[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-469":3,"related-469":68},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":62,"slug":65,"view_count":52,"doi":66,"paper":8,"created_at":67},469,"Portable Hyperspectral Imaging Combined with Interpretable PLS-DA-SHAP for Geographical Origin Traceability and Authenticity Discrimination of Poria cocos (Fushen)","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract","本文提出便携式高光谱成像结合可解释PLS-DA-SHAP方法,用于茯苓(Fushen,Poria cocos)的地理来源溯源与真实性鉴别。研究展示了如何将机器学习与SHAP可解释性相结合,应用于中药材产地溯源。原文标题:Portable hyperspectral imaging combined with interpretable PLS-DA-SHAP for geographical origin traceability and authenticity discrimination of Poria cocos (Schw.) Wolf (Fushen),作者:Xing W、Zhang Y、Wei X、Nie S、Cheng X、Cai M、Yang Q、Wang Y,发表于Frontiers in Sustainable Food Systems 2026年第10卷doi:10.3389\u002Ffsufs.2026.1891249,2026年7月15日接收,8月7日发表。本研究为基于光谱成像的农产品\u002F中药材产地溯源提供了可解释AI方法范式。",null,"## Abstract\n\n**Introduction:**\n\n_Poria cocos_ (Schw.) Wolf (_Fushen_) is a fungus that is edible and has medicinal value. The quality of the fungus varies with geographical origin and its commercial substitution by Chuanshen.\n\n**Methods:**\n\nThis study developed a rapid, non-destructive approach for the geographical origin traceability and authenticity discrimination of _Fushen_ using portable hyperspectral imaging (HSI; 400–1,000 nm) combined with interpretable machine learning. The discriminatory potential of four _Fushen_ regions was assessed. Partial least-squares discriminant analysis (PLS-DA), support vector machine, and multilayer perceptron were compared, while the successive projections algorithm and SHapley Additive exPlanations (SHAP) algorithms were applied for feature wavelength selection and model interpretation.\n\n**Results:**\n\nThe PLS-DA-SHAP strategy exhibited the best overall performance. After SHAP-based wavelength selection, PLS-DA combined with first derivative (D1) preprocessing achieved 92.33% accuracy for geographical origin traceability, whereas PLS-DA using raw spectra achieved 100% accuracy for authenticity discrimination. The outer layer of white _Fushen_ (M2) provided the highest regional discrimination accuracy of 100%. Wavelengths of 893 nm, 896 nm, and 881 and 423 nm were identified as key contributors to geographical origin traceability, authenticity discrimination using the All dataset, and authenticity discrimination using M2, respectively.\n\n**Discussion:**\n\nThese findings can support the use of portable HSI as a practical tool for on-site quality assessment of _Fushen_ and related edible and medicinal materials.\n\n## 1 Introduction\n\n_Poria cocos_ (Schw.) Wolf (_Fushen_) is a saprotrophic fungus of the Polyporaceae family. It commonly parasitizes the roots of Pinus species and forms dense white sclerotia that naturally enclose the growing portions of pine roots. This material is commonly referred to as _Fushen_ in China (). _Fushen_ is distributed mainly in Asia, America, Oceania, and parts of Africa, with China serving as the major cultivator (). _Fushen_ is commonly regarded as one of the representative species with both medicinal and edible properties. In addition to recording its therapeutic properties, ancient medical texts have emphasized its nutritional value and suitability for long-term consumption (). Therefore, _Fushen_ has a long history of use in the food industry, with a wide range of products such as porridge, pastries, herbal teas, and tonic soups, which are well accepted by consumers and reflect its edible value (). Modern studies have shown that _Fushen_ is rich in bioactive constituents, including polysaccharides and triterpenoids, and exhibits sleep-improving and anxiolytic effects, indicating its promising potential as a functional food ingredient (; ).\n\n_Fushen_ has a long cultivation history in China and is widely produced in Anhui, Yunnan, Hubei, and Hunan. Its quality is affected by production area conditions (e.g., soil, climate, and cultivation practices), which may lead to variations in key functional components (; ). In addition, counterfeit _Fushen_ products that closely resemble genuine products are present in the market and are difficult to identify visually. These counterfeit products, commonly known as Chuanshen (CS), are produced by artificially inserting pine roots into the sclerotium during the later growth stage of _Poria cocos_ (PC) (; ). In genuine _Fushen_, the lignocellulose of pine roots undergoes biological transformation with the mycelium of PC during development of the sclerotia, resulting in changes in the active components. In CS, the symbiotic period between pine roots and PC is relatively short, contributing to the marked compositional differences from genuine _Fushen_ (). Previous studies have also shown that _Fushen_ blocks can be divided into four regions, namely _Fushen_ wood, the inner layer of white _Fushen_, the outer layer of white _Fushen_, and skin _Fushen_, each with distinct chemical compositions (; ). However, whether genuine and counterfeit products differ across these regions and whether such regional differences can be effectively used for counterfeit discrimination remain unclear. Therefore, a reliable detection method is required to identify the geographical origin, authenticity, and regional characteristics of _Fushen_, thereby supporting product quality control.\n\nTraditional food detection methods mainly rely on analytical techniques such as liquid chromatography–mass spectrometry (; ), gas chromatography–mass spectrometry (), and ultra-high-performance liquid chromatography–quadrupole time-of-flight mass spectrometry (; ; ). Although these methods provide high analytical accuracy, they require complex procedures, long analysis times, high costs, and destructive pretreatment, which limit their suitability for rapid market screening (; ). As a rapid analytical technique, near-infrared spectroscopy still faces limitations related to low sensitivity, dependence on chemometric models, and insufficient model interpretability ().\n\nHyperspectral imaging (HSI) integrates spectral analysis with imaging acquisition and has become an effective, rapid, and non-destructive detection technique. Without requiring complex chemical pretreatment, HSI can simultaneously capture the spatial and spectral characteristics of samples. Moreover, the integration of HSI with machine learning algorithms has further improved both accuracy and efficiency, and this combined approach has now been widely adopted in food safety applications (; ; ). However, conventional HSI systems are generally bulky and require controlled operating environments, limiting their suitability for portable deployment and on-site detection. Conversely, portable spectral instruments are compact and more suitable for field-based applications. In recent years, devices such as SPECIM IQ have been successfully used for rapid and non-destructive on-site analysis, including saffron origin identification () and quantitative detection of rice adulteration (), demonstrating their practical value in food quality evaluation. Nevertheless, portable hyperspectral datasets are affected by high dimensionality, limited computational efficiency, and insufficient model interpretability. To address these constraints, the successive projections algorithm (SPA) and SHapley Additive exPlanations (SHAP) can be employed for feature wavelength selection. By removing redundant variables and retaining informative wavelengths, these methods enable dimensionality reduction and improve model efficiency. In addition, SHAP can be integrated with different machine learning models to quantify the marginal contribution of each wavelength and generate global importance rankings, thereby enhancing the interpretability of model decisions (; ).\n\nOn this basis, portable HSI combined with interpretable machine learning was used in this study to support the geographical origin traceability and authenticity discrimination of _Fushen_, with the aim of providing a technical reference for rapid and non-destructive detection of functional food materials. The specific objectives were as follows: (1) to acquire HSI data from _Fushen_ samples collected from different geographical origins, as well as from genuine and counterfeit products, and to divide the genuine and counterfeit samples into four regions; (2) to compare the classification performance of three algorithms, including support vector machine (SVM), partial least-squares discriminant analysis (PLS-DA), and multilayer perceptron (MLP), under six preprocessing methods; and (3) to use SPA and SHAP for characteristic wavelength selection, dimensionality reduction, classification efficiency improvement, and interpretation of the relationship between wavelengths and samples. The methodological workflow is illustrated in [Figure 1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#fig1). For abbreviations see [Supplementary Table S1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#sec24).\n\nFigure 1\n\n## 2 Materials and methods\n\n### 2.1 Sample collection\n\n_Fushen_ samples were collected from five authentic production areas in China, namely Jinzhai, Anhui (AJ); Yuexi, Anhui (AY); Hubei (HB); Hunan (HN); and Yunnan (YN). Four independent biological replicates were obtained from each production area, with each replicate derived from different farmer fields. Five blocks were randomly selected from each replicate, yielding 20 blocks per production area and a total of 100 authentic _Fushen_ blocks across the five areas. The counterfeit CS samples were collected from Jinzhai County, Anhui Province, China, with six independent biological replicates and five blocks randomly selected from each replicate, totaling 30 CS blocks. All samples were authenticated as genuine _Fushen_ or counterfeit CS by Associate Professor Yang Qingshan from Anhui University of Chinese Medicine. After collection, the outer skin was removed, and _Fushen_ blocks of similar size were selected for subsequent analysis. Representative sample images are shown in [Figure 1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#fig1), Step 1 Samples collection, and detailed sample information is provided in [Supplementary Table S2](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#sec24).\n\n### 2.2 Data collection using the HSI system\n\nHyperspectral images were acquired using a portable hyperspectral camera (SPECIM IQ, SPECIM Spectral Imaging Ltd., Oulu, Finland) by scanning one surface of each _Fushen_ block ([Figure 1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#fig1), Step 2 Hyperspectral image acquisition). The camera was fitted with a visible–near-infrared lens covering 400–1,000 nm and provided 204 bands, a spatial resolution of 512 × 512 pixels, a spectral resolution of 7 nm, a sampling interval of approximately 2.94 nm, and band-division capability (). A white reference plate with 90% reflectance was used for reflectance correction during image acquisition.\n\nImages were captured while the samples were stationary. To reduce background interference, the samples and white reference plate were placed on a black background, as described in the literature (). The SPECIM IQ instrument was mounted on a tripod, and the lens was positioned vertically approximately 40 cm above the samples. Because all images were collected outdoors under sunlight, the simultaneous mode was adopted to minimize the effect of illumination variation, following previous research (). The integration and recording times were set to 2 ms and 32 s, respectively, to ensure consistent imaging conditions during HSI data collection. Pixel-level reflectance correction was performed using the black-white reference correction formula reported in the literature (). The corrected hyperspectral images were transferred to a computer for subsequent region of interest (ROI) extraction.\n\n### 2.3 Spectral data extraction from ROIs\n\nThe ROIs were manually delineated using Insight 1.3.1 software provided by the instrument manufacturer for subsequent analysis. For geographical origin traceability, ROIs were extracted from the complete regions of samples from five geographical origins (20 blocks per area, 100 blocks in total), with 15 ROIs per block, yielding 300 ROIs per area and 1,500 ROIs overall. For authenticity discrimination (All), ROIs were extracted from the complete regions of 30 authentic and 30 counterfeit CS blocks, with 10 ROIs per block, resulting in 300 ROIs for authentic samples and 300 for counterfeit samples, totaling 600 ROIs.\n\nGiven the differences in bioactive components among the four regions of _Fushen_, and following previous studies and morphological characteristics (), the authentic and counterfeit CS samples were divided from the inside outward into four regions: _Fushen_ wood (the internal host pine root, abbreviated as FSM), the inner layer of white _Fushen_ (the white sclerotial part near the host pine root, abbreviated as M1), the outer layer of white _Fushen_ (the white part near the outer region, abbreviated as M2), and the peripheral sclerotium (the outermost sclerotial part after peeling, abbreviated as M3), since all samples had their outer skin removed at collection. The division is illustrated in [Supplementary Figure S1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#sec24) and [Figure 1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#fig1), Step 2 Hyperspectral image acquisition. For each region, 10 ROIs were extracted per block from 30 authentic and 30 counterfeit CS blocks, yielding 300 ROIs per region for each category. Across the four regions, a total of 1,200 ROIs from authentic samples and 1,200 from counterfeit samples were obtained, amounting to 2,400 ROIs in total. These data were used to evaluate the spectral differences and the discriminatory ability of each region in authenticity discrimination.\n\nBased on the above strategy, the mean reflectance within each ROI was extracted as spectral information. Subsequently, the three independent datasets were each randomly divided into training and test sets at an 8:2 ratio.\n\n### 2.4 Spectral preprocessing\n\nSeveral preprocessing methods were applied to the raw spectral data to reduce the background noise and physical interference generated during HSI acquisition. These methods included multiplicative scatter correction (MSC), first derivative (D1), second derivative (D2), standard normal variate (SNV), Savitzky–Golay smoothing (SG), and wavelet transform (Wave).\n\n### 2.5 Machine learning classification model\n\nSVM is a supervised learning algorithm with a strong generalization ability. It separates classes by constructing an optimal hyperplane in the feature space, thereby maximizing the margin between categories. For linearly inseparable samples, kernel functions are used to map the original data into a high-dimensional feature space in which linear separation can be achieved (; ). The model classification performance is mainly controlled by the penalty factor and the kernel parameter. In this study, the model parameters were optimized using a grid search combined with 10-fold cross-validation. The candidate values for the penalty factor were 5, 10, 15, 50, and 100, whereas the kernel parameter was searched over 1e-7, 1e-6, 1e-5, 1e-4, 1e-3, 1e-2, 1e-1, and 1. Three kernel functions, namely linear, polynomial, and radial basis function kernels, were systematically compared to determine the optimal model configuration and improve classification performance.\n\nPLS-DA is a supervised pattern recognition method derived from partial least-squares regression. By extracting latent variables with maximum covariance with class labels, PLS-DA enables dimensionality reduction and classification to be achieved simultaneously while balancing the retention of discriminant information with the mitigation of high-dimensional effects (). Its classification performance depends on the selected number of PLS latent components, defined as n_components. In this study, the number of PLS latent components was searched from 1 to 21, and the optimal value was determined using 10-fold cross-validation.\n\nMLP is an artificial neural network with a relatively simple architecture that can learn from sample data and effectively represent classification features (). In this study, the MLP consisted of two hidden layers, with the number of neurons in each layer ranging from 50 to 500. The optimal parameters were determined by grid search. The rectified linear unit function was used as the activation function for hidden layers. The limited-memory Broyden–Fletcher–Goldfarb–Shanno algorithm was used for optimization. The regularization coefficient was set to 0.0001, and the maximum number of iterations was set to 10,000 to ensure sufficient model convergence.\n\n### 2.6 Feature wavelength selection algorithm\n\nTo address the high dimensionality, collinearity, and redundancy of hyperspectral data, SPA and SHAP were used to extract characteristic bands. Through dimensionality reduction and the removal of irrelevant variables, these methods were applied to simplify the models and improve prediction performance.\n\nSPA is based on vector-space projection. It identifies wavelength subsets with low collinearity and high information content by sequentially projecting wavelength vectors onto the orthogonal complement space of the remaining vectors. The optimal wavelength combination was selected according to the root mean square error of cross-validation, thereby achieving spectral dimensionality reduction (; ). To improve the stability and reliability of the selected wavelengths, 10-fold cross-validation was applied, and automatic scaling was used in the preprocessing parameters.\n\nSHAP is an interpretability method derived from Shapley value theory in cooperative game theory (). Each input feature is regarded as a participant in a cooperative game, and its Shapley value is calculated from the weighted average of its marginal contributions across all possible feature subset combinations. The resulting value quantifies the contribution of each feature to the model prediction. The specific calculation formula is provided in .\n\n### 2.7 Model evaluation and software\n\nA confusion matrix was used for model evaluation, with accuracy, precision, recall, and F1-score as the main metrics for assessing classification performance. The corresponding calculation formula is provided in . All analyses were conducted on a Windows 11 platform equipped with an AMD Ryzen 9 9955HX CPU, 32 GB of memory, and an NVIDIA RTX 5060 Laptop GPU. Data processing and model construction were performed using Python 3.12 (64-bit) and PyCharm Community 2024.1. All scripts were developed by our research group.\n\n## 3 Results\n\n### 3.1 Spectral curve analysis of samples\n\nThe mean raw spectral curves of _Fushen_ samples from different geographical origins are presented in [Figure 2A](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#fig2). Across all origins, the reflectance increased over the 400–900 nm range, reached a maximum at approximately 850–900 nm, and then declined gradually between 900 and 1,000 nm. This pattern indicates an overall spectral trend characterized by an initial increase, followed by a slow decrease. Over the entire wavelength range, the reflectance of the AY and AJ samples was higher than that of the other samples. The HB samples displayed intermediate reflectance, whereas the YN and HN samples had relatively lower reflectance. For genuine _Fushen_, the four regional spectra showed a similar overall pattern, with the reflectance increasing and decreasing ([Figure 2B](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#fig2)). However, an evident regional variation was observed, with the reflectance increasing from the inner to the outer region in the order FSM \u003C M1 \u003C M2 \u003C M3. Notably, M2 exhibited a reflectance profile similar to that of All. For counterfeit _Fushen_, the spectra of M1, M2, and M3 were highly consistent with that of All, whereas FSM showed a different spectral profile ([Figure 2C](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1891249\u002Fabstract#fig2)). M2 had the highest reflectance among the four counterfeit regions. In both genuine and counterfeit samples, FSM showed low reflectance and similar curve patterns. Although the spectral reflectance varied among s","Frontiers in Sustainable Food Systems 2026-08-07","2026-08-07T00:00:00Z","论文",10,false,67,{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":20,"relevant":21,"comment":22},12,20,18,5,1,"研究利用便携式高光谱成像结合可解释机器学习实现茯苓产地溯源与真伪鉴别，方法新颖，数据详实，对中药材质量监管有参考价值，但属细分领域进展，影响范围有限。",[24],{"name":10,"url":6},[26,27,28,29],"SHAP","高光谱成像","产地溯源","中药材",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":38,"locked":14,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,50,56],{"code":31,"score":44,"supported":45,"title":46,"abstract":48,"tags":49},11,true,[47],"hyperspectral",[47],[],{"code":51,"score":52,"supported":45,"title":53,"abstract":54,"tags":55},"B6",4,[],[29],[29],{"code":57,"score":52,"supported":45,"title":58,"abstract":59,"tags":61},"I2",[],[60],"机器学习",[26],[63,64],"高光谱成像 产地溯源 中药材 SHAP","高光谱成像 产地溯源","高光谱成像产地溯源中药材SHAP-469","10.3389\u002Ffsufs.2026.1891249\u002Fabstract","2026-08-12T23:57:24.335667Z",{"total":69,"page":21,"page_size":69,"items":70},6,[71,187,283,344,393,481],{"id":72,"title":73,"url":74,"summary":75,"summary_zh":76,"content":8,"source_name":77,"source_url":74,"published_at":78,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":79,"score_detail":80,"sources":84,"tags":86,"primary_topic":92,"secondary_topics":93,"classification":98,"search_phrases":157,"slug":160,"view_count":161,"doi":162,"paper":163,"created_at":186},5582,"AI-Based RGB Imaging and 14-Channel Multispectral Food Quality Scanner","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85255","Food-quality assessment plays an important role in food safety, agricultural processing, storage, and supply-chain management. Conventional inspection methods depend on visual judgement or laboratory-based testing, which may require considerable time, specialised equipment, and manual effort. Recent developments in computer vision, multispectral sensing, and artificial intelligence (AI) provide opportunities for automated, non-destructive food-quality assessment. This paper reviews the application of RGB imaging, multispectral sensing, machine learning, and deep learning for fruit-ripeness estimation, surfacedefect detection, grain classification, and food-authenticity assessment. The reviewed literature demonstrates that RGB imaging can extract visible features such as colour, shape, and texture, whereas multispectral sensing provides wavelength-dependent information associated with food characteristics. Published studies have reported promising results in tomato-ripeness classification, apple-defect detection, rice-grain analysis, and honey-adulteration screening. Based on these findings, a compact food-quality scanner integrating an RGB camera, a 14-channel multispectral sensor, controlled illumination, and an embedded processing unit is proposed. The review discusses sensor integration, data preprocessing, feature fusion, classification methods, evaluation metrics, and implementation challenges. It also identifies the need for broader datasets, standardised illumination, independent validation, and resource-efficient AI models to improve the reliability of portable food-inspection systems.","食品质量评估在食品安全、农产品加工、储运和供应链管理中发挥着重要作用。传统检测方法依赖人工目视判断或实验室检测，往往需要较长时间、专用设备和人工投入。近年来，计算机视觉、多光谱传感和人工智能（AI）的发展为自动化、无损食品质量评估提供了新的机遇。本文综述了RGB成像、多光谱传感、机器学习和深度学习在果实成熟度估计、表面缺陷检测、谷物分类和食品真实性评估中的应用。所综述的文献表明，RGB成像能够提取颜色、形状和纹理等可见特征，而多光谱传感则可提供与食品特性相关的波长依赖信息。已发表研究在番茄成熟度分类、苹果缺陷检测、稻米籽粒分析和蜂蜜掺假筛查等方面取得了良好结果。基于上述研究结果，本文提出一种集成了RGB相机、14通道多光谱传感器、受控照明和嵌入式处理单元的紧凑型食品质量扫描仪。综述讨论了传感器集成、数据预处理、特征融合、分类方法、评价指标和实现挑战，并指出需要更广泛的数据集、标准化照明、独立验证和资源高效的AI模型，以提高便携式食品检测系统的可靠性。","International Journal for Research in Applied Science and Engineering Technology","2026-10-21T00:00:00Z",65,{"impact":17,"substance":19,"depth":81,"authority":82,"freshness":13,"relevant":21,"comment":83},16,9,"综述性论文，提出集成RGB与14通道多光谱的便携食品质量扫描仪方案，方法框架清晰但缺乏自有实验数据，属细分领域技术进展，可作参考但非重大突破。",[85],{"name":77,"url":74},[87,88,89,90,91],"智慧农业","农业人工智能","无损检测","多光谱成像","食品质量检测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[94],{"code":57,"slug":95,"name":96,"path":97,"parent_code":35},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":38,"locked":14,"version":39,"method":40,"evidence":99},{"candidates":100,"agricultural_evidence":45},[101,106,116,124,131,138,145,152],{"code":31,"score":17,"supported":45,"title":102,"abstract":104,"tags":105},[103],"multispectral",[103],[90],{"code":57,"score":13,"supported":45,"title":107,"abstract":108,"tags":115},[],[109,60,110,111,112,113,114],"深度学习","计算机视觉","machine learning","deep learning","artificial intelligence","computer vision",[88],{"code":117,"score":118,"supported":45,"title":119,"abstract":120,"tags":123},"E4",7,[],[121,122],"食品安全","food safety",[89],{"code":125,"score":69,"supported":45,"title":126,"abstract":127,"tags":130},"A1",[],[128,129],"稻米","rice",[],{"code":132,"score":69,"supported":45,"title":133,"abstract":134,"tags":137},"B1",[],[135,136],"番茄","tomato",[],{"code":139,"score":69,"supported":45,"title":140,"abstract":141,"tags":144},"B2",[],[142,143],"苹果","apple",[],{"code":146,"score":147,"supported":45,"title":148,"abstract":149,"tags":151},"E1",3,[],[150],"农产品加工",[],{"code":153,"score":21,"supported":14,"title":154,"abstract":155,"tags":156},"I1",[],[],[87],[158,159],"RGB成像 多光谱 食品质量","14通道 多光谱 扫描仪","RGB成像多光谱食品质量-5582",0,"10.22214\u002Fijraset.2026.85255",{"doi":162,"openalex_id":164,"authors":165,"venue":77,"cited_by_count":161,"oa_url":74,"card":178,"direction":184,"ingested_from":185},"W7223139905",[166,168,170,172,174,176],{"name":167,"orcid":8},"Eshwari Take",{"name":169,"orcid":8},"Avanish Raut",{"name":171,"orcid":8},"Vedant Joshi",{"name":173,"orcid":8},"Shravani Akolkar",{"name":175,"orcid":8},"R. M. Gharat",{"name":177,"orcid":8},"Shruti Dive",{"tldr":179,"method":180,"finding":181,"direction":182,"opportunity":183},"综述RGB与多光谱成像结合AI的食品品质无损检测，并提出一款集成14通道多光谱传感器的紧凑型扫描仪方","综述RGB成像、多光谱传感与机器学习\u002F深度学习在食品检测中的应用，并提出传感器集","RGB与多光谱融合在番茄成熟度、苹果缺陷、稻米分类和蜂蜜掺假检测中表现良好。","农业人工智能与决策模型","可研究多源光谱特征融合与轻量化模型，构建标准化数据集和便携设备独立验证体系。","数字乡村与农业信息化","openalex","2026-10-22T11:20:48.684398Z",{"id":188,"title":189,"url":190,"summary":191,"summary_zh":192,"content":8,"source_name":193,"source_url":190,"published_at":78,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":194,"score_detail":195,"sources":199,"tags":201,"primary_topic":205,"secondary_topics":211,"classification":219,"search_phrases":250,"slug":253,"view_count":161,"doi":254,"paper":255,"created_at":282},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",80,{"impact":81,"substance":196,"depth":19,"authority":197,"freshness":13,"relevant":21,"comment":198},22,14,"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。",[200],{"name":193,"url":190},[87,88,202,203,204],"农业遥感","氮素监测","紫花苜蓿",{"code":206,"slug":207,"name":208,"path":209,"parent_code":210},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[212,213],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"code":214,"slug":215,"name":216,"path":217,"parent_code":218},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":38,"locked":14,"version":39,"method":40,"evidence":220},{"candidates":221,"agricultural_evidence":45},[222,228,235,241,246],{"code":31,"score":19,"supported":45,"title":223,"abstract":224,"tags":227},[47],[225,226,47],"遥感","remote sensing",[202],{"code":206,"score":229,"supported":45,"title":230,"abstract":232,"tags":234},15,[231],"alfalfa",[233,231],"苜蓿",[204],{"code":214,"score":13,"supported":45,"title":236,"abstract":237,"tags":240},[],[238,233,239],"饲草","forage",[204],{"code":57,"score":13,"supported":45,"title":242,"abstract":243,"tags":245},[],[109,60,111,112,244],"decision support",[88],{"code":153,"score":21,"supported":14,"title":247,"abstract":248,"tags":249},[],[],[87],[251,252],"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":254,"openalex_id":256,"authors":257,"venue":193,"cited_by_count":161,"oa_url":190,"card":276,"direction":280,"ingested_from":185},"W7223154576",[258,260,262,264,266,269,271,274],{"name":259,"orcid":8},"Shuai Fu",{"name":261,"orcid":8},"Yunhao Li",{"name":263,"orcid":8},"Chunli Miao",{"name":265,"orcid":8},"Jie Liu",{"name":267,"orcid":268},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":270,"orcid":8},"Yongjia Hu",{"name":272,"orcid":273},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":275,"orcid":8},"吴彩霞",{"tldr":277,"method":278,"finding":279,"direction":280,"opportunity":281},"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","农业遥感与作物表型","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":284,"title":285,"url":286,"summary":287,"summary_zh":288,"content":8,"source_name":289,"source_url":286,"published_at":78,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":290,"score_detail":291,"sources":294,"tags":296,"primary_topic":299,"secondary_topics":300,"classification":301,"search_phrases":319,"slug":322,"view_count":161,"doi":323,"paper":324,"created_at":343},5571,"Temporal Multi-Scale Spatio-Temporal Network (TMST): Polarization–Temporal Feature Selection and Multi-Scale Spatiotemporal Fusion for Crop Mapping","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202068","Accurate and timely crop mapping supports agricultural resource management, yield prediction, and food security decision-making. In this study, we propose the Temporal Multi-scale Spatio-Temporal Network (TMST), a crop mapping method that integrates multi-source remote sensing time series through polarization–temporal feature selection and multi-scale spatiotemporal fusion. TMST combines Sentinel-1 dual-polarization synthetic aperture radar (SAR), Sentinel-2 multispectral data, and vegetation indices. Its Temporal Feature Importance Explainer (TFIExplainer) selects informative polarization–time features, the Multi-Scale Attention Aggregation (MSAA) module enhances spatial representations, and the Spatio-Temporal Feature Encoder (STFE) models long-range spatial dependencies and phenological dynamics; a composite loss improves minority-class and difficult-pixel recognition. On the Xinxiang dataset, TMST achieved an overall accuracy (OA) of 0.8625 and a mean F1-score (mF1) of 0.8329. Module and data-source ablations suggested benefits of the combined modules and multi-source fusion, while a cropland mask reduced non-cropland misclassification. In direct cross-dataset evaluation, models trained on a self-constructed Austrian dataset and tested on the radar-extended Panoptic Agricultural Satellite Time Series (PASTIS-R) dataset showed that TMST outperformed the evaluated baselines under the specified source–target setting. Annual mapping of Xinxiang for 2019–2023, using year-specific samples and independently trained models, provided map-based estimates of regional cropping structures and spatial patterns. Under the evaluated settings, TMST provides an effective approach to crop classification and annually updated crop mapping.","准确的作物制图有助于农业资源管理、产量预测和粮食安全决策。本研究提出了一种时间多尺度时空网络（Temporal Multi-scale Spatio-Temporal Network，TMST），这是一种通过极化—时间特征选择和多尺度时空融合来整合多源遥感时间序列的作物制图方法。TMST结合了Sentinel-1双极化合成孔径雷达（SAR）、Sentinel-2多光谱数据和植被指数。其时间特征重要性解释器（Temporal Feature Importance Explainer，TFIExplainer）用于选择信息量丰富的极化—时间特征，多尺度注意力聚合（Multi-Scale Attention Aggregation，MSAA）模块增强空间表征，时空特征编码器（Spatio-Temporal Feature Encoder，STFE）建模长程空间依赖关系和物候动态；复合损失函数改善了少数类和困难像元的识别。在新乡数据集上，TMST取得了0.8625的总体精度（OA）和0.8329的平均F1分数（mF1）。模块和数据源消融实验表明，组合模块和多源融合具有优势，而耕地掩膜减少了非耕地误分类。在直接的跨数据集评估中，在自行构建的奥地利数据集上训练并在雷达扩展的Panoptic农业卫星时间序列（PASTIS-R）数据集上测试的模型表明，在指定的源—目标设置下，TMST优于所评估的基线方法。使用逐年样本和独立训练的模型对新乡2019—2023年进行年度制图，提供了基于制图的区域种植结构和空间格局估计。在所评估的设置下，TMST为作物分类和年度更新的作物制图提供了一种有效方法。","Agronomy",73,{"impact":17,"substance":18,"depth":292,"authority":197,"freshness":13,"relevant":21,"comment":293},17,"提出多源遥感融合的作物制图新方法，方法新颖、实验充分，但属细分技术进展，公共影响有限。",[295],{"name":289,"url":286},[87,297,225,298],"作物制图","SAR",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":302},{"candidates":303,"agricultural_evidence":45},[304,308,315],{"code":31,"score":13,"supported":45,"title":305,"abstract":306,"tags":307},[],[225,226,103],[225],{"code":309,"score":69,"supported":45,"title":310,"abstract":311,"tags":314},"A8",[],[312,313],"粮食安全","food security",[],{"code":153,"score":21,"supported":14,"title":316,"abstract":317,"tags":318},[],[],[87],[320,321],"Sentinel-1 Sentinel-2 作物分类","TMST 多尺度时空网络","Sentinel-1Sentinel-2作物分类-5571","10.3390\u002Fagronomy16202068",{"doi":323,"openalex_id":325,"authors":326,"venue":289,"cited_by_count":161,"oa_url":286,"card":338,"direction":280,"ingested_from":185},"W7223117203",[327,330,332,335],{"name":328,"orcid":329},"Xi Kan","https:\u002F\u002Forcid.org\u002F0000-0002-4629-9357",{"name":331,"orcid":8},"Wentao Lv",{"name":333,"orcid":334},"Lei Gong","https:\u002F\u002Forcid.org\u002F0000-0001-6429-267X",{"name":336,"orcid":337},"Linglong Zhu","https:\u002F\u002Forcid.org\u002F0000-0002-8863-9911",{"tldr":339,"method":340,"finding":341,"direction":280,"opportunity":342},"提出TMST网络，融合SAR与多光谱时序数据实现作物制图。","Sentinel-1\u002F2时序、极化-时序特征选择、多尺度注意力与时空编码器。","新乡OA达0.8625，多源融合与模块组合有效，跨数据集优于基线。","可探索极化-时序特征选择在跨区域迁移与少样本作物制图中的泛化能力。","2026-10-22T11:20:39.359881Z",{"id":345,"title":346,"url":347,"summary":348,"summary_zh":349,"content":8,"source_name":350,"source_url":347,"published_at":78,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":351,"sources":354,"tags":356,"primary_topic":359,"secondary_topics":360,"classification":362,"search_phrases":377,"slug":380,"view_count":161,"doi":381,"paper":382,"created_at":392},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。","Zenodo (CERN European Organization for Nuclear Research)",{"impact":352,"substance":18,"depth":292,"authority":17,"freshness":13,"relevant":21,"comment":353},8,"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[355],{"name":350,"url":347},[87,88,357,225,358],"产量预测","可解释性",{"code":57,"slug":95,"name":96,"path":97,"parent_code":35},[361],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":363},{"candidates":364,"agricultural_evidence":45},[365,369,373],{"code":57,"score":17,"supported":45,"title":366,"abstract":367,"tags":368},[114],[110],[88],{"code":31,"score":352,"supported":45,"title":370,"abstract":371,"tags":372},[],[225,226],[357,225],{"code":153,"score":21,"supported":14,"title":374,"abstract":375,"tags":376},[],[],[87],[378,379],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":381,"openalex_id":383,"authors":384,"venue":350,"cited_by_count":161,"oa_url":347,"card":387,"direction":280,"ingested_from":185},"W7223114002",[385],{"name":386,"orcid":8},"Kadiatou Barry",{"tldr":388,"method":389,"finding":390,"direction":280,"opportunity":391},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":394,"title":395,"url":396,"summary":397,"summary_zh":398,"content":8,"source_name":399,"source_url":396,"published_at":400,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":401,"score_detail":402,"sources":404,"tags":406,"primary_topic":409,"secondary_topics":410,"classification":412,"search_phrases":433,"slug":436,"view_count":161,"doi":437,"paper":438,"created_at":480},5567,"Capturing Spatial Heterogeneity Using UAV-Derived Multispectral Phenotypes and Random Regression Models Improves Genetic Evaluation in Alfalfa Breeding Trials","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.10.14.759249","Spatial heterogeneity is a major source of environmental noise in field trials, reducing genetic evaluation accuracy. Conventional spatial correction methods use field layout and plot proximity but often fail to capture in-season dynamics or leverage temporal data from high-throughput phenotyping. We hypothesized that longitudinal UAV-derived multispectral measurements could characterize field-scale environmental heterogeneity and improve genetic evaluation in breeding trials. Multispectral imagery was collected throughout the growing season across eight alfalfa trials in New York and New Mexico (20222023). Vegetation indices were evaluated for heritability and association with biomass yield using univariate and multi-trait models. Longitudinal measurements were modeled with random regression (RR) to estimate plot-specific permanent environmental effects (PEE), incorporated into genomic mixed models within a two-stage framework. Model performance was compared with conventional autoregressive (AR) and baseline (no correction) models using metrics of consistency and accuracy of estimated genetic effects across replicates. Vegetation indices showed moderate to high heritability, with GNDVI consistently outperforming NDVI and NDRE. Both univariate and multi-trait analyses revealed substantial spatial variability, particularly in New Mexico trials. RR-derived PEE captured field-scale spatial patterns and improved genetic signal recovery relative to baseline and AR models, with the largest gains under strong spatial heterogeneity and comparable performance where variability was limited. The RR framework improved reproducibility of genetic effect estimates across independent field subsets without compromising agreement with full-trial evaluations. These findings show that integrating UAV data via random regression enhances genetic signal recovery and selection accuracy, with broader potential for precision agriculture and biosensor-driven crop management.","空间异质性是田间试验中环境噪声的主要来源，会降低遗传评估的准确性。传统空间校正方法利用田间布局和小区邻近性，但往往无法捕捉生育期内的动态变化，也未能充分利用高通量表型分析产生的时间序列数据。我们假设，基于无人机（UAV）的纵向多光谱测量能够表征田块尺度的环境异质性，并改善育种试验中的遗传评估。在2022—2023年纽约州和新墨西哥州的8个紫花苜蓿试验中，于整个生长季收集了多光谱影像。采用单性状和多性状模型评估了植被指数的遗传力及其与生物量产量的关联。纵向测量数据采用随机回归（RR）建模，以估计小区特异性永久环境效应（PEE），并在两阶段框架中将其纳入基因组混合模型。利用重复间估计遗传效应的一致性和准确性指标，将模型性能与传统的自回归（AR）模型和基线（无校正）模型进行比较。植被指数表现出中到高的遗传力，其中GNDVI始终优于NDVI和NDRE。单性状和多性状分析均揭示了显著的空间变异，尤其在新墨西哥州的试验中更为明显。RR衍生的PEE捕捉到了田块尺度的空间格局，相对于基线模型和AR模型改善了遗传信号的恢复，在强空间异质性条件下增益最大，而在变异有限时性能相当。RR框架提高了遗传效应估计在独立田间子集间的可重复性，同时未损害与全试验评估的一致性。这些结果表明，通过随机回归整合UAV数据可增强遗传信号恢复和选择准确性，在精准农业和生物传感器驱动的作物管理方面具有更广泛的潜力。","bioRxiv (Cold Spring Harbor Laboratory)","2026-10-20T00:00:00Z",79,{"impact":19,"substance":196,"depth":19,"authority":17,"freshness":82,"relevant":21,"comment":403},"该研究利用无人机多光谱表型与随机回归模型校正田间空间异质性，显著提升苜蓿育种遗传评估精度，方法新颖、数据覆盖两州八组试验，对智慧育种有实质参考价值。",[405],{"name":399,"url":396},[87,407,408,225,204],"无人机","育种",{"code":206,"slug":207,"name":208,"path":209,"parent_code":210},[411],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":413},{"candidates":414,"agricultural_evidence":45},[415,419,423,429],{"code":206,"score":229,"supported":45,"title":416,"abstract":417,"tags":418},[231],[233,231],[204],{"code":31,"score":17,"supported":45,"title":420,"abstract":421,"tags":422},[103],[103],[225],{"code":153,"score":118,"supported":45,"title":424,"abstract":425,"tags":428},[],[426,427],"精准农业","precision agriculture",[87],{"code":214,"score":52,"supported":45,"title":430,"abstract":431,"tags":432},[],[233],[204],[434,435],"无人机 多光谱 苜蓿 育种","随机回归 空间异质性 遗传评估","无人机多光谱苜蓿育种-5567","10.64898\u002F2026.10.14.759249",{"doi":437,"openalex_id":439,"authors":440,"venue":399,"cited_by_count":161,"oa_url":396,"card":475,"direction":280,"ingested_from":185},"W7223083966",[441,444,447,450,453,455,457,460,463,466,469,472],{"name":442,"orcid":443},"Dinesh Ghimire","https:\u002F\u002Forcid.org\u002F0009-0008-2281-1396",{"name":445,"orcid":446},"Ranjita Thapa","https:\u002F\u002Forcid.org\u002F0000-0001-6116-7611",{"name":448,"orcid":449},"Karl H. Kunze","https:\u002F\u002Forcid.org\u002F0000-0003-4548-1808",{"name":451,"orcid":452},"Felipe Sabadin","https:\u002F\u002Forcid.org\u002F0000-0003-2937-1465",{"name":454,"orcid":8},"Julie Hansen",{"name":456,"orcid":8},"Christopher Pierce",{"name":458,"orcid":459},"Liam Wickes-Do","https:\u002F\u002Forcid.org\u002F0009-0003-2927-4590",{"name":461,"orcid":462},"Nicholas Santantonio","https:\u002F\u002Forcid.org\u002F0000-0002-4351-4023",{"name":464,"orcid":465},"Ian M. Ray","https:\u002F\u002Forcid.org\u002F0000-0003-2056-536X",{"name":467,"orcid":468},"Michael A. Gore","https:\u002F\u002Forcid.org\u002F0000-0001-6896-8024",{"name":470,"orcid":471},"Virginia Mae Moore","https:\u002F\u002Forcid.org\u002F0000-0001-7888-3366",{"name":473,"orcid":474},"Kelly R. Robbins","https:\u002F\u002Forcid.org\u002F0000-0001-9522-9585",{"tldr":476,"method":477,"finding":478,"direction":280,"opportunity":479},"用无人机多光谱时序表型和随机回归模型校正田间空间异质性，提升苜蓿育种遗传评估精度。","八项苜蓿试验的无人机多光谱植被指数，随机回归估计小区永久环境效应并嵌入基因组混合","随机回归提取的环境效应能捕捉田块尺度空间格局，在强异质性下显著提升遗传信号恢复与选择准确性。","可将无人机时序表型与随机回归框架推广到其他作物育种试验，并探索多源遥感与基因组选择的联合建模。","2026-10-22T11:20:32.655394Z",{"id":482,"title":483,"url":484,"summary":485,"summary_zh":486,"content":8,"source_name":350,"source_url":484,"published_at":78,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":487,"score_detail":488,"sources":490,"tags":492,"primary_topic":496,"secondary_topics":502,"classification":509,"search_phrases":541,"slug":544,"view_count":161,"doi":545,"paper":546,"created_at":557},5552,"INTEGRATING IoT, REMOTE SENSING, AND ARTIFICIAL INTELLIGENCE FOR SMART IRRIGATION: A REVIEW OF ARCHITECTURES, METHODS, AND CHALLENGES","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531020","This research paper reviews the integration of Internet of Things (IoT), remote sensing, and Artificial Intelligence (AI) in smart irrigation systems. It discusses system architectures, intelligent irrigation techniques, automated water management, key challenges, and future research opportunities to improve water-use efficiency and promote sustainable agriculture.","本文综述了物联网（Internet of Things, IoT）、遥感与人工智能（Artificial Intelligence, AI）在智能灌溉系统中的融合应用，探讨了系统架构、智能灌溉技术、自动化水资源管理、关键挑战及未来研究方向，以提升用水效率并促进可持续农业发展。",75,{"impact":19,"substance":18,"depth":81,"authority":17,"freshness":82,"relevant":21,"comment":489},"系统综述物联网、遥感与AI融合的智能灌溉架构与方法，属智慧农业细分领域有实质增量的国际综述，值得入选。",[491],{"name":350,"url":484},[88,493,225,494,495],"农业物联网","智慧灌溉","节水农业",{"code":497,"slug":498,"name":499,"path":500,"parent_code":501},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[503,508],{"code":504,"slug":505,"name":506,"path":507,"parent_code":35},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":510},{"candidates":511,"agricultural_evidence":45},[512,519,526,530,534],{"code":497,"score":513,"supported":45,"title":514,"abstract":515,"tags":518},19,[498],[516,517,498],"灌溉","水资源",[494,495],{"code":504,"score":19,"supported":45,"title":520,"abstract":522,"tags":525},[521],"IoT",[523,524,521],"物联网","internet of things",[493],{"code":31,"score":229,"supported":45,"title":527,"abstract":528,"tags":529},[226],[225,226],[225],{"code":57,"score":17,"supported":45,"title":531,"abstract":532,"tags":533},[113],[113],[88],{"code":535,"score":69,"supported":45,"title":536,"abstract":537,"tags":540},"H8",[],[538,539],"可持续农业","sustainable agriculture",[],[542,543],"IoT 遥感 AI 智能灌溉","农业人工智能 农业物联网 智慧灌溉 节水农业","IoT遥感AI智能灌溉-5552","10.5281\u002Fzenodo.23531020",{"doi":545,"openalex_id":547,"authors":548,"venue":350,"cited_by_count":161,"oa_url":484,"card":551,"direction":555,"ingested_from":185},"W7223090389",[549],{"name":550,"orcid":8},"Patil",{"tldr":552,"method":553,"finding":554,"direction":555,"opportunity":556},"综述物联网、遥感与人工智能融合的智能灌溉系统架构、方法与挑战。","文献综述，梳理IoT、遥感与AI集成的系统架构与智能灌溉技术。","融合三者可提升用水效率并推动可持续农业，但仍面临关键挑战。","智慧农业 \u002F 农业物联网","可针对多源数据融合的实时灌溉决策模型与边缘部署开展实证研究。","2026-10-22T11:20:18.028252Z"]