[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-680":3,"related-680":59},{"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":35,"classification":36,"search_phrases":52,"slug":55,"view_count":56,"doi":57,"paper":8,"created_at":58},680,"GCT-BCLN 水稻种子活力双向闭环高光谱无损检测网络(Frontiers in Plant Science 2026-08-17)","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1923668\u002Fabstract","提出GCT-BCLN(GCT双向闭环网络):基于高光谱成像技术的水稻种子活力无损检测方法。该方法结合图卷积与Transformer构建双向闭环特征提取机制,可同时捕获高光谱图像的空间-光谱联合特征,在水稻种子活力分级任务上较传统检测方法准确率与效率均显著提升。研究为种子质检、储藏与播种前的活力快速评估提供新工具。",null,"## Abstract\n\nRice seed vigor is a key determinant of germination performance and final crop yield, making its rapid and non-destructive assessment essential for seed quality evaluation. Conventional vigor detection methods are often destructive, labor-intensive, and time-consuming. Hyperspectral imaging provides a promising non-destructive alternative, but hyperspectral data are typically high-dimensional, redundant, and susceptible to noise and scattering interference. Moreover, existing models still have limited ability to discriminate subtle spectral differences among seed vigor levels. To address these challenges, this study proposes a gated recurrent unit (GRU)-guided closed-loop CNN-Transformer network (GCT-BCLN) for accurate, non-destructive identification of rice seed vigor. The model establishes bidirectional information flow between CNN and Transformer via the GRU, enabling dynamic and synergistic optimization of local spectral features and global spectral representations. In addition, a combined preprocessing strategy integrating adaptive iteratively reweighted penalized least squares (AirPLS), Savitzky–Golay (SG) smoothing, and multiplicative scatter correction (MSC) was adopted to improve spectral quality. Experimental results showed that GCT-BCLN achieved a test accuracy of 0.9795 for hybrid indica rice, outperforming the CNN-Transformer fusion model by 1.37%. The model also achieved accuracies of 0.9793 and 0.9758 on conventional japonica rice and glutinous japonica rice, respectively, showing consistent performance across the three evaluated variety-specific datasets under the controlled experimental protocol. These results support the feasibility of GCT-BCLN for laboratory-scale, non-destructive discrimination of aging-induced rice seed categories under controlled conditions, while practical application requires further external validation.\n\n## 1 Introduction\n\nRice is one of the world’s most important staple crops, and its yield and grain quality are closely related to global food security (; ). In crop production, seed quality is a key determinant of field performance, among which seed vigor is a crucial physiological indicator affecting germination, seedling establishment, and ultimately crop productivity (). High-vigor seeds, characterized by stronger stress tolerance and growth potential, contribute to stable and high yields (). Therefore, accurate and efficient assessment of rice seed vigor is of great significance for seed breeding, processing, and storage management. Conventional methods, including standard germination tests, electrical conductivity measurements, and tetrazolium staining, can differentiate seed vigor to some extent, but they are generally limited by laborious procedures, long detection cycles, and destructive sampling requirements (). With the development of intelligent and precision agriculture, there is an increasing demand for non-destructive and accurate methods for rice seed vigor assessment.\n\nRecent advances in hyperspectral imaging (HSI) have provided a promising non-destructive technique for seed vigor evaluation (). By combining spatial information, such as seed morphology and texture, with spectral signatures associated with molecular vibrations of internal biochemical constituents, HSI enables seed quality assessment without physical damage (). Its potential has been demonstrated in several seed vigor studies. For example, applied HSI to detect rice seed vigor under sample-imbalanced conditions. used HSI to predict the vigor of naturally aged Xishuangbanna cucumber seeds, and achieved non-destructive detection of maize seed vigor using a data-fusion-driven HSI approach. Nevertheless, hyperspectral data are typically characterized by high dimensionality (), substantial redundancy (), susceptibility to noise (), and sample-specific variability, all of which hinder robust feature extraction and modeling. Conventional pipelines combining spectral preprocessing methods, such as first derivative (FD) (), Savitzky-Golay (SG) smoothing (), and standard normal variate (SNV) transformation (), with traditional machine learning models, including partial least squares regression (PLSR) (), support vector machine (SVM) (), and Random Forest (RF) (), can improve seed vigor prediction to some extent. However, these methods usually depend on manual feature engineering and often fail to capture the complex nonlinear relationships between spectral information and seed vigor, resulting in limited generalization and reduced sensitivity to subtle vigor differences.\n\nDeep learning, with its end-to-end feature learning capability, has shown strong potential for modeling high-dimensional and highly correlated hyperspectral data. In seed vigor detection, proposed a multi-scale spectral attention residual network (MSARN) for common bean seed vigor assessment, achieving accuracy, precision, recall, and F1-score values of 98.75%, 98.97%, 98.80%, and 98.81%, respectively. combined CNNs with a long short-term memory (LSTM) network to model the vigor of _Styphnolobium japonicum_ seeds, achieving recognition accuracy above 90%. Despite these advances, conventional CNNs are limited by their kernel-size-dependent receptive fields and tend to emphasize local spectral patterns while underrepresenting long-range spectral relationships. This limitation restricts their ability to model complex spectral signatures associated with seed aging and biochemical heterogeneity. To jointly capture local and global information, recent studies have introduced Transformer architectures, which model long-range dependencies through self-attention. developed a CNN-Transformer fusion model for rice variety classification using reconstructed hyperspectral images, achieving 99.413% accuracy and markedly outperforming a standalone CNN. proposed a dual-feature transformation fusion transformer (DFTFT), which explicitly models global spectral associations for wheat and maize leaf disease and quality grade classification, improving classification accuracy by 5.2%–7.8% compared with single-CNN baselines. designed an interpretable lightweight CNN-Transformer hybrid model for rapid rice leaf disease identification, achieving an accuracy of up to 97%.\n\nAlthough CNN-Transformer hybrid models have shown advantages over conventional CNNs in crop hyperspectral recognition and classification, rice seed vigor detection remains challenging. First, spectral differences among seeds at different aging stages are often subtle, requiring models with strong sensitivity to fine inter-class variations. Second, the curved surface morphology of rice seeds induces scattering heterogeneity, causing spectra from seeds with the same vigor level to be affected by sample-specific physical differences. Third, varietal diversity leads to differences in spectral baselines and characteristic peaks, further complicating feature learning. Most existing CNN-Transformer fusion models adopt cascaded serial architectures (), in which features are transmitted unidirectionally and statically. In such designs, local feature extraction is weakly guided by global spectral representations, while global modeling provides limited feedback for refining local features. This restricts model robustness under subtle vigor differences and spectral interference. Therefore, dynamic and synergistic optimization of local and global features is needed to improve the adaptability of hyperspectral models for rice seed vigor assessment. Bidirectional feedback has been shown to enhance feature interaction in other fields. proposed a lightweight bidirectional feedback network for image super-resolution, reducing parameters while improving reconstruction quality. incorporated encoder–decoder bidirectional transmission with dense connections into U-Net (BiDFDC-Net), improving skin lesion segmentation. In remote sensing, proposed a dual-stream spectral interactive network with multi-scale enhancement, cross-attention complementarity, and cross-layer interaction for salient object detection. However, such bidirectional feedback mechanisms remain rarely explored in agricultural hyperspectral analysis, particularly for seed vigor assessment. Collectively, these studies indicate that reciprocal feature transmission can improve representation refinement, but existing approaches have not yet provided a stateful feedback mechanism for iterative interaction between local and global representations of wavelength-ordered hyperspectral signals.\n\nTo address this limitation, this study proposes a GRU-guided bidirectional closed-loop CNN-Transformer network (GCT-BCLN) for rice seed vigor identification. In this framework, the term bidirectional describes the two-way information flow between the CNN and Transformer: CNN-derived local spectral features are propagated forward for global dependency modeling, whereas Transformer-derived global representations are fed back to refine CNN-based local feature extraction. By contrast, the term closed-loop refers to the recurrent use of this two-way pathway, whereby feedback-refined local features re-enter the GRU-Transformer pathway in subsequent iterations until the prediction distribution stabilizes. The GRU is adopted as the feedback carrier because hyperspectral bands form an ordered sequence, and its gated hidden state can retain wavelength-dependent contextual information while selectively integrating the current global representation with information from previous feedback iterations. Through this iterative local-global interaction, GCT-BCLN is designed to enhance the representation of subtle vigor-related spectral differences and improve robustness to spectral interference. The proposed framework provides a useful methodological basis for non-destructive rice seed vigor assessment using hyperspectral data.\n\n## 2 Materials and methods\n\nTo systematically achieve non-destructive rice seed vigor detection, this study established an integrated workflow encompassing sample preparation, hyperspectral data acquisition and processing, spectral preprocessing, and model construction, as illustrated in [**Figure 1**](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1923668\u002Fabstract#f1). Sample preparation generated seed samples with different vigor levels for subsequent data acquisition. Hyperspectral imaging and spectral preprocessing provided high-quality spectral inputs for model development, while standard germination tests were conducted to establish reference labels for vigor assessment. Finally, the proposed model was constructed to map spectral features to corresponding vigor levels. The operational procedures and principles of each stage are described in detail in the following sections.\n\nFigure 1\n\n### 2.1 Preparation of rice seed samples with different vigor levels\n\nThis study employed an artificial accelerated aging method () to prepare rice seed samples with aging-induced vigor categories under controlled laboratory conditions. Three rice varieties were used in this study, including hybrid indica rice, conventional japonica rice, and glutinous japonica rice. All seeds were harvested in 2024 and provided by the Rice Research Institute of the Anhui Academy of Agricultural Sciences, China. For each variety, diseased, damaged, and empty grains were removed, and 1,200 plump, healthy seeds with uniform morphology were selected. Therefore, a total of 3,600 individual seeds were included in the experiments. The hybrid indica rice dataset was used as the primary dataset for model development and comparative evaluation, whereas the conventional japonica rice and glutinous japonica rice datasets were used as additional variety-specific evaluation datasets. Before aging, the seeds were surface-sterilized by immersion in 1% sodium hypochlorite (NaClO) solution for 15 min, thoroughly rinsed with sterile deionized water at least five times, and air-dried at room temperature until no visible surface moisture remained. Accelerated aging was conducted under controlled high-temperature and high-humidity conditions (). Briefly, 500 mL of sterile water was added to a glass desiccator, which was then placed in a dark incubator maintained at 45°C. After the internal environment stabilized at 45°C and approximately 100% relative humidity, the seeds were placed in breathable nylon mesh bags, arranged flat on a perforated porcelain plate inside the desiccator, and exposed to the aging treatment. For each rice variety, the 1,200 seeds were equally divided into six aging-duration groups, with 200 seeds in each group. Samples were collected after 0 d (control), 1 d, 2 d, 3 d, 4 d, and 5 d of aging to generate seed lots with a controlled vigor deterioration gradient. Temperature and relative humidity inside the desiccator were continuously monitored to ensure treatment consistency. After aging, seeds from each treatment were transferred to room-temperature conditions for moisture equilibration, thereby minimizing the influence of moisture differences on subsequent hyperspectral measurements and germination testing. It should be emphasized that the accelerated-aging protocol was used to generate a controlled and reproducible vigor gradient for methodological development rather than to reproduce the complete deterioration process of naturally aged commercial seed lots. The six classification targets in this study were defined according to aging duration rather than commercially defined vigor grades. Therefore, the current dataset should be interpreted as a laboratory-scale dataset for methodological evaluation rather than as a direct representation of naturally aged commercial seed lots.\n\n### 2.2 Hyperspectral data acquisition\n\nHyperspectral images of aged rice seeds were acquired using a FigSpec FS-20 hyperspectral imaging system, as illustrated in [**Figure 2**](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1923668\u002Fabstract#f2). The system acquired 300 spectral bands over the wavelength range of 400–1000 nm, corresponding to a nominal spectral sampling interval of approximately 2.0 nm. The spatial dimensions of each hyperspectral image were 1920 × 1920 pixels. For each aging treatment, 200 seeds were imaged in two batches. In each batch, 100 seeds were arranged without overlap in a 10 × 10 matrix on a black matte background to minimize background reflection and facilitate subsequent ROI extraction. Illumination was provided by two 100 W tungsten-halogen lamps positioned symmetrically on both sides of the sample platform at an angle of approximately 60°. The hyperspectral camera was mounted vertically above the samples, with a lens-to-sample working distance of 30 cm. The integration time was set to 20 ms. Before image acquisition, the lamps were warmed up for 15 min to ensure stable illumination, and all acquisition parameters were kept constant throughout the experiment. Before each acquisition batch, white- and dark-reference images were collected for radiometric calibration. The white-reference image was acquired using a polytetrafluoroethylene (PTFE) diffuse-reflectance panel with a nominal reflectance of approximately 99%. The reference panel was placed under the same imaging geometry and camera settings as the seed samples. The dark-reference image was acquired with the camera lens completely covered. To reduce the effects of dark current, non-uniform illumination, and sensor noise, the raw hyperspectral images were radiometrically calibrated using the manufacturer-provided software (). The corrected reflectance was calculated according to ([Equation 1](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1923668\u002Fabstract#eq1)). After calibration, all subsequent data processing was performed using ENVI 5.6 software. For each seed, a fixed 10 × 10-pixel square region of interest (ROI) was manually positioned within the visually homogeneous central endosperm region, with its center located near the longitudinal axis of the seed. To reduce edge scattering and background interference, the ROI boundary was kept at least 3 pixels inside the visible seed contour. The embryo-bearing basal one-third of the seed, shadowed pixels, and visibly damaged areas were excluded. When positional adjustment was necessary, the ROI was translated within the central endosperm region without changing its dimensions. The mean reflectance spectrum of the 100 pixels within the ROI was used to represent the corresponding seed and was subsequently exported for spectral preprocessing and modeling. The same ROI-selection criteria were applied to all seeds and aging treatments.\n\nFigure 2\n\n**(1)**\n\n$$\nR = \\frac{R_{\\text{O}} - R_{\\text{D}}}{R_{\\text{W}} - R_{\\text{D}}}\n$$\n\n(1)\n\nwhere $R$ is the calibrated reflectance image, $R_{\\text{O}}$ is the original hyperspectral image of the rice seeds, $R_{\\text{D}}$ is the dark-reference image acquired with the camera lens completely covered, and $R_{\\text{W}}$ is the white-reference image acquired from the PTFE reference panel under identical acquisition conditions.\n\n### 2.3 Standard laboratory germination test\n\nTo quantify the physiological decline caused by accelerated aging, a standard laboratory germination test was conducted with reference to the principles of the International Rules for Seed Testing (). For each aging treatment, 150 seeds were tested in three replicates, with 50 seeds per replicate. Seeds were placed on moistened filter paper in 90-mm Petri dishes and incubated in a controlled-environment chamber at 30 ± 0.5°C and 60 ± 5% relative humidity (RH) for 14 days. Sterile distilled water was added daily to maintain adequate moisture, and germination status was recorded daily. A seed was considered germinated when the radicle protruded through the seed coat and reached a length equal to or greater than half of the seed length (). After 14 days of incubation, the germination percentage was calculated for each replicate, and the mean value of the three replicates was used as the final germination percentage for the corresponding aging treatment. The six class labels used for spectral modeling corresponded to the aging durations (0–5 d), whereas germination percentage was used as a group-level physiological indicator to verify the progressive decline in germination performance. Therefore, the classification results should be interpreted as discrimination among aging-induced vigor categories under controlled laboratory conditions, rather than as direct measurements of the absolute vigor of naturally aged commercial seeds.\n\n### 2.4 Dataset partitioning and spectral preprocessing\n\nFor each rice variety, 1,200 seed-level spectra were obtained, corresponding to six aging-duration categories, with 200 spectra in each category. The hybrid indica rice dataset was used as the primary dataset for model development and comparative evaluation, whereas the conventional japonica rice and glutinous japonica rice datasets were used as additional variety-specific evaluation datasets. To ensure balanced class distribution and reduce evaluation bias, the 200 spectra from each aging-duration category were randomly divided into training, validation, and test subsets at a ratio of 7:2:1, yielding 140, 40, and 20 spectra per level, respectively. Consequently, each variety-specific dataset contained 840 training spectra, 240 validation spectra, and 120 test spectra. The global random seed was fixed at 42 during dataset partitioning and model weight initialization to improve experimental reproducibility. Five-fold cross-validation was conducted only on the training set of the primary hybrid indica rice dataset to support hyperparameter tuning and assess training stability. The validation set was used for model selection, early stopping, and ablation analysis, whereas the test set was strictly reserved for final performance evaluation. For the conventional japonica rice and glutinous japonica ri","Frontiers in Plant Science 2026-08-17","2026-08-17T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":13,"relevant":21,"comment":22},12,18,16,14,1,"提出水稻种子活力检测新方法，技术有创新，但属实验室阶段，影响有限。",[24],{"name":10,"url":6},[26,27,28,29],"水稻","高光谱","无损检测","种子活力",{"code":31,"slug":32,"name":26,"path":33,"parent_code":34},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[],{"status":37,"locked":14,"version":38,"method":39,"evidence":40},"classified","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":43},[42,47],{"code":31,"score":17,"supported":43,"title":44,"abstract":45,"tags":46},true,[26],[26],[26],{"code":48,"score":21,"supported":14,"title":49,"abstract":50,"tags":51},"I3",[],[],[27],[53,54],"无损检测 种子活力 高光谱 水稻","无损检测 种子活力","无损检测种子活力高光谱水稻-680",5,"10.3389\u002Ffpls.2026.1923668\u002Fabstract","2026-08-17T23:54:56.154768Z",{"total":60,"page":21,"page_size":60,"items":61},6,[62,117,183,223,276,357],{"id":63,"title":64,"url":65,"summary":66,"summary_zh":8,"content":67,"source_name":68,"source_url":8,"published_at":69,"category":70,"cover_url":8,"hotness":13,"is_selected":14,"score":71,"score_detail":72,"sources":76,"tags":78,"primary_topic":83,"secondary_topics":84,"classification":85,"search_phrases":111,"slug":114,"view_count":115,"doi":8,"paper":8,"created_at":116},5449,"安徽省农科院专家在淮南潘集「绿色吨半粮」基地开展水稻良种与高效肥测产观摩","https:\u002F\u002Fwww.panji.gov.cn\u002Fpjzx\u002Fjcgz\u002F11259072035.html","10 月 14 日上午，水稻良种和高效肥展示观摩会在淮南市潘集区贺疃镇「绿色吨半粮」示范基地举行，来自中国农业大学、南京农业大学、安徽省农业科学院、安徽农业大学的专家教授以及种粮大户、基层农技人员参加。示范田内多个水稻新品种分区种植，同步设置高效肥与常规施肥对照试验田块，通过机收和人员测产直观展示良种搭配高效肥料的增产效果，为做好新一年店集贡米品种选育与宣传推广提供技术依据，推动水稻单产提升行动。","为加快优良水稻品种、高效新型肥料示范推广，推动良种良法配套落地，助力粮食稳产增产，10月14日上午，水稻良种和高效肥展示观摩会在贺疃镇“绿色吨半粮”示范基地举行。来自中国农业大学、南京农业大学、安徽省农业科学院、安徽农业大学的专家教授以及种粮大户、基层农技人员齐聚基地，现场观摩对比，开展实收测产。\n\n在示范田内，多个水稻新品种分区种植，同步设置高效肥与常规施肥对照试验田块。观摩会现场，通过查看不同品种的长势、抗倒伏、抗病性，对比施用高效肥和常规肥料水稻的株型、穗粒、结实情况，现场讲解品种特性、科学施肥、田间管护等关键技术要点，为种粮大户答疑解惑，做好新一年的店集贡米的品种选育、宣传推广。现场通过机收和人员测产，直观展示了优良品种搭配高效肥料的增产效果，用真实数据验证良种与高效肥相结合的增产提质、节肥增效优势，对推进水稻单产提升行动具有积极作用。\n\n潘集区农技推广中心主任杨中保表示：“近年来，我们立足本地农业生产实际，聚焦粮食安全底线、农业增效目标、农民增收核心，扎实推进农作物良种筛选推广、配套栽培良法落地、新型肥料示范应用等一系列重点工作，通过建示范、抓培训、强指导、树样板，良种良法配套、科学施肥增效的农业生产新模式全面落地，让农作物抗灾能力、单产水平、农产品品质稳步提升，农业生产综合效益持续提高，农业生产取得了阶段性成效。”\n\n通过现场观摩不同品种的水稻生长特性，选用适配本地气候土壤的水稻良种，配套应用高效肥料，能够提升肥料利用率，对于减少化肥投入，改善稻米品质，推动水稻绿色高产，壮大潘集水稻产业的有效路径。此次观摩测产活动，搭建起科研院所、农技部门与种植主体交流对接的平台，打通农业科技成果转化 “最后一公里”。\n\n潘集区农技推广中心主任杨中保表示：“下一步，我们农技部门要锚定农业高质量发展总目标，紧扣稳粮、提质、增效、绿色核心任务，持续深耕良种良法推广、科学施肥示范工作，推动农业生产提质增效、提档升级，为稳定粮食生产、壮大特色农业、助力乡村产业振兴提供有力支撑。”","淮南市潘集区人民政府 2026-10-16","2026-10-16T00:00:00Z","报道",50,{"impact":17,"substance":20,"depth":73,"authority":74,"freshness":56,"relevant":21,"comment":75},11,8,"地方示范基地的良种良法观摩测产活动，有现场数据和多方信源，但属区域性农技推广动态，公共价值有限。",[77],{"name":68,"url":65},[26,79,80,81,82],"单产提升","科学施肥","良种良法","绿色吨半粮",{"code":31,"slug":32,"name":26,"path":33,"parent_code":34},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":86},{"candidates":87,"agricultural_evidence":43},[88,92,100,106],{"code":31,"score":17,"supported":43,"title":89,"abstract":90,"tags":91},[26],[26],[26],{"code":93,"score":94,"supported":43,"title":95,"abstract":96,"tags":99},"F3",7,[],[97,98],"施肥","肥料",[80],{"code":101,"score":102,"supported":43,"title":103,"abstract":104,"tags":105},"A8",4,[],[79],[79],{"code":107,"score":21,"supported":14,"title":108,"abstract":109,"tags":110},"F1",[],[],[81],[112,113],"潘集 绿色吨半粮 水稻","安徽省农科院 水稻 高效肥 测产","潘集绿色吨半粮水稻-5449",0,"2026-10-21T00:10:02.459897Z",{"id":118,"title":119,"url":120,"summary":121,"summary_zh":8,"content":122,"source_name":123,"source_url":8,"published_at":124,"category":70,"cover_url":8,"hotness":13,"is_selected":14,"score":125,"score_detail":126,"sources":130,"tags":132,"primary_topic":137,"secondary_topics":138,"classification":139,"search_phrases":178,"slug":181,"view_count":115,"doi":8,"paper":8,"created_at":182},5447,"安徽省农科院「银月丝苗」331 亩示范片测产 亩产 605.2 公斤 增产 31.6%","https:\u002F\u002Fwww.aaas.org.cn\u002F4303179\u002F71505657.html","安徽省农业科学院农业机械装备与工程所牵头、联合水稻研究所实施的省财政农业科技成果转化项目「粮油农文旅融合集成技术转化应用」，10 月 12 日在黄山市休宁县商山镇荪田村对水稻新品种「银月丝苗」百亩示范片开展现场测产验收。示范片面积 331 亩，配套水稻机直播、机插同步侧深施肥、稻田杂草与病虫害绿色防控等技术，实收折算干谷亩产 605.2 公斤，比去年黄山市水稻平均亩产 460.0 公斤高出 145.2 公斤、增产幅度 31.6%，远超项目亩增产 50 公斤的预期目标。","发布时间：2026-10-15 14:46   来源：安徽省农业科学院机械与工程所    阅读： 次   字体：[大] [中] [小]   保护视力色：\n\n2026年10月12日，我院的安徽省财政农业科技成果转化项目“粮油农文旅融合集成技术转化应用”，在黄山市休宁县商山镇荪田村实施的水稻新品种“银月丝苗”百亩示范片进行现场测产验收。该项目由农业机械装备与工程所牵头、联合水稻研究所共同实施。\n\n专家组听取了实施情况汇报，实地考察了项目示范片并机收测产。示范片面积331亩，种植了水稻新品种“银月丝苗”，配套应用了水稻机直播、机插同步侧深施肥、稻田杂草绿色防控、优质稻病虫害绿色防控等绿色高产优质栽培技术。示范片处于黄熟期，专家组随机选取代表性田块，实收折算干谷亩产达605.2公斤。示范片单产比去年黄山市统计的水稻平均亩产460.0公斤高出145.2公斤，增产幅度达31.6%，远超项目增产50公斤的预期目标。\n\n示范片田间生长整齐平衡，熟相好，未发现明显病虫草害，充分展现了该品种高产、优质、抗倒伏能力较强的综合优势，项目区生态环境优良，稻米产量高、品质优，同时展现了稻丰田园的大地景观，为游客初秋乡村旅游和美食体验提供了良好去处。","安徽省农业科学院 2026-10-15","2026-10-15T00:00:00Z",69,{"impact":18,"substance":127,"depth":17,"authority":128,"freshness":60,"relevant":21,"comment":129},20,13,"省级科研机构主导的新品种示范测产，数据具体、增产显著，具备行业参考价值，但属区域性进展，时效略滞后。",[131],{"name":123,"url":120},[26,133,134,135,136],"成果转化","测产验收","绿色栽培","银月丝苗",{"code":31,"slug":32,"name":26,"path":33,"parent_code":34},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":140},{"candidates":141,"agricultural_evidence":43},[142,147,152,157,163,169,173],{"code":31,"score":94,"supported":43,"title":143,"abstract":144,"tags":146},[],[26,145],"稻田",[26],{"code":148,"score":102,"supported":43,"title":149,"abstract":150,"tags":151},"G1",[],[133],[133],{"code":93,"score":153,"supported":43,"title":154,"abstract":155,"tags":156},3,[],[97],[],{"code":158,"score":153,"supported":43,"title":159,"abstract":160,"tags":162},"F4",[],[161],"绿色防控",[],{"code":164,"score":153,"supported":43,"title":165,"abstract":166,"tags":168},"F5",[],[167],"农业机械",[],{"code":101,"score":21,"supported":14,"title":170,"abstract":171,"tags":172},[],[],[134],{"code":174,"score":21,"supported":14,"title":175,"abstract":176,"tags":177},"H8",[],[],[135],[179,180],"安徽省农科院 银月丝苗 水稻","休宁 水稻 测产 605.2公斤","安徽省农科院银月丝苗水稻-5447","2026-10-21T00:10:02.221618Z",{"id":184,"title":185,"url":186,"summary":187,"summary_zh":8,"content":188,"source_name":189,"source_url":8,"published_at":69,"category":70,"cover_url":8,"hotness":13,"is_selected":14,"score":190,"score_detail":191,"sources":193,"tags":195,"primary_topic":199,"secondary_topics":200,"classification":201,"search_phrases":218,"slug":221,"view_count":115,"doi":8,"paper":8,"created_at":222},5444,"四川省农科院生核所「花香优872」百亩连片实收亩产 635 公斤","https:\u002F\u002Fwww.chinawestagr.com\u002Fzwgk\u002Fshowcontent.asp?id=67505","四川省农业科学院生物核与农业工程研究所在成都郫都区举办郫都粮经复合综合试验站杂交水稻新品种百亩连片现场观摩与验收会，重点展示该所选育的优质一级香型杂交稻「花香优872」百亩连片示范方。副所长王平研究员就该品种特征特性、配套栽培技术要点及粮经复合茬口衔接模式作现场讲解。种植大户反馈该品种在迟播条件下百亩片现场实收平均亩产 635 公斤，机械化效率提升 2.1%，抗病性与机收适应性表现良好。","λԺ                ʱ䣺2026\u002F10\u002F16171\n\nΪӿӽˮƷƹӦãƶ֡أ1011գԺڳɶۯٰۯۺվӽˮƷְĶƬֳĦջᡣʡũԺйרҡҵҵֲ󻧲μӡ\n\nĿصչʾԺѡһӽ“872”ĶƬʾԺƽоԱ͸Ʒԡ༼Ҫ㼰ϲνģʽֳ⡣λ﹡ʵز쿴ƷֵҶ̬ṹͿ֣ΧɹӦúͻеֲЧʵȷ˽ֲ󻧽ֲ飬϶ƷڿԺͻӦԷ֣ڳٲ“872”ĶƬֳʵƽĶ635еЧ2.1%ҵҵֲ󻧾͸ƷֵĽһƹ˶ԽǢ̸\n\n˴λͨ“—ҵ—ֲ”ƽ̨ѡֱָۡѧһԺΧˮֲЧӿ߲ʡ࿹˻Ʒֵɸѡչʾ׼ɣֱչʾ“”ںϵЧDZӶƹӦá","四川省农业科学院 2026-10-16",64,{"impact":18,"substance":19,"depth":17,"authority":128,"freshness":56,"relevant":21,"comment":192},"省级科研机构水稻新品种百亩连片实收测产，数据具体、有示范推广价值，但属区域性进展，时效稍旧。",[194],{"name":189,"url":186},[26,196,197,198],"种业振兴","粮食单产","新品种示范",{"code":31,"slug":32,"name":26,"path":33,"parent_code":34},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":202},{"candidates":203,"agricultural_evidence":43},[204,209,214],{"code":31,"score":94,"supported":43,"title":205,"abstract":206,"tags":208},[],[26,207],"杂交稻",[26],{"code":164,"score":153,"supported":43,"title":210,"abstract":211,"tags":213},[],[212],"机械化",[],{"code":107,"score":21,"supported":14,"title":215,"abstract":216,"tags":217},[],[],[196],[219,220],"花香优872 水稻","四川省农科院 花香优872 测产","花香优872水稻-5444","2026-10-21T00:10:01.936262Z",{"id":224,"title":225,"url":226,"summary":227,"summary_zh":8,"content":228,"source_name":229,"source_url":8,"published_at":230,"category":70,"cover_url":8,"hotness":13,"is_selected":14,"score":231,"score_detail":232,"sources":234,"tags":236,"primary_topic":241,"secondary_topics":242,"classification":248,"search_phrases":271,"slug":274,"view_count":115,"doi":8,"paper":8,"created_at":275},5432,"广东农科院水稻所主办 2026 年再生稻技术培训和现场观摩会在始兴举行","https:\u002F\u002Fnews.sciencenet.cn\u002Fhtmlnews\u002F2026\u002F10\u002F573077.shtm","广东省农业科学院水稻研究所主办的 2026 年再生稻技术培训和现场观摩会在韶关市始兴县举行，面向粤北「一季有余、两季不足」光温受限区域挖掘周年粮食产能。始兴县澄江镇善亨村 750 亩再生稻示范基地在省农科院水稻所、省农技推广中心和省水稻产业技术体系技术支撑下实行标准化种植，集中展示多个优质稻、杂交稻品种并开展品种对比试验。近年来始兴再生稻已连续 3 年实现头季、再生季两季亩产突破「吨粮」。","广东省农业技术推广中心种植业技术与种业推广部部长罗学梅在总结中充分肯定再生稻项目取得的技术突破和示范成效，并就下一阶段强化技术指导、完善示范推广体系、推动再生稻扩大应用等工作作出部署。他指出，要进一步加强科研、推广、种业和种植主体协同联动，加快适宜品种、先进技术和标准模式落地，为稳定粮食生产提供有力支撑。\n\n随后，与会人员前往始兴县澄江镇善亨村750亩再生稻示范基地开展现场观摩。该基地在广东省农业科学院水稻研究所、广东省农业技术推广中心以及广东省水稻产业技术体系的技术支撑下实行标准化种植，集中展示多个优质稻、杂交稻品种，并开展品种对比试验。技术人员走进田间，结合不同品种长势，围绕品种筛选、栽培管理、促芽肥施用、病虫害防控和机械化收割等关键环节进行讲解，并面对面解答参会人员提出的生产问题。\n\n参训人员沿着田埂仔细察看苗情和穗型，认真听取田间讲解，踊跃交流技术要点，现场学习氛围浓厚。此次活动将室内授课与田间教学有机结合，进一步提升了基层农技人员和种植主体对再生稻技术的认识，增强了推广应用信心。与会人员表示，将结合本地生产实际，把学习成果转化为田间管理措施，积极提升再生稻种植水平。\n\n版权声明：凡本网注明“来源：中国科学报、科学网、科学新闻杂志”的所有作品，网站转载，请在正文上方注明来源和作者，且不得对内容作实质性改动；微信公众号、头条号等新媒体平台，转载请联系授权。邮箱：shouquan@stimes.cn。","科学网 2026-10-17","2026-10-17T00:00:00Z",58,{"impact":19,"substance":128,"depth":73,"authority":17,"freshness":60,"relevant":21,"comment":233},"省级科研机构主办的再生稻技术培训与田间观摩，有示范基地和品种对比等实质内容，但属常规推广活动，影响力限于区域。",[235],{"name":229,"url":226},[237,26,238,239,240],"广东","再生稻","农技推广","粮食生产",{"code":31,"slug":32,"name":26,"path":33,"parent_code":34},[243],{"code":148,"slug":244,"name":245,"path":246,"parent_code":247},"extension-transfer","农技推广与成果转化","\u002Ftopic\u002Frural-services\u002Fextension-transfer","G",{"status":37,"locked":14,"version":38,"method":39,"evidence":249},{"candidates":250,"agricultural_evidence":43},[251,256,262,267],{"code":31,"score":252,"supported":43,"title":253,"abstract":254,"tags":255},27,[26,238],[26,207,238],[238,26],{"code":148,"score":257,"supported":43,"title":258,"abstract":260,"tags":261},15,[259],"技术培训",[239,259],[239],{"code":101,"score":102,"supported":43,"title":263,"abstract":264,"tags":266},[],[265],"粮食产能",[240],{"code":34,"score":21,"supported":14,"title":268,"abstract":269,"tags":270},[],[],[240],[272,273],"广东农科院 再生稻 始兴","再生稻 技术培训 观摩会","广东农科院再生稻始兴-5432","2026-10-21T00:10:01.007510Z",{"id":277,"title":278,"url":279,"summary":280,"summary_zh":281,"content":8,"source_name":282,"source_url":279,"published_at":283,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":284,"score_detail":285,"sources":288,"tags":290,"primary_topic":295,"secondary_topics":296,"classification":302,"search_phrases":336,"slug":339,"view_count":115,"doi":340,"paper":341,"created_at":356},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z",78,{"impact":18,"substance":286,"depth":18,"authority":17,"freshness":74,"relevant":21,"comment":287},22,"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[289],{"name":282,"url":279},[291,292,26,293,294],"智慧农业","农业人工智能","产量预测","遥感",{"code":31,"slug":32,"name":26,"path":33,"parent_code":34},[297],{"code":48,"slug":298,"name":299,"path":300,"parent_code":301},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":37,"locked":14,"version":38,"method":39,"evidence":303},{"candidates":304,"agricultural_evidence":43},[305,309,314,320,326,331],{"code":31,"score":257,"supported":43,"title":306,"abstract":307,"tags":308},[32],[26,32],[26],{"code":48,"score":74,"supported":43,"title":310,"abstract":311,"tags":313},[],[294,312],"remote sensing",[293,294],{"code":101,"score":60,"supported":43,"title":315,"abstract":316,"tags":319},[],[317,318],"粮食安全","food security",[],{"code":321,"score":153,"supported":43,"title":322,"abstract":323,"tags":325},"J1",[],[324],"农业规划",[],{"code":327,"score":21,"supported":14,"title":328,"abstract":329,"tags":330},"I1",[],[],[291],{"code":332,"score":21,"supported":14,"title":333,"abstract":334,"tags":335},"I2",[],[],[292],[337,338],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":340,"openalex_id":342,"authors":343,"venue":282,"cited_by_count":115,"oa_url":279,"card":349,"direction":353,"ingested_from":355},"W7222942064",[344,346],{"name":345,"orcid":8},"Nayana Venkatesh",{"name":347,"orcid":348},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":350,"method":351,"finding":352,"direction":353,"opportunity":354},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","农业遥感与作物表型","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","openalex","2026-10-20T23:30:19.292634Z",{"id":358,"title":359,"url":360,"summary":361,"summary_zh":362,"content":8,"source_name":363,"source_url":360,"published_at":364,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":365,"score_detail":366,"sources":369,"tags":371,"primary_topic":374,"secondary_topics":375,"classification":376,"search_phrases":417,"slug":420,"view_count":115,"doi":421,"paper":422,"created_at":436},5388,"A digital twin framework for proactive disease management in paddy cultivation using spatio-temporal graph neural networks","https:\u002F\u002Fdoi.org\u002F10.1080\u002F20421338.2026.2707951","Rice production is highly affected by disease outbreaks, particularly in Asian agricultural systems, resulting in major yield losses and excessive pesticide usage. This study proposes a digital twin framework for paddy cultivation that integrates predictive disease modelling with real-time crop phenology simulation to support proactive disease management. The framework utilizes historical phenological records, IoT-based microclimatic sensor data, irrigation information, and field management records collected from 150 hectares of paddy fields in Maharashtra, India. A Spatio-Temporal Graph Neural Network (ST-GNN), integrating Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks, is employed to model spatial disease propagation and temporal crop dynamics for predicting blast, brown planthopper, and bacterial leaf blight outbreaks up to 14 days in advance. Experimental results demonstrate 87.3% prediction accuracy, 23.7% reduction in pesticide usage, and 31.2% reduction in crop losses, while outperforming traditional Random Forest and SVM models in F1-score performance. The proposed framework enables real-time decision support for sustainable precision agriculture and optimized resource management.","水稻生产极易受到病害暴发的影响，在亚洲农业体系中尤为突出，造成重大产量损失和农药过度使用。本研究提出一个水稻栽培数字孪生（digital twin）框架，将预测性病害建模与实时作物物候模拟相结合，以支持主动式病害管理。该框架利用从印度马哈拉施特拉邦150公顷稻田采集的历史物候记录、基于物联网的微气候传感器数据、灌溉信息及田间管理记录。采用融合图卷积网络（Graph Convolutional Networks, GCN）与长短期记忆网络（Long Short-Term Memory, LSTM）的时空图神经网络（Spatio-Temporal Graph Neural Network, ST-GNN），对病害空间传播与作物时序动态进行建模，以提前14天预测稻瘟病、褐飞虱和白叶枯病的暴发。实验结果表明，预测准确率达87.3%，农药使用量减少23.7%，作物损失减少31.2%，且在F1分数上优于传统随机森林（Random Forest）和支持向量机（SVM）模型。所提框架可为可持续精准农业和优化资源管理提供实时决策支持。","African Journal of Science Technology Innovation and Development","2026-10-19T00:00:00Z",80,{"impact":18,"substance":286,"depth":18,"authority":128,"freshness":367,"relevant":21,"comment":368},9,"方法新颖、数据规模明确且量化效果显著，属智慧农业细分领域实质进展，值得进入每日精选。",[370],{"name":363,"url":360},[291,292,26,372,373],"数字孪生","病虫害预警",{"code":31,"slug":32,"name":26,"path":33,"parent_code":34},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":377},{"candidates":378,"agricultural_evidence":43},[379,387,392,398,405,412],{"code":327,"score":380,"supported":43,"title":381,"abstract":383,"tags":386},19,[382],"digital twin",[384,372,385,382],"精准农业","precision agriculture",[372,291],{"code":31,"score":18,"supported":43,"title":388,"abstract":390,"tags":391},[389],"paddy",[26,145,32,389],[26],{"code":158,"score":60,"supported":43,"title":393,"abstract":394,"tags":397},[],[395,396],"农药","pesticide",[],{"code":399,"score":60,"supported":43,"title":400,"abstract":401,"tags":404},"H3",[],[402,403],"灌溉","irrigation",[],{"code":406,"score":60,"supported":43,"title":407,"abstract":408,"tags":411},"I5",[],[409,410],"物联网","IoT",[],{"code":332,"score":102,"supported":43,"title":413,"abstract":414,"tags":416},[],[415],"decision support",[292],[418,419],"水稻 病害预测 数字孪生","ST-GNN 水稻 病虫害","水稻病害预测数字孪生-5388","10.1080\u002F20421338.2026.2707951",{"doi":421,"openalex_id":423,"authors":424,"venue":363,"cited_by_count":115,"oa_url":8,"card":429,"direction":435,"ingested_from":355},"W7222969403",[425,427],{"name":426,"orcid":8},"Jyoti Rani",{"name":428,"orcid":8},"Dr.  Narendra S.  Jadhav",{"tldr":430,"method":431,"finding":432,"direction":433,"opportunity":434},"构建水稻数字孪生框架，用时空图神经网络提前14天预测病害。","融合物联网微气候、物候与管理数据，用GCN+LSTM的ST-GNN建模。","预测准确率87.3%，农药减23.7%、损失减31.2%，优于RF与SVM。","农业人工智能与决策模型","可探索多尺度时空图建模与数字孪生闭环决策，并迁移至其他作物与区域。","智慧农业 \u002F 农业物联网","2026-10-20T23:30:12.636299Z"]