200,"abstract":201,"tags":202},[],[140,141],[26],{"code":204,"score":20,"supported":51,"title":205,"abstract":206,"tags":208},"I3",[],[181,207],"remote sensing",[181],{"code":210,"score":62,"supported":51,"title":211,"abstract":212,"tags":213},"I5",[],[180],[180],[215,216],"Raspberry Pi 玉米 生长阶段","PhenoCam 玉米 深度学习","RaspberryPi玉米生长阶段-3842",5,"10.3390\u002Frs18193337",{"doi":219,"openalex_id":221,"authors":222,"venue":170,"cited_by_count":87,"oa_url":167,"card":247,"direction":251,"ingested_from":162},"W7214787420",[223,226,229,232,235,238,241,244],{"name":224,"orcid":225},"Anne Joice","https:\u002F\u002Forcid.org\u002F0000-0001-7499-9222",{"name":227,"orcid":228},"Humeera Tazeen","https:\u002F\u002Forcid.org\u002F0000-0003-2411-0725",{"name":230,"orcid":231},"Talha Tufaique","https:\u002F\u002Forcid.org\u002F0000-0002-4490-5341",{"name":233,"orcid":234},"Mathala Juliet Gupta","https:\u002F\u002Forcid.org\u002F0000-0002-3886-2429",{"name":236,"orcid":237},"Cannayen Igathinathane","https:\u002F\u002Forcid.org\u002F0000-0001-8884-7959",{"name":239,"orcid":240},"Nitin Rai","https:\u002F\u002Forcid.org\u002F0000-0002-9350-9601",{"name":242,"orcid":243},"Craig W. Whippo","https:\u002F\u002Forcid.org\u002F0000-0002-7626-6919",{"name":245,"orcid":246},"David Walter Archer","https:\u002F\u002Forcid.org\u002F0000-0002-4816-7040",{"tldr":248,"method":249,"finding":250,"direction":251,"opportunity":252},"用PhenoCam图像训练轻量深度学习模型，在树莓派上实时分类玉米8个生长阶段。","基于10个PhenoCam站点图像，开发4种轻量DL模型，在树莓派5上边缘推理。","ELiteCrop0表现最佳（CMDR=0.93），站点内精度0.90-0.93，但站点间泛化差（0","农业遥感与作物表型","站点间泛化差是主要瓶颈，可研究跨站点迁移学习或域适应以提升模型鲁棒性。","2026-09-30T23:30:29.168194Z",{"id":255,"title":256,"url":257,"summary":258,"summary_zh":8,"content":8,"source_name":259,"source_url":257,"published_at":260,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":261,"score_detail":262,"sources":264,"tags":266,"primary_topic":269,"secondary_topics":270,"classification":276,"search_phrases":301,"slug":304,"view_count":62,"doi":305,"paper":306,"created_at":315},3152,"An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23311932.2026.2725400","An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania。Cogent Food & Agriculture","Cogent Food & Agriculture","2026-09-22T00:00:00Z",69,{"impact":111,"substance":110,"depth":16,"authority":19,"freshness":12,"relevant":21,"comment":263},"论文提出物联网与机器学习融合的玉米产量预测框架，方法有新意但属区域性应用研究，影响力有限，时效性强。",[265],{"name":259,"url":257},[26,27,267,268,29],"产量预测","物联网",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[271,272],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":210,"slug":273,"name":274,"path":275,"parent_code":42},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":44,"locked":13,"version":45,"method":46,"evidence":277},{"candidates":278,"agricultural_evidence":51},[279,283,288,292,297],{"code":32,"score":111,"supported":51,"title":280,"abstract":281,"tags":282},[33],[33],[29],{"code":61,"score":111,"supported":51,"title":284,"abstract":286,"tags":287},[285],"smart agriculture",[285],[26],{"code":38,"score":111,"supported":51,"title":289,"abstract":290,"tags":291},[128],[128],[27],{"code":210,"score":111,"supported":51,"title":293,"abstract":295,"tags":296},[294],"IoT",[294],[268],{"code":204,"score":21,"supported":13,"title":298,"abstract":299,"tags":300},[],[],[267],[302,303],"坦桑尼亚 玉米 产量预测","物联网 机器学习 智慧农业","坦桑尼亚玉米产量预测-3152","10.1080\u002F23311932.2026.2725400",{"doi":305,"openalex_id":307,"authors":308,"venue":259,"cited_by_count":87,"oa_url":257,"card":8,"direction":314,"ingested_from":162},"W7213978365",[309,312],{"name":310,"orcid":311},"Alcardo Alex Barakabitze","https:\u002F\u002Forcid.org\u002F0000-0001-8960-8415",{"name":313,"orcid":8},"Yasinta Nzogera","智慧农业 \u002F 农业物联网","2026-09-22T23:30:10.178097Z",{"id":317,"title":318,"url":319,"summary":320,"summary_zh":321,"content":8,"source_name":322,"source_url":319,"published_at":323,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":324,"score_detail":325,"sources":328,"tags":330,"primary_topic":332,"secondary_topics":333,"classification":335,"search_phrases":362,"slug":365,"view_count":83,"doi":366,"paper":367,"created_at":401},2505,"A continually evolving knowledge-guided deep learning framework for daily maize yield formation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104981","CONTEXT As multi-source agricultural datasets expand, accurate and interpretable simulation of crop yield formation is increasingly feasible and important for food security. Process-based models are widely used for yield forecasting but require laborious regional calibration. Artificial intelligence models learn physiological patterns from large datasets but lack physiological consistency and generalize poorly under data-scarce conditions. OBJECTIVE We developed AgroEvoDeep-Yield, a knowledge-guided model that encodes mechanistic understanding through its neural architecture, enabling explicit and interpretable simulation of daily maize yield formation from flowering to maturity. We further established a framework that supports continual model evolution as new data become available. METHODS The model was pretrained on APSIM-simulated grain number and daily grain biomass sequences to impose physiological consistency. Following pretraining, the model evolved through two continual learning stages. First, field-level continual learning using 796 field observations reduced biases inherited from APSIM. The model was then adapted to regional-scale multi-source inputs using long-term records from 945 meteorological stations and expert-constrained cultivar-parameter optimization. RESULTS AND CONCLUSIONS After field-level continual learning, AgroEvoDeep-Yield reduced grain number and yield simulation errors by 29% and 24%, respectively, relative to APSIM, and outperformed conventional machine learning models in out-of-region prediction. Region-level continual learning reduced yield RMSE to 1.09 t\u002Fha, and expert-constrained cultivar-parameter optimization further reduced it to 0.80 t\u002Fha. SIGNIFICANCE This study demonstrates how a knowledge-guided model can be repeatedly adapted as new data become available, providing a practical framework for continual model evolution and a basis for future agricultural decision support.","背景 随着多源农业数据集的不断扩展，准确且可解释地模拟作物产量形成过程日益可行，对粮食安全也愈发重要。基于过程的模型广泛用于产量预测，但需要耗费大量精力进行区域校准。人工智能模型能够从大规模数据集中学习生理模式，但缺乏生理一致性，在数据稀缺条件下泛化能力较差。目标 我们开发了AgroEvoDeep-Yield，这是一种知识引导模型，通过其神经网络架构编码机理认识，能够对玉米从开花到成熟的逐日产量形成过程进行显式且可解释的模拟。我们还建立了一个框架，以支持在新数据可用时模型的持续演化。方法 该模型在APSIM模拟的粒数和逐日籽粒生物量序列上进行预训练，以施加生理一致性约束。预训练后，模型通过两个持续学习阶段进行演化。首先，利用796个田间观测数据进行田块级持续学习，以减少继承自APSIM的偏差。随后，利用945个气象站的长期记录和专家约束的品种参数优化，将模型适配到区域尺度多源输入。结果与结论 经过田块级持续学习后，AgroEvoDeep-Yield相对于APSIM将粒数和产量模拟误差分别降低了29%和24%，并在区域外预测中优于传统机器学习模型。区域级持续学习将产量RMSE降至1.09 t\u002Fha，专家约束的品种参数优化进一步将其降至0.80 t\u002Fha。意义 本研究表明，知识引导模型可以在新数据可用时被反复适配，为模型持续演化提供了实用框架，并为未来农业决策支持奠定了基础。","Agricultural Systems","2026-09-14T00:00:00Z",85,{"impact":174,"substance":326,"depth":110,"authority":175,"freshness":109,"relevant":21,"comment":327},23,"知识引导的深度学习框架实现玉米逐日产量形成模拟，误差显著低于APSIM且支持持续学习，方法新颖、数据规模扎实，对智慧农业决策支持有参考价值。",[329],{"name":322,"url":319},[26,27,267,29,331],"作物模型",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[334],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":13,"version":45,"method":46,"evidence":336},{"candidates":337,"agricultural_evidence":51},[338,343,347,354,358],{"code":38,"score":126,"supported":51,"title":339,"abstract":340,"tags":342},[190],[117,128,341,130],"artificial intelligence",[331,27],{"code":32,"score":133,"supported":51,"title":344,"abstract":345,"tags":346},[33],[29,33],[29],{"code":348,"score":97,"supported":51,"title":349,"abstract":350,"tags":353},"A8",[],[351,352],"粮食安全","food security",[],{"code":61,"score":21,"supported":13,"title":355,"abstract":356,"tags":357},[],[],[26],{"code":204,"score":21,"supported":13,"title":359,"abstract":360,"tags":361},[],[],[267],[363,364],"农业人工智能 产量预测 作物模型 智慧农业","农业人工智能 产量预测","农业人工智能产量预测作物模型智慧农业-2505","10.1016\u002Fj.agsy.2026.104981",{"doi":366,"openalex_id":368,"authors":369,"venue":322,"cited_by_count":87,"oa_url":319,"card":396,"direction":92,"ingested_from":162},"W7212532256",[370,372,374,377,380,383,385,388,390,393],{"name":371,"orcid":8},"Junji Ou",{"name":373,"orcid":8},"Wenyao Yan",{"name":375,"orcid":376},"Fangzheng Chen","https:\u002F\u002Forcid.org\u002F0009-0006-5061-6227",{"name":378,"orcid":379},"Tao Ye","https:\u002F\u002Forcid.org\u002F0000-0002-5037-8410",{"name":381,"orcid":382},"Ke Liu","https:\u002F\u002Forcid.org\u002F0000-0002-8343-0449",{"name":384,"orcid":8},"Matthew Tom Harrison",{"name":386,"orcid":387},"William D. Batchelor","https:\u002F\u002Forcid.org\u002F0000-0002-3881-6246",{"name":389,"orcid":8},"Yong Chen",{"name":391,"orcid":392},"Kelin Hu","https:\u002F\u002Forcid.org\u002F0000-0001-9321-0821",{"name":394,"orcid":395},"Puyu Feng","https:\u002F\u002Forcid.org\u002F0000-0003-4845-9876",{"tldr":397,"method":398,"finding":399,"direction":92,"opportunity":400},"提出知识引导的深度学习框架AgroEvoDeep-Yield，实现玉米逐日产量形成的可解释模拟与持续","基于APSIM模拟数据预训练，结合796个田间观测和945个气象站数据持续学习。","田间持续学习使粒数和产量误差比APSIM降低29%和24%，区域优化后RMSE降至0.80 t\u002Fha","可探索将知识引导与持续学习框架迁移至其他作物，并融合实时遥感与物联网数据实现动态产量预测。","2026-09-15T23:30:04.611750Z",{"id":403,"title":404,"url":405,"summary":406,"summary_zh":407,"content":8,"source_name":408,"source_url":405,"published_at":409,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":410,"score_detail":411,"sources":413,"tags":415,"primary_topic":417,"secondary_topics":418,"classification":424,"search_phrases":443,"slug":446,"view_count":69,"doi":447,"paper":448,"created_at":466},2058,"Machine Learning-Based Prediction of Fall Armyworm (Spodoptera frugiperda) Outbreaks in Maize Production Systems of Northern Nigeria Using Climate and Remote Sensing Data","https:\u002F\u002Fdoi.org\u002F10.58578\u002Fkijst.v3i3.12026","Fall Armyworm (Spodoptera frugiperda) poses a substantial threat to maize production across sub-Saharan Africa, particularly in Nigeria, where climatic variability intensifies the risk of pest outbreaks. This study developed and evaluated machine learning models for predicting Fall Armyworm outbreaks in northern Nigeria using integrated climate and remote sensing variables. A retrospective modeling framework was applied to simulated but biologically constrained datasets covering a six-year period (2019–2024) and comprising temperature, rainfall, relative humidity, Normalized Difference Vegetation Index (NDVI), and vegetation condition indices. Three supervised learning algorithms—Random Forest, Support Vector Machine, and Gradient Boosting—were trained and validated using five-fold cross-validation. Gradient Boosting achieved the highest predictive accuracy at 92.8%, followed by Random Forest at 89.2% and Support Vector Machine at 84.6%. Temperature, relative humidity, and NDVI emerged as the most influential predictors of outbreak occurrence, while the integration of satellite-derived vegetation indices improved overall model performance. These findings demonstrate the potential of combining machine learning with remote sensing data to develop scalable and cost-effective early warning systems for agricultural pest management. However, because the models were developed using simulated data, their predictive validity requires confirmation using field-collected observational data. The proposed framework contributes to data-driven pest surveillance by providing a basis for anticipating outbreaks and supporting timely decision-making in maize production systems.","草地贪夜蛾（Spodoptera frugiperda）对撒哈拉以南非洲的玉米生产构成重大威胁，在尼日利亚尤为突出，因为气候变率加剧了害虫暴发的风险。本研究开发并评估了机器学习模型，利用气候与遥感综合变量预测尼日利亚北部草地贪夜蛾的暴发。研究采用回顾性建模框架，基于模拟但受生物学约束的数据集，覆盖六年时间（2019—2024年），包括温度、降雨量、相对湿度、归一化植被指数（NDVI）及植被状况指数。三种监督学习算法——随机森林、支持向量机和梯度提升——通过五折交叉验证进行训练与验证。梯度提升取得了最高的预测准确率，达92.8%，其次为随机森林（89.2%）和支持向量机（84.6%）。温度、相对湿度和NDVI是暴发发生最具影响力的预测因子，而卫星衍生植被指数的整合提升了模型的整体性能。这些发现表明，将机器学习与遥感数据相结合，有望开发可扩展且成本效益高的农业害虫管理预警系统。然而，由于模型基于模拟数据开发，其预测效度仍需利用实地观测数据加以验证。所提出的框架为数据驱动的害虫监测提供了依据，有助于预判暴发并支持玉米生产系统中的及时决策。","Kwaghe International Journal of Sciences and Technology","2026-09-09T00:00:00Z",75,{"impact":110,"substance":50,"depth":16,"authority":111,"freshness":112,"relevant":21,"comment":412},"将机器学习与气候及遥感数据结合用于尼日利亚北部玉米草地贪夜蛾暴发预测，方法框架有参考价值，但基于模拟数据、结论可靠性待田间验证，属细分领域研究进展。",[414],{"name":408,"url":405},[26,27,29,181,416],"病虫害预警",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[419,420],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":204,"slug":421,"name":422,"path":423,"parent_code":42},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":44,"locked":13,"version":45,"method":46,"evidence":425},{"candidates":426,"agricultural_evidence":51},[427,431,435,439],{"code":32,"score":133,"supported":51,"title":428,"abstract":429,"tags":430},[33],[29,33],[29],{"code":38,"score":133,"supported":51,"title":432,"abstract":433,"tags":434},[128],[117,128],[27],{"code":204,"score":133,"supported":51,"title":436,"abstract":437,"tags":438},[207],[181,207],[181],{"code":61,"score":21,"supported":13,"title":440,"abstract":441,"tags":442},[],[],[26],[444,445],"农业人工智能 病虫害预警 智慧农业 玉米","农业人工智能 病虫害预警","农业人工智能病虫害预警智慧农业玉米-2058","10.58578\u002Fkijst.v3i3.12026",{"doi":447,"openalex_id":449,"authors":450,"venue":408,"cited_by_count":87,"oa_url":8,"card":461,"direction":251,"ingested_from":162},"W7212022953",[451,453,455,457,459],{"name":452,"orcid":8},"Okwor Jude I.",{"name":454,"orcid":8},"Attamah Chinyere G.",{"name":456,"orcid":8},"Uchendu Christian N.",{"name":458,"orcid":8},"Onyima John O.",{"name":460,"orcid":8},"Idoko Bartholomew",{"tldr":462,"method":463,"finding":464,"direction":92,"opportunity":465},"用气候与遥感数据构建机器学习模型预测尼日利亚北部玉米草地贪夜蛾暴发。","随机森林、SVM、梯度提升，结合温度、降雨、湿度、NDVI等模拟数据，五折交叉验","梯度提升准确率最高达92.8%，温度、相对湿度和NDVI是最关键预测因子。","模型基于模拟数据，亟需用田间实测数据验证，并开发可扩展的实时早期预警系统。","2026-09-10T23:30:27.820508Z",{"id":468,"title":469,"url":470,"summary":471,"summary_zh":472,"content":8,"source_name":473,"source_url":470,"published_at":474,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":261,"score_detail":475,"sources":477,"tags":479,"primary_topic":481,"secondary_topics":482,"classification":484,"search_phrases":503,"slug":506,"view_count":21,"doi":507,"paper":508,"created_at":541},5164,"Lightweight Hybrid CNN-Transformer Network for Robust Maize Leaf Disease Detection and Edge Deployment","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.50","Early and accurate detection of maize leaf diseases is essential for improving crop productivity and supporting precision agriculture.However, deep learning models trained on controlled leaf-image datasets often experience performance degradation under real-world agricultural conditions because of illumination variation, background clutter, occlusion, leaf orientation, and imaging noise.To address these challenges, this study develops a lightweight deep learning framework for robust maize leaf disease classification and edge-oriented deployment.The framework employs MobileNetV3-Small for efficient extraction of disease-discriminative visual features and investigates lightweight feature-learning strategies for improving classification under challenging field conditions.Experiments were conducted using PlantVillage-Maize and Field-Maize datasets comprising 6,188 images from four categories: Maize Leaf Blight (MLB), Common Rust, Healthy, and Leaf Spot.The image-only MobileNetV3-Small model achieved 97.8% accuracy and a 97.4% F1-score on the controlled PlantVillage-Maize dataset, while its performance decreased to 86.1% accuracy and an 83.9% F1-score on Field-Maize, highlighting the domain gap between controlled and real-field imagery.Robustness was further evaluated under Gaussian noise, illumination variation, and partial occlusion, together with computational-efficiency and edge-deployment analyses.The findings demonstrate the importance of lightweight and robust visual feature learning for practical maize disease diagnosis under real-world agricultural imaging conditions.","早期准确检测玉米叶片病害对于提高作物生产力和支持精准农业至关重要。然而，在受控叶片图像数据集上训练的深度学习模型，在真实农业条件下往往会出现性能下降，原因包括光照变化、背景杂乱、遮挡、叶片朝向以及成像噪声。为应对这些挑战，本研究开发了一个轻量级深度学习框架，用于稳健的玉米叶片病害分类和面向边缘的部署。该框架采用MobileNetV3-Small高效提取具有病害判别力的视觉特征，并研究轻量级特征学习策略，以提升在复杂田间条件下的分类性能。实验使用PlantVillage-Maize和Field-Maize数据集进行，共包含来自四个类别的6，188张图像：玉米大斑病（Maize Leaf Blight，MLB）、普通锈病（Common Rust）、健康（Healthy）和叶斑病（Leaf Spot）。仅使用图像的MobileNetV3-Small模型在受控的PlantVillage-Maize数据集上达到了97.8%的准确率和97.4%的F1分数，而在Field-Maize上的性能下降至86.1%的准确率和83.9%的F1分数，凸显了受控图像与真实田间图像之间的域差距。研究进一步在高斯噪声、光照变化和部分遮挡条件下评估了稳健性，并进行了计算效率和边缘部署分析。研究结果表明，轻量级且稳健的视觉特征学习对于真实农业成像条件下的实际玉米病害诊断具有重要意义。","International journal of intelligent engineering and systems","2026-10-16T00:00:00Z",{"impact":111,"substance":50,"depth":16,"authority":111,"freshness":112,"relevant":21,"comment":476},"该研究提出轻量级玉米叶病检测框架，并揭示受控数据集与田间数据之间的性能差距，方法扎实、结论有参考价值，但属细分技术论文，公共影响有限。",[478],{"name":473,"url":470},[26,27,180,192,480],"玉米病害",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[483],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":13,"version":45,"method":46,"evidence":485},{"candidates":486,"agricultural_evidence":51},[487,491,495,499],{"code":32,"score":175,"supported":51,"title":488,"abstract":489,"tags":490},[33],[29,33],[],{"code":38,"score":109,"supported":51,"title":492,"abstract":493,"tags":494},[],[192,190],[27,192],{"code":61,"score":20,"supported":51,"title":496,"abstract":497,"tags":498},[],[140,141],[26],{"code":210,"score":21,"supported":13,"title":500,"abstract":501,"tags":502},[],[],[180],[504,505],"MobileNetV3 玉米叶部病害","玉米叶片病害 边缘部署","MobileNetV3玉米叶部病害-5164","10.22266\u002Fijies2026.1130.50",{"doi":507,"openalex_id":509,"authors":510,"venue":473,"cited_by_count":87,"oa_url":470,"card":536,"direction":251,"ingested_from":162},"W7222602850",[511,514,517,519,521,524,526,528,531,533],{"name":512,"orcid":513},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":515,"orcid":516},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":518,"orcid":8},"Bhavani K",{"name":520,"orcid":8},"Sailee N. Panchbhai",{"name":522,"orcid":523},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":525,"orcid":8},"Manoj Kumar S B",{"name":527,"orcid":8},"Dharamvir",{"name":529,"orcid":530},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":532,"orcid":8},"Rani Chhagan Dalvi",{"name":534,"orcid":535},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",{"tldr":537,"method":538,"finding":539,"direction":92,"opportunity":540},"构建轻量MobileNetV3-Small框架实现玉米叶片病害分类并评估边缘部署。","MobileNetV3-Small，PlantVillage-Maize与Fie","受控数据准确率97.8%，田间降至86.1%，揭示明显域差距。","可研究跨域自适应与田间鲁棒特征学习，缩小受控与真实场景性能差距。","2026-10-17T23:30:28.248539Z"]