[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5324":3,"related-5324":91},{"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":9,"secondary_topics":31,"classification":32,"search_phrases":61,"slug":64,"view_count":65,"doi":66,"paper":67,"created_at":90},5324,"Estimation of rubber yield on Hainan Island, China using multi-source data during 2021-2025","https:\u002F\u002Fdoi.org\u002F10.1080\u002F17538947.2026.2750730","Rubber is both a strategic material and an essential industrial raw commodity, making accurate yield estimation critically important. Current remote sensing-based physical models require enhancement to converting potential yield into actual yield using limited field samples, while improving parameter applicability and estimation accuracy. Integrating DEM, Sentinel-2 imagery, and meteorological data, this study develops a multi-stage framework that couple the CASA model, SOLARFLUX, a conversion module, and a parameter calibration scheme. Calibrated and validated with field-measured data, the model enables high-resolution dynamic monitoring of dry rubber yield across Hainan Island. Validation demonstrates strong model performance (R2 > 0.95), with relative error (RE) reduced from 21.99 % to 16.62 % after refinement. The model substantially outperforms machine learning approaches. Results reveal a year-on-year decline in total rubber yield from 2021 to 2023, followed by a marked rebound during the 2023-2024. The proposed framework offers a robust and practical solution for data‑scarce regions, and its products provide valuable support for the sustainable development and ecological monitoring of Hainan’s rubber industry.","橡胶既是战略物资，也是重要的工业原料，准确的产量估算至关重要。当前基于遥感的物理模型需要改进，以利用有限的田间样本将潜在产量转化为实际产量，同时提高参数适用性和估算精度。本研究整合DEM、Sentinel-2影像和气象数据，构建了一个多阶段框架，耦合CASA模型、SOLARFLUX、转换模块和参数校准方案。经田间实测数据校准和验证，该模型实现了海南岛干胶产量的高分辨率动态监测。验证结果表明模型性能良好（R² > 0.95），经改进后相对误差（RE）从21.99%降至16.62%。该模型显著优于机器学习方法。结果显示，2021年至2023年橡胶总产量逐年下降，随后在2023—2024年明显回升。所提出的框架为数据稀缺地区提供了一种稳健且实用的解决方案，其产品为海南橡胶产业的可持续发展和生态监测提供了有力支持。",null,"International Journal of Digital Earth","2026-10-17T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"该研究融合多源遥感与气象数据构建橡胶产量估算框架，精度高、误差显著降低，对天然橡胶产业监测有实质参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","海南","遥感监测","橡胶产量","多源数据",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":36},"needs_review","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":14,"reason":60},[38,47,55],{"code":39,"score":40,"supported":41,"title":42,"abstract":43,"tags":46},"I3",7,true,[],[44,45],"遥感","remote sensing",[28],{"code":48,"score":49,"supported":41,"title":50,"abstract":51,"tags":54},"I2",6,[],[52,53],"机器学习","machine learning",[],{"code":56,"score":21,"supported":14,"title":57,"abstract":58,"tags":59},"I1",[],[],[26],"农业相关性需要复核",[62,63],"海南岛 橡胶产量 遥感估算","Sentinel-2 橡胶 产量监测","海南岛橡胶产量遥感估算-5324",0,"10.1080\u002F17538947.2026.2750730",{"doi":66,"openalex_id":68,"authors":69,"venue":10,"cited_by_count":65,"oa_url":82,"card":83,"direction":87,"ingested_from":89},"W7222825632",[70,73,75,77,79],{"name":71,"orcid":72},"Ruofan Jing","https:\u002F\u002Forcid.org\u002F0009-0005-9622-9989",{"name":74,"orcid":9},"廖静娟",{"name":76,"orcid":9},"Li Zhang",{"name":78,"orcid":9},"尧德明",{"name":80,"orcid":81},"X. Liu","https:\u002F\u002Forcid.org\u002F0000-0002-9699-338X","https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fpdf\u002F10.1080\u002F17538947.2026.2750730?needAccess=true",{"tldr":84,"method":85,"finding":86,"direction":87,"opportunity":88},"构建多源数据耦合框架，实现海南岛橡胶干胶产量的高分辨率动态估算。","融合DEM、Sentinel-2与气象数据，耦合CASA、SOLARFLUX及参","模型R2超0.95，相对误差降至16.62%，精度显著优于机器学习方法。","农业遥感与作物表型","可探索将样本稀缺下的参数迁移校准框架推广至其他热带经济作物产量估算。","openalex","2026-10-19T23:30:23.116430Z",{"total":49,"page":21,"page_size":49,"items":92},[93,153,232,324,393,486],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":98,"content":9,"source_name":99,"source_url":96,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":101,"score_detail":102,"sources":105,"tags":107,"primary_topic":111,"secondary_topics":117,"classification":118,"search_phrases":136,"slug":139,"view_count":65,"doi":140,"paper":141,"created_at":152},5565,"A Unified Survival-Based Energy Framework Linking Plant Color, Stress, and Productivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23540961","Plant coloration, expressed through leaf greenness, floral pigmentation, and fruit color intensity, reflects the integrated outcome of pigment biosynthesis, optical absorption, metabolic regulation, and energy–mass exchange with the environment. While the biochemical pathways governing the synthesis and degradation of major pigment classes—including chlorophylls, carotenoids, and anthocyanins—are well established, existing models largely interpret color expression as a localized biochemical phenomenon. Such approaches do not explicitly account for whole-plant energy balance, transpiration-driven losses, or thermodynamic constraints, limiting their ability to explain widely observed patterns of color saturation, stress-induced fading, and species-specific stability across environmental gradients. Here we develop a unified framework for plant color generation and stability that treats pigmentation as a survival-limited energetic process embedded within the broader dynamics of absorption, transport, metabolism, and entropy production. Central to the framework is a dimensionless energy survival factor, Ψ=AE\u002FTE+ε where AE represents absorbed and retained energetic and elemental resources relevant to pigment formation, TE denotes transpiration-linked, metabolic, and environmental dissipation losses, and ε captures irreducible entropy-producing degradation inherent to non-equilibrium biological systems. By construction, 0\u003CΨ\u003C1, ensuring full compliance with the second law of thermodynamics. When combined with pigment-specific optical absorption coefficients and physiological limitation functions, the framework yields a physically interpretable description of both pigment concentration and color stability. Empirical ranges for absorbed photosynthetically active radiation (≈45–70%), excitation survival (≈85–95%), and respiratory and transpiration losses (≈30–60% of assimilated resources) naturally constrain Ψ, predicting observed limits on sustained pigment accumulation without invoking biochemical inefficiency or ad hoc correction factors. The analysis demonstrates that increased light availability or enhanced biosynthetic capacity alone does not intensify coloration unless absorbed resources survive transport and loss processes. Stress-induced chlorosis, transient anthocyanin accumulation, and saturation of greenness under high irradiance emerge as direct consequences of reduced energy survival rather than impaired pigment synthesis. By explicitly separating survival from synthesis, the framework reconciles molecular-scale pigment biochemistry with whole-plant and ecosystem-scale color dynamics. This survival-based formulation provides a unified physical basis for interpreting plant color variation across species and environments and offers a scalable foundation for crop stress diagnostics, remote-sensing interpretation, and comparative plant phenotyping. More broadly, it extends survival-limited energy principles to visible plant traits, advancing plant science beyond isolated biochemical descriptions toward a systems-level understanding of how energy governs phenotypic expression.","植物色泽通过叶片绿色度、花色苷着色和果实颜色强度体现，反映了色素生物合成、光学吸收、代谢调控以及与环境的能量-物质交换的综合结果。尽管主要色素类别——包括叶绿素、类胡萝卜素和花青素——的合成与降解生化途径已较为明确，但现有模型大多将颜色表达解释为局部生化现象。此类方法未明确考虑整株植物能量平衡、蒸腾驱动的损耗或热力学约束，限制了其解释广泛观察到的颜色饱和度、胁迫诱导褪色以及跨环境梯度的物种特异性稳定性等模式的能力。本文构建了一个统一的植物颜色生成与稳定性框架，将色素沉着视为一种受生存限制的能量过程，并将其嵌入吸收、运输、代谢和熵产生的更广泛动力学之中。该框架的核心是一个无量纲能量生存因子Ψ=AE\u002FTE+ε，其中AE代表与色素形成相关的被吸收并保留的能量和元素资源，TE表示与蒸腾相关的、代谢的和环境的耗散损失，ε则捕捉非平衡生物系统固有的不可约熵产生降解。根据构建方式，0\u003CΨ\u003C1，确保完全符合热力学第二定律。当与色素特异性光学吸收系数和生理限制函数相结合时，该框架可对色素浓度和颜色稳定性给出具有物理可解释性的描述。吸收性光合有效辐射（约45–70%）、激发能存活率（约85–95%）以及呼吸和蒸腾损失（约占同化资源的30–60%）的经验范围自然约束了Ψ，从而预测出所观察到的持续色素积累限度，而无需引入生化低效性或特设校正因子。分析表明，仅增加光照可用性或增强生物合成能力并不会加深颜色，除非被吸收的资源能够在运输和损失过程中存活下来。胁迫诱导的黄化、瞬时花青素积累以及高辐照下绿色度饱和，均表现为能量生存率降低而非色素合成受损的直接后果。通过明确分离生存","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",79,{"impact":17,"substance":18,"depth":17,"authority":103,"freshness":20,"relevant":21,"comment":104},12,"提出以能量生存因子统一解释植物颜色与胁迫的物理框架，方法新颖且对遥感解译和作物诊断有潜在价值，但属预印本理论模型，尚缺田间验证。",[106],{"name":99,"url":96},[26,28,108,109,110],"植物表型","作物胁迫诊断","能量平衡",{"code":112,"slug":113,"name":114,"path":115,"parent_code":116},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":119,"locked":14,"version":34,"method":35,"evidence":120},"classified",{"candidates":121,"agricultural_evidence":41},[122,128,132],{"code":112,"score":123,"supported":41,"title":124,"abstract":125,"tags":127},3,[],[126],"萝卜",[],{"code":56,"score":21,"supported":14,"title":129,"abstract":130,"tags":131},[],[],[26],{"code":39,"score":21,"supported":14,"title":133,"abstract":134,"tags":135},[],[],[28],[137,138],"植物颜色 能量生存因子","作物胁迫 遥感诊断","植物颜色能量生存因子-5565","10.5281\u002Fzenodo.23540961",{"doi":140,"openalex_id":142,"authors":143,"venue":99,"cited_by_count":65,"oa_url":96,"card":147,"direction":87,"ingested_from":89},"W7223098474",[144],{"name":145,"orcid":146},"Mokhdum Azam Mashrafi","https:\u002F\u002Forcid.org\u002F0009-0002-1801-1130",{"tldr":148,"method":149,"finding":150,"direction":87,"opportunity":151},"提出基于生存的能量框架，用能量存活因子解释植物颜色生成与稳定性。","构建无量纲能量存活因子Ψ=AE\u002F(TE+ε)，结合色素吸收系数与生理限制函数。","颜色深浅取决于吸收资源经运输损耗后的存活率，而非单纯合成能力。","可将Ψ因子与冠层光谱\u002F表型遥感结合，发展胁迫早期诊断与生产力预测模型。","2026-10-22T11:20:31.195819Z",{"id":154,"title":155,"url":156,"summary":157,"summary_zh":158,"content":9,"source_name":99,"source_url":156,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":159,"score_detail":160,"sources":164,"tags":166,"primary_topic":170,"secondary_topics":175,"classification":176,"search_phrases":214,"slug":217,"view_count":65,"doi":218,"paper":219,"created_at":231},5563,"AI-Powered Early Detection of Crop Diseases and Pest Infestations: A New Paradigm for Plantation Risk Management","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531525","Abstract: Crop diseases and pest infestations remain persistent threats to plantation productivity, with pests estimated to destroy up to 40% of global crop production and plant diseases and invasive insects imposing substantial economic losses worldwide (Food and Agriculture Organization of the United Nations [FAO], 2019). Climate change is intensifying these risks by altering the geographic range, seasonality, and population dynamics of pathogens and pests (Gullino et al., 2021; Skendžić et al., 2021). This paper examines how artificial intelligence (AI) — including convolutional neural networks (CNNs), vision transformers (ViTs), unmanned aerial vehicle (UAV)-based multispectral and hyperspectral sensing, and Internet of Things (IoT)-enabled monitoring — can strengthen the early detection of biotic stress in plantation crops and thereby support plantation risk management. Drawing on recent peer-reviewed and industry literature, the paper synthesises evidence on detection performance, deployment modalities, and pathways for integration into enterprise risk-management systems. It proposes a conceptual framework in which AI-enabled early-warning systems operate as a continuous, spatially explicit risk-sensing layer linking agronomic observations with operational, financial, and insurance decision-making. AI can improve the timeliness, spatial precision, and consistency of surveillance; however, its risk-management value depends on field validation, representative training data, reliable infrastructure, affordable deployment, and appropriate governance. AI should therefore currently be positioned as decision support that augments, rather than replaces, agronomic expertise and ground-truthing. Keywords: artificial intelligence; plant disease detection; pest infestation; precision agriculture; plantation risk management; machine learning; remote sensing. Title: AI-Powered Early Detection of Crop Diseases and Pest Infestations: A New Paradigm for Plantation Risk Management Author: Dr. Geetha Govindan K Gopalakrishnan International Journal of Management and Commerce Innovations ISSN 2348-7585 (Online) Vol. 14, Issue 2, October 2026 - March 2027 Page No: 54-59 Research Publish Journals Website: www.researchpublish.com Published Date: 21-October-2026 DOI: https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531526 Paper Download Link (Source) https:\u002F\u002Fwww.researchpublish.com\u002Fpapers\u002Fai-powered-early-detection-of-crop-diseases-and-pest-infestations-a-new-paradigm-for-plantation-risk-management","摘要：作物病害与虫害侵染始终是种植园生产力的持续威胁，据估计，害虫每年可摧毁全球高达40%的作物产量，植物病害与入侵昆虫在全球范围内造成重大经济损失（联合国粮食及农业组织[FAO]，2019）。气候变化通过改变病原体与害虫的地理分布范围、季节性规律及种群动态，正在加剧这些风险（Gullino等，2021；Skendžić等，2021）。本文探讨人工智能（AI）——包括卷积神经网络（CNN）、视觉变换器（ViT）、基于无人机（UAV）的多光谱与高光谱遥感，以及物联网（IoT）赋能的监测技术——如何强化种植园作物生物胁迫的早期检测，从而支撑种植园风险管理。本文基于近期同行评审文献与行业文献，综合梳理了检测性能、部署模式及其融入企业风险管理系统的路径等方面的证据。文章提出一个概念框架，其中AI赋能的预警系统作为持续运行、空间显性的风险感知层，将农艺观测与运营、财务及保险决策相衔接。AI能够提升监测的及时性、空间精度与一致性；然而，其风险管理价值取决于田间验证、具有代表性的训练数据、可靠的基础设施、可负担的部署成本以及适当的治理。因此，当前应将AI定位为决策支持工具，用以增强而非替代农艺专业知识与实地核验。关键词：人工智能；植物病害检测；虫害侵染；精准农业；种植园风险管理；机器学习；遥感。题目：AI驱动的作物病害与虫害侵染早期检测：种植园风险管理的新范式。作者：Geetha Govindan K Gopalakrishnan博士。《国际管理与商业创新期刊》ISSN 2348-7585（在线）第14卷第2期，2026年10月—2027年3月，第54-59页。研究出版期刊网站：www.researchpublish.com。发布日期：2026年10月21日。DOI：https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531526。论文下载链接（来源）：https:\u002F\u002Fwww.researchpublish.com\u002Fpapers\u002Fai-powered-early-detection-of-crop-diseases-and-pest-infestations-a-new-paradigm-for-plantation-risk-ma",56,{"impact":103,"substance":161,"depth":162,"authority":49,"freshness":20,"relevant":21,"comment":163},16,13,"综述性论文，系统梳理AI与遥感在作物病虫害早期预警中的应用并提出风险管理框架，有参考价值但方法创新与数据规模有限，信源为普通出版平台。",[165],{"name":99,"url":156},[26,167,28,168,169],"农业人工智能","风险管理","病虫害监测",{"code":171,"slug":172,"name":173,"path":174,"parent_code":9},"I","digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":177,"locked":14,"version":34,"method":35,"evidence":178},"partial",{"candidates":179,"agricultural_evidence":41,"reason":213},[180,186,192,200,206],{"code":48,"score":13,"supported":41,"title":181,"abstract":182,"tags":185},[],[52,53,183,184],"artificial intelligence","decision support",[167],{"code":39,"score":13,"supported":41,"title":187,"abstract":188,"tags":191},[],[44,45,189,190],"multispectral","hyperspectral",[28],{"code":193,"score":20,"supported":41,"title":194,"abstract":195,"tags":199},"I5",[],[196,197,198],"物联网","internet of things","IoT",[],{"code":56,"score":40,"supported":41,"title":201,"abstract":202,"tags":205},[],[203,204],"精准农业","precision agriculture",[26],{"code":207,"score":49,"supported":41,"title":208,"abstract":209,"tags":212},"H7",[],[210,211],"气候变化","climate change",[],"一级领域明确，二级方向需要细分",[215,216],"AI 作物病害 早期检测","无人机 多光谱 病虫害监测","AI作物病害早期检测-5563","10.5281\u002Fzenodo.23531525",{"doi":218,"openalex_id":220,"authors":221,"venue":99,"cited_by_count":65,"oa_url":156,"card":224,"direction":230,"ingested_from":89},"W7223085400",[222],{"name":223,"orcid":9},"Dr. Geetha Govindan K Gopalakrishnan",{"tldr":225,"method":226,"finding":227,"direction":228,"opportunity":229},"综述AI（CNN、ViT、无人机遥感、物联网）用于作物病虫害早期检测并融入种植园风险管理。","文献综述，整合CNN、ViT、无人机多\u002F高光谱与IoT监测的检测性能与部署方式。","AI可提升监测及时性与空间精度，但价值取决于田间验证、代表性数据与治理，应作决策支持而非替代专家。","农业人工智能与决策模型","可将AI预警层与保险、金融风控系统对接，研究跨域数据融合与可解释风险定价的空白。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:24.428080Z",{"id":233,"title":234,"url":235,"summary":236,"summary_zh":237,"content":9,"source_name":238,"source_url":235,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":239,"score_detail":240,"sources":244,"tags":246,"primary_topic":249,"secondary_topics":255,"classification":266,"search_phrases":301,"slug":304,"view_count":65,"doi":305,"paper":306,"created_at":323},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy",77,{"impact":161,"substance":241,"depth":242,"authority":162,"freshness":13,"relevant":21,"comment":243},21,17,"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[245],{"name":238,"url":235},[26,52,28,247,248],"土壤墒情","冬小麦",{"code":250,"slug":251,"name":252,"path":253,"parent_code":254},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[256,262],{"code":257,"slug":258,"name":259,"path":260,"parent_code":261},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":48,"slug":263,"name":264,"path":265,"parent_code":171},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":119,"locked":14,"version":34,"method":35,"evidence":267},{"candidates":268,"agricultural_evidence":41},[269,275,281,285,289,296],{"code":250,"score":270,"supported":41,"title":271,"abstract":273,"tags":274},26,[272,251],"winter wheat",[252,272,251],[248],{"code":257,"score":276,"supported":41,"title":277,"abstract":278,"tags":280},15,[258],[279,258],"土壤",[247],{"code":48,"score":276,"supported":41,"title":282,"abstract":283,"tags":284},[53],[52,53],[52],{"code":39,"score":13,"supported":41,"title":286,"abstract":287,"tags":288},[],[44,45,189],[28],{"code":290,"score":49,"supported":41,"title":291,"abstract":292,"tags":295},"H3",[],[293,294],"灌溉","irrigation",[],{"code":56,"score":297,"supported":41,"title":298,"abstract":299,"tags":300},4,[],[26],[26],[302,303],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":305,"openalex_id":307,"authors":308,"venue":238,"cited_by_count":65,"oa_url":235,"card":318,"direction":230,"ingested_from":89},"W7223156204",[309,312,314,316],{"name":310,"orcid":311},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":313,"orcid":9},"Yi Zhang",{"name":315,"orcid":9},"WEI Lei",{"name":317,"orcid":9},"Chengcai Zhang",{"tldr":319,"method":320,"finding":321,"direction":87,"opportunity":322},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","2026-10-22T11:20:18.887301Z",{"id":325,"title":326,"url":327,"summary":328,"summary_zh":329,"content":9,"source_name":330,"source_url":327,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":239,"score_detail":331,"sources":334,"tags":336,"primary_topic":339,"secondary_topics":340,"classification":345,"search_phrases":364,"slug":367,"view_count":65,"doi":368,"paper":369,"created_at":392},5367,"Integration of multi-source UAV remote sensing features and derived features for winter wheat aboveground biomass estimation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102656","Accurate estimation of winter wheat ( Triticum aestivum L.) aboveground biomass (AGB) is important for crop growth monitoring and field management. However, unmanned aerial vehicle (UAV)-based AGB estimation remains challenging due to variations in canopy conditions across growth stages, and different remote sensing features can capture complementary characteristics related to AGB estimation. This study integrated multi-source UAV-derived features, including vegetation indices (VIs), texture features (TFs), light detection and ranging (LiDAR)-derived features, and derived features (DFs) generated from the original feature sets, with four machine learning algorithms for winter wheat AGB estimation. Results showed that TFs provided better prediction performance than other single-source feature sets. Compared with single-source feature sets, the integration of VIs, TFs, LiDAR-derived features, and DFs further improved AGB estimation, and the random forest (RF) model achieved the best performance among the evaluated models (R² = 0.923, RMSE = 1.731 Mg ha⁻¹). Incremental R² analysis based on a stage-only baseline model showed that the RF model explained additional variation in AGB beyond growth-stage information, with an incremental R² of 0.479. Stage-specific evaluation indicated that model performance varied among growth stages, with the highest accuracy observed at the booting stage (R² = 0.632, RMSE = 1.425 Mg ha⁻¹). Feature contribution analysis based on the full-feature fusion model using all growth-stage data identified canopy coverage and several DFs as important predictors, while stage-specific analyses showed differences in dominant predictors across growth stages. The integration of multi-source UAV-derived features and DFs with machine learning provides an effective approach for winter wheat AGB estimation, while model performance remains strongly dependent on growth stage.","准确估算冬小麦（Triticum aestivum L.）地上生物量（aboveground biomass, AGB）对作物生长监测和田间管理具有重要意义。然而，由于不同生育期冠层条件存在差异，且不同遥感特征能够捕捉与AGB估算相关的互补信息，基于无人机（unmanned aerial vehicle, UAV）的AGB估算仍面临挑战。本研究将多源无人机衍生特征，包括植被指数（vegetation indices, VIs）、纹理特征（texture features, TFs）、激光雷达（light detection and ranging, LiDAR）衍生特征以及由原始特征集生成的衍生特征（derived features, DFs），与四种机器学习算法相结合，用于冬小麦AGB估算。结果表明，TFs的预测性能优于其他单一来源特征集。与单一来源特征集相比，融合VIs、TFs、LiDAR衍生特征和DFs进一步提高了AGB估算精度，其中随机森林（random forest, RF）模型在所评估的模型中表现最佳（R² = 0.923，RMSE = 1.731 Mg ha⁻¹）。基于仅含生育期信息的基线模型进行的增量R²分析表明，RF模型在生育期信息之外解释了AGB的额外变异，增量R²为0.479。分生育期评估表明，模型性能在不同生育期之间存在差异，其中在孕穗期观察到最高精度（R² = 0.632，RMSE = 1.425 Mg ha⁻¹）。基于使用全部生育期数据的全特征融合模型进行的特征贡献分析识别出冠层覆盖度和若干DFs为重要预测因子，而分生育期分析则表明不同生育期的主导预测因子存在差异。将多源无人机衍生特征和DFs与机器学习相结合，为冬小麦AGB估算提供了一种有效方法，但模型性能仍强烈依赖于生育期。","Smart Agricultural Technology",{"impact":161,"substance":18,"depth":17,"authority":162,"freshness":332,"relevant":21,"comment":333},8,"该研究融合无人机多源遥感特征与衍生特征，用随机森林估算冬小麦地上生物量，方法新颖、结论可靠，对作物长势监测有参考价值。",[335],{"name":330,"url":327},[26,337,28,248,338],"无人机","生物量估算",{"code":250,"slug":251,"name":252,"path":253,"parent_code":254},[341],{"code":39,"slug":342,"name":343,"path":344,"parent_code":171},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":119,"locked":14,"version":34,"method":35,"evidence":346},{"candidates":347,"agricultural_evidence":41},[348,352,356,360],{"code":250,"score":270,"supported":41,"title":349,"abstract":350,"tags":351},[272,251],[252,272,251],[248],{"code":39,"score":161,"supported":41,"title":353,"abstract":354,"tags":355},[45],[44,45],[338,28],{"code":48,"score":49,"supported":41,"title":357,"abstract":358,"tags":359},[],[52,53],[],{"code":56,"score":21,"supported":14,"title":361,"abstract":362,"tags":363},[],[],[26],[365,366],"无人机 多源遥感 冬小麦 生物量","冬小麦 地上生物量 随机森林","无人机多源遥感冬小麦生物量-5367","10.1016\u002Fj.atech.2026.102656",{"doi":368,"openalex_id":370,"authors":371,"venue":330,"cited_by_count":65,"oa_url":327,"card":387,"direction":87,"ingested_from":89},"W7222806066",[372,374,376,378,381,383,385],{"name":373,"orcid":9},"Guangtao Wang",{"name":375,"orcid":9},"Sumei Yao",{"name":377,"orcid":9},"Yanzheng Xie",{"name":379,"orcid":380},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":382,"orcid":9},"Xiangdong Chen",{"name":384,"orcid":9},"Yuhao Zhang",{"name":386,"orcid":9},"Lina Jiang",{"tldr":388,"method":389,"finding":390,"direction":87,"opportunity":391},"融合无人机多源遥感特征与衍生特征，用机器学习估算冬小麦地上生物量。","无人机植被指数、纹理、LiDAR特征及衍生特征结合四种机器学习算法建模。","多源特征融合优于单一特征，随机森林最优（R²=0.923），精度随生育期变化。","可探索生育期自适应建模与特征选择，提升跨期生物量估算的稳健性与可迁移性。","2026-10-20T23:30:03.106267Z",{"id":394,"title":395,"url":396,"summary":397,"summary_zh":398,"content":9,"source_name":399,"source_url":396,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":400,"score_detail":401,"sources":403,"tags":405,"primary_topic":409,"secondary_topics":415,"classification":416,"search_phrases":467,"slug":470,"view_count":471,"doi":472,"paper":473,"created_at":485},5235,"Role of Smart Fertilization in Modern Agriculture","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fijpss\u002F2026\u002Fv38i106378","Global food demand is increasing rapidly owing to population growth, placing considerable pressure on agricultural systems to enhance productivity under constraints on natural resources. Although conventional fertiliser use has contributed significantly to improved yields, its excessive and imbalanced application has resulted in soil degradation, nutrient leaching, groundwater contamination, and increased emissions of nitrous oxide (N₂O), thereby reducing nutrient use efficiency (NUE). In this context, smart fertilisation has emerged as a science-driven nutrient management strategy that emphasises the application of the right nutrient source at the right rate, time and place (4R principle), supported by advanced tools such as soil and plant sensors, remote sensing, geographic information systems, and decision-support platforms. Key components include controlled-release fertilisers, nano-fertilisers, bio-formulations, fertigation systems, variable rate technology (VRT), and unmanned aerial vehicle (UAV)-based crop monitoring. Evidence from multi-location field studies across diverse agro-climatic regions of India and other countries indicates that smart fertilisation can enhance nutrient use efficiency by 50–80%, reduce fertiliser input by 19–30%, and improve crop yields by 22–30% in major crops such as rice, wheat, maize and pulses. With the global fertiliser market exceeding USD 200 billion, the adoption of precision nutrient management technologies is gaining momentum. Overall, smart fertilisation offers a sustainable intensification pathway by improving productivity while simultaneously minimising environmental externalities. However, challenges related to technology accessibility, cost, and farmer adoption remain critical constraints that require policy and institutional support.","由于人口增长，全球粮食需求迅速上升，给农业系统带来了巨大压力，要求在自然资源约束下提高生产力。尽管常规施肥对提高产量作出了显著贡献，但过量和不平衡施肥已导致土壤退化、养分淋失、地下水污染以及氧化亚氮（N₂O）排放增加，从而降低了养分利用效率（NUE）。在此背景下，智能施肥作为一种以科学为驱动的养分管理策略应运而生，强调在正确的时间、正确的地点以正确的用量施用正确的养分来源（4R原则），并借助土壤与植物传感器、遥感、地理信息系统和决策支持平台等先进工具加以支撑。其关键组成部分包括控释肥料、纳米肥料、生物制剂、水肥一体化系统、变量施肥技术（VRT）以及基于无人机（UAV）的作物监测。来自印度及其他国家不同农业气候区多点田间研究的数据表明，智能施肥可使养分利用效率提高50%–80%，减少肥料投入19%–30%，并使水稻、小麦、玉米和豆类等主要作物增产22%–30%。随着全球肥料市场规模超过2000亿美元，精准养分管理技术的采用正在加速推进。总体而言，智能施肥通过提高生产力同时最大限度减少环境负外部性，提供了一条可持续集约化路径。然而，技术可及性、成本和农民采用等方面的挑战仍是关键制约因素，需要政策和制度支持。","International Journal of Plant & Soil Science",83,{"impact":18,"substance":18,"depth":17,"authority":162,"freshness":332,"relevant":21,"comment":402},"系统综述智能施肥技术体系与多国田间数据，量化增产节肥效果，对智慧农业与绿色投入品方向有参考价值，但属综述性论文且非国内案例，时效与权威度中等。",[404],{"name":399,"url":396},[26,337,406,407,28,408],"精准施肥","变量施肥","养分利用效率",{"code":410,"slug":411,"name":412,"path":413,"parent_code":414},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",[],{"status":119,"locked":14,"version":34,"method":35,"evidence":417},{"candidates":418,"agricultural_evidence":41},[419,430,434,441,445,452,456,463],{"code":410,"score":420,"supported":41,"title":421,"abstract":423,"tags":429},20,[422],"fertilization",[424,425,426,427,428],"施肥","肥料","水肥一体化","养分管理","fertigation",[408,407,406],{"code":39,"score":40,"supported":41,"title":431,"abstract":432,"tags":433},[],[44,45],[28],{"code":435,"score":49,"supported":41,"title":436,"abstract":437,"tags":440},"A1",[],[438,439],"水稻","rice",[],{"code":250,"score":49,"supported":41,"title":442,"abstract":443,"tags":444},[],[252,251],[],{"code":446,"score":49,"supported":41,"title":447,"abstract":448,"tags":451},"A3",[],[449,450],"玉米","maize",[],{"code":257,"score":49,"supported":41,"title":453,"abstract":454,"tags":455},[],[279,258],[],{"code":457,"score":49,"supported":41,"title":458,"abstract":459,"tags":462},"I4",[],[460,461],"地理信息","geographic information",[],{"code":56,"score":21,"supported":14,"title":464,"abstract":465,"tags":466},[],[],[26],[468,469],"智能施肥 4R原则","变量施肥技术 无人机","智能施肥4R原则-5235",2,"10.9734\u002Fijpss\u002F2026\u002Fv38i106378",{"doi":472,"openalex_id":474,"authors":475,"venue":399,"cited_by_count":65,"oa_url":396,"card":480,"direction":230,"ingested_from":89},"W7222838957",[476,478],{"name":477,"orcid":9},"S. T. Panusha",{"name":479,"orcid":9},"T. M. Soumya",{"tldr":481,"method":482,"finding":483,"direction":230,"opportunity":484},"综述智能施肥（4R原则+传感器\u002F遥感\u002FVRT）提升养分利用效率与产量的机制与证据。","整合多地点田间试验证据，梳理传感器、遥感、GIS、控释\u002F纳米肥与无人机监测等技术","智能施肥可提高养分利用效率50–80%、减施化肥19–30%、增产22–30%，但受成本与农户采纳制","可研究低成本传感器+无人机变量施肥在小农户场景的适配与采纳机制，及减氮减排的量化评估。","2026-10-18T23:30:07.850055Z",{"id":487,"title":488,"url":489,"summary":490,"summary_zh":491,"content":9,"source_name":492,"source_url":489,"published_at":493,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":494,"score_detail":495,"sources":497,"tags":499,"primary_topic":502,"secondary_topics":503,"classification":504,"search_phrases":525,"slug":528,"view_count":21,"doi":529,"paper":530,"created_at":555},5162,"Detection of Eulecanium giganteum Infestation in Jujube Orchards Based on UAV Multispectral Remote Sensing","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fhorticulturae12101286","The application of remote sensing technology to monitor agricultural pests and diseases provides an effective approach for rapid and non-destructive assessment of crop health. This study evaluated a UAV multispectral remote sensing framework integrating vegetation indices and SPAD information for assessing Eulecanium giganteum infestation in jujube orchards. Initially, 24 vegetation indices were extracted from canopy multispectral imagery, and Pearson correlation analysis was used for feature screening, resulting in a refined subset of 19 vegetation indices. Seven machine learning algorithms were evaluated during model development, with Grid Search combined with tree-level grouped 7-fold cross-validation for hyperparameter selection. Vegetation indices were used as predictor variables, while SPAD value and infestation severity were treated as response variables in the regression and classification tasks, respectively. During internal model development, the CatBoost-19opt model achieved an R2 of 0.81 and an RMSE of 1.84 for SPAD estimation. On the independent test set consisting of 58 jujube trees, the previously selected model achieved an R2 of 0.84 and an RMSE of 1.56. During internal model development, incorporating measured SPAD values improved pest classification performance, with XGBoost-19sopt achieving an OA of 0.89 and a Kappa coefficient of 0.84. On the independent test set, the measured-SPAD configuration achieved an OA of 0.88, whereas both the VI-only and VI combined with predicted-SPAD configurations achieved an OA of 0.71. Thus, incorporating predicted SPAD did not improve overall classification accuracy relative to using vegetation indices alone. Further model optimization and additional validation across different orchards, growing seasons, and phenological stages are required before the approach can be considered for operational large-scale monitoring.","遥感技术在农业病虫害监测中的应用，为作物健康的快速、无损评估提供了有效途径。本研究评估了一种集成植被指数与SPAD信息的无人机多光谱遥感框架，用于评估枣园中枣球蜡蚧（Eulecanium giganteum）的危害情况。首先，从冠层多光谱影像中提取了24个植被指数，并采用Pearson相关分析进行特征筛选，最终得到包含19个植被指数的精简子集。在模型开发过程中评估了7种机器学习算法，采用网格搜索结合树级分组7折交叉验证进行超参数选择。以植被指数作为预测变量，分别将SPAD值和危害程度作为回归任务和分类任务的响应变量。在内部模型开发中，CatBoost-19opt模型在SPAD估算中取得了R²为0.81、RMSE为1.84的结果。在由58株枣树构成的独立测试集上，先前选定的模型取得了R²为0.84、RMSE为1.56的结果。在内部模型开发中，引入实测SPAD值提升了病虫害分类性能，XGBoost-19sopt取得了OA为0.89、Kappa系数为0.84的结果。在独立测试集上，实测SPAD配置取得了OA为0.88的结果，而仅使用植被指数以及植被指数结合预测SPAD的配置均取得了OA为0.71的结果。因此，相对于仅使用植被指数，引入预测SPAD并未提升整体分类精度。在该方法可被视为适用于业务化大规模监测之前，仍需进一步的模型优化，并在不同枣园、生长季和物候期开展额外验证。","Horticulturae","2026-10-16T00:00:00Z",73,{"impact":103,"substance":18,"depth":242,"authority":162,"freshness":20,"relevant":21,"comment":496},"方法扎实、数据完整的单果园研究，但作者自述尚未达到大规模业务化监测水平，属细分领域进展，可入精选但非重大突破。",[498],{"name":492,"url":489},[26,337,28,500,501],"病虫害防治","枣树",{"code":39,"slug":342,"name":343,"path":344,"parent_code":171},[],{"status":119,"locked":14,"version":34,"method":35,"evidence":505},{"candidates":506,"agricultural_evidence":41},[507,512,516,521],{"code":39,"score":270,"supported":41,"title":508,"abstract":509,"tags":511},[45,189],[44,510,45,189],"无人机多光谱",[28],{"code":48,"score":49,"supported":41,"title":513,"abstract":514,"tags":515},[],[52,53],[],{"code":517,"score":123,"supported":41,"title":518,"abstract":519,"tags":520},"B2",[],[501],[],{"code":56,"score":21,"supported":14,"title":522,"abstract":523,"tags":524},[],[],[26],[526,527],"无人机 多光谱 枣园 虫害","Eulecanium giganteum 遥感 监测","无人机多光谱枣园虫害-5162","10.3390\u002Fhorticulturae12101286",{"doi":529,"openalex_id":531,"authors":532,"venue":492,"cited_by_count":65,"oa_url":489,"card":550,"direction":87,"ingested_from":89},"W7222575708",[533,535,537,540,543,545,547],{"name":534,"orcid":9},"Yueteng Chao",{"name":536,"orcid":9},"Yulong Wang",{"name":538,"orcid":539},"Zhuoyang Xu","https:\u002F\u002Forcid.org\u002F0000-0003-0344-3424",{"name":541,"orcid":542},"Ruohong He","https:\u002F\u002Forcid.org\u002F0009-0000-7404-9112",{"name":544,"orcid":9},"Rina Yangdao",{"name":546,"orcid":9},"Hongqiang Dong",{"name":548,"orcid":549},"Ping Li","https:\u002F\u002Forcid.org\u002F0009-0007-4465-1023",{"tldr":551,"method":552,"finding":553,"direction":87,"opportunity":554},"用无人机多光谱植被指数与SPAD估算枣园大球蚧发生程度。","24个植被指数筛选19个，7种机器学习+网格搜索与分组交叉验证。","CatBoost估SPAD R²达0.84；实测SPAD提升分类，预测SPAD无增益。","可探索预测SPAD失效原因及跨果园、物候期泛化与多源数据融合监测。","2026-10-17T23:30:28.025984Z"]