Plant Methods最新文献

{"title":"Comparative analysis of distinct phenotyping methods for assessing wheat resistance and pathogen virulence among Fusarium species causing head blight disease.","authors":"Vahideh Rafiei, Liza DeGenring, Erin M Schwister, James Mitch Elmore, Mukesh Dubey, Magnus Karlsson, Milton T Drott","doi":"10.1186/s13007-025-01402-8","DOIUrl":"10.1186/s13007-025-01402-8","url":null,"abstract":"<p><p>Developing disease-resistant crops is a critical strategy for reducing chemical treatments and mitigating plant disease outbreaks, particularly amid global environmental changes. Fusarium head blight (FHB), caused by a complex of Fusarium species, is one of the most devastating cereal diseases, leading to significant economic losses and contamination of grain with harmful mycotoxins that threaten global cereal production and human health. The high variability in virulence within the complex of Fusarium spp and the lack of efficient high-throughput screening methods have impeded the development of resistant cultivars and made large-scale virulence testing labor-intensive and time-consuming. This study evaluates the efficacy of detached leaf, coleoptile, and seedling assays as high-throughput alternatives to the standard head infection assay for assessing the virulence of Fusarium species and differentiating wheat genotypes by resistance or susceptibility. Two near-isogenic wheat lines, one carrying FHB resistance loci and the other without, were used to assess the virulence of four Fusarium species. The seedling and coleoptile assays showed strong concordance with the traditional head infection assay, accurately reflecting differences in disease severity across Fusarium species and between wheat lines. Conversely, the detached leaf assay provided some differentiation among species but was inconsistent in identifying differences between plant genotypes. Across all assays, F. graminearum consistently exhibited the highest virulence, causing severe disease in leaves, stems, seedlings, and heads, while F. poae was the least virulent. Interestingly, F. culmorum and F. avenaceum displayed tissue-specific variability. These findings establish the coleoptile and seedling assays as rapid, high-throughput alternatives for breeding programs, accelerating the identification of FHB-resistant genotypes and reducing the reliance on the labor-intensive head assay.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"85"},"PeriodicalIF":4.7,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12168331/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144310286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Bayesian mixture expert recognition model for tobacco leaf curing stages based on feature fusion.","authors":"Panzhen Zhao, Shijiang Duan, Songfeng Wang, Aihua Wang, Lingfeng Meng, Zhicheng Wang, Yingpeng Dai","doi":"10.1186/s13007-025-01384-7","DOIUrl":"10.1186/s13007-025-01384-7","url":null,"abstract":"<p><p>The diverse visual features of tobacco leaves during various curing stages are influenced by multiple factors such as the origin of the tobacco and the environment of the curing room, making precise identification challenging with single features or models. To address this issue, this study proposes a Bayesian Mixture Expert Recognition Model for Tobacco Leaf Curing Stages based on feature fusion. First, deep learning models (ResNet34, MobileNetV2, EfficientNetb0) are utilized to extract deep features and traditional features positively correlated with curing stages from a constructed tobacco leaf image dataset. Various feature fusion methods (concatenate fusion, scaled fusion, adaptive gated fusion) are employed to construct multi-level feature representations. Next, different feature fusion methods of the same model are optimized to select the best-performing model as the foundational model for ensemble learning. Finally, Bayesian optimization is applied to integrate three optimized models, and comparisons are made with voting and weighted averaging methods. The proposed model achieves a recognition accuracy of 93.96% on the test set, with other performance metrics surpassing those of the base models. This research efficiently captures and robustly recognizes the complex dynamic visual features of the tobacco curing process through the integration of diverse features, adaptive adjustments, and expert collaboration mechanisms, thereby enhancing the system's adaptability and interpretability in complex environments. This provides strong support for the intelligent upgrading of the tobacco industry.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"86"},"PeriodicalIF":4.7,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12168287/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144310287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rapid Ragi: A speed breeding protocol for finger millet.","authors":"Sobhan Sajja, Jwala Pranati, S Shyamala, K S Vinutha, Ramya Reddy, Priyanka Joshi, Srinivasulu Pannem, P Rakshit, Yashoda Jadhav, C V Sameer Kumar, Sean Mayes","doi":"10.1186/s13007-025-01403-7","DOIUrl":"10.1186/s13007-025-01403-7","url":null,"abstract":"<p><strong>Background: </strong>Climate change is gradually increasing demand for resilient, nutritious crops like finger millet or ragi. Ensuring food security requires researchers to develop improved and adapted cultivars rapidly. Modern techniques such as genomics-assisted breeding have emerged in the previous decade and combined with rapid generation advancement they will offer a step change in the speed of cultivar development.</p><p><strong>Results: </strong>In this study, we developed a repeatable and cost-effective speed breeding protocol for finger millet by modulating the agronomic and physiological components for early generation advancement. A photoperiod of 9-hours, 29 ± 2℃ temperature, 70% relative humidity, 105 plants per 1.5 sq. ft., 0.17% Hoagland's No. 2 solution spray, restricted irrigation and harvesting at physiological maturity successfully reduced 28-54 days across the maturity groups of finger millet. The advantage was validated in segregating populations confirming up to 4-5 generations a year, instead of 1-2 under field conditions.</p><p><strong>Conclusion: </strong>The speed breeding protocol developed reduces the breeding cycle time significantly allowing increased genetic gain. The protocol provides the advantage of rapid development of recombinant inbred lines (RILs), high-throughput phenotyping for biotic and abiotic stresses, and genotyping for early generation selections.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"84"},"PeriodicalIF":4.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12160354/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144286114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of TuMV by a toehold switch sensor coupled with NASBA amplification in Pseudostellaria heterophylla.","authors":"Yun Qiu, Shuxin Zhang, Aidi Tan, Qiang Cai, Kezhi Chen, Kaiwen Yang, Yanyang Jiao, Qiuting Lai, Chenjing Zhang, Sheng Lin, Wenxiong Lin, Xuelian Yang, Wenfei Wang","doi":"10.1186/s13007-025-01394-5","DOIUrl":"10.1186/s13007-025-01394-5","url":null,"abstract":"<p><p>Pseudostellaria heterophylla (P. heterophylla) is a perennial herb that has been used as a medicinal food for hundreds of years in China. Viral infections during the production of P. heterophylla severely reduce the yield and quality. Turnip mosaic virus (TuMV) is a common and highly variable viral pathogen in P. heterophylla plants. A high-efficiency diagnostic system is urgently needed to control and alleviate TuMV infection. However, the current detection methods still have various deficiencies that limit their field application. Here, a cell-free expression system relying on nucleic acid sequence-based amplification (NASBA) with toehold switch sensors and a visual reporter for color change was developed and introduced for TuMV detection in P. heterophylla. After designing and screening the approach, the selected sensitive sensor was able to detect 1 pM TuMV RNA fragments within 40 min, and the detection limit was less than 10 fM if the time was extended to 90 min. The sensor exhibited high specificity, with no cross-reactivity detected when tested against cucumber mosaic virus, another prevalent viral pathogen in P. heterophylla. In addition, in in-field samples, TuMV was successfully detected directly from both purified and crude RNA extracts in approximately 3 h. This cell-free synthetic biology tool is rapid, sensitive, specific and field-applicable and provides high-capacity and low-cost diagnostics for TuMV in P. heterophylla, as well as various viruses in herbs and other host plants.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"81"},"PeriodicalIF":4.7,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12147267/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144258618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pod-pose : an efficient top-down keypoint detection model for fine-grained pod phenotyping in mature soybean.","authors":"Fei Liu, Hang Liu, Qiong Wu, Zhongzhi Han, Shanchen Pang, Shudong Wang, Longgang Zhao","doi":"10.1186/s13007-025-01399-0","DOIUrl":"10.1186/s13007-025-01399-0","url":null,"abstract":"<p><strong>Background: </strong>Phenotypic characterization of mature soybean pods is a crucial aspect of breeding programs, yet efficiently obtaining accurate pod phenotypic parameters remains a major challenge. Recent advances in deep learning, particularly in keypoint detection models, have introduced innovative methods for pod phenotype extraction. However, precise identification and analysis of fine-scale phenotypic traits in soybean pods remain challenging in current research.</p><p><strong>Results: </strong>We propose Pod-pose, an innovative top-down keypoint detection model for precise soybean pod phenotyping that adapts human pose estimation techniques to plant phenotyping. Specifically, Pod-pose integrates the architectural strengths of various advanced YOLO (You Only Look Once) models through bottleneck structure optimization and positional feature enhancement to achieve superior detection accuracy. Furthermore, we implemented a two-stage detection method augmented with transfer learning, which not only reduces training complexity but also significantly enhances the model's performance. Extensive evaluation of our custom-built dataset demonstrated Pod-Pose's superior performance, with the X variant achieving an Average Precision of 0.912 at an IoU threshold of 0.5 (AP@IoU = 0.5). Notably, four critical pod-related phenotypic traits were successfully quantified: pod length, bending length, curvature, and inflection point width.</p><p><strong>Conclusions: </strong>This study establishes Pod-Pose as a viable solution for pod phenotyping, with potential applications in soybean breeding optimization.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"82"},"PeriodicalIF":4.7,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12147338/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144258619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CRISPR-Cas13a as a next-generation tool for rapid and precise plant RNA virus diagnostics.","authors":"Marzieh Karimi, Abozar Ghorbani, Ali Niazi, Mahsa Rostami, Ahmad Tahmasebi","doi":"10.1186/s13007-025-01401-9","DOIUrl":"10.1186/s13007-025-01401-9","url":null,"abstract":"<p><p>Plant viruses are among the most serious threats to global agriculture, causing significant yield losses and jeopardizing food security. Identifying these viruses is crucial to prevent widespread crop damage and ensure effective management. CRISPR-Cas13a, a subtype of the RNA-targeting Cas13 family, has emerged as a transformative tool in molecular diagnostics, specifically tailored to detect these plant RNA viruses with unparalleled precision. Unlike traditional methods such as ELISA and RT-PCR, which are often limited by sensitivity, equipment dependency, and long processing times, Cas13a offers exceptional specificity and attomolar-level sensitivity. Its RNA-guided collateral cleavage mechanism allows signal amplification, making it particularly suitable for field-deployable diagnostics. Recent advances in Cas13 engineering, including compact variants such as Cas13bt3 and Cas13Y, have further improved its delivery efficiency and minimized immune responses, enhancing its agricultural applications. Integration with amplification methods like LAMP and innovative biosensor platforms like graphene-based and electrochemical systems further enhances its diagnostic potential. While challenges remain, including off-target effects, reagent stability, and scalability, innovations in CRISPR RNA (crRNA) design, reagent encapsulation, and microfluidic technologies are actively addressing these barriers. CRISPR-Cas13a represents a cutting-edge solution for rapid, accurate, and accessible plant virus diagnostics, providing a powerful safeguard for crop yields and global food security.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"83"},"PeriodicalIF":4.7,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12150587/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144258617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Earlier quantification of rice blast impact via instantaneous chlorophyll fluorescence.","authors":"Insu Yeon, Jihyeon Yeo, Yejin Park, Ghiseok Kim, Jae Hoon Lee, Hyungsuk Kimm","doi":"10.1186/s13007-025-01391-8","DOIUrl":"10.1186/s13007-025-01391-8","url":null,"abstract":"<p><strong>Background: </strong>Rice blast, one of the major diseases causing significant rice yield loss, downregulates the photosynthetic activity and induces aggressive spread of cell death causing food security concerns. Hence, earlier quantification of rice blast is imperative for improved management of the disease. Instantaneous chlorophyll fluorescence (e.g., sun-induced chlorophyll fluorescence under sunlight), which is mechanistically linked with photosynthesis at the photosystem scale, has shown the potential for quantifying the impact of abiotic stresses on plant physiology but remains yet to be tested for biotic stresses. Here, we assessed the potential of chlorophyll fluorescence (CF) for quantifying rice blast impact on plant physiology. In particular, we further retrieved the quantum yield of chlorophyll fluorescence (Φ_F) by normalizing the influence of the magnitude of incident radiation.</p><p><strong>Results: </strong>Φ_F sensitively responded to rice blast within 24 and 96 hours post-inoculation for susceptible and resistant cultivars, respectively. We confirmed that the Φ_F showed strong sensitivity in response to different doses of inoculation and to cultivar difference. In addition to Φ_F results, we further investigated the role of red to far-red CF ratio (CF_R:FR) in rice blast detection. CF_R:FR, which was previously reported to be tightly coupled with chlorophyll contents, captured the impact of rice blast inoculation to some extent while green chlorophyll vegetation index did not show any difference across all inoculated groups.</p><p><strong>Conclusions: </strong>We confirmed that the Φ_F sensitively responded to rice blast inoculation and differentiated two dose levels of inoculation and low- and high-resistance levels via the comparison of two cultivars. Furthermore, the full spectrum of chlorophyll fluorescence was used to obtain the red to far-red CF ratio and showed its capability for indicating the physiological impact of rice blast. Our findings highlight the unique role of chlorophyll fluorescence in sensitively quantifying rice blast impact. Our approach is highly scalable through sun-induced chlorophyll fluorescence observations and thus will contribute to improving the large-scale management of rice blast.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"80"},"PeriodicalIF":4.7,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12142957/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144234802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Small sample amounts from rhizosphere of barley maintain microbial community structure and diversity revealed by total RNA sequencing.","authors":"Nikolaj L Kindtler, Sanea Sheikh, Athanasios Zervas, Lea Ellegaard-Jensen, Louise Feld, Maria Scheel, Francisco Campuzano Jiménez, Rute R da Fonseca, Kristian H Laursen, Carsten S Jacobsen, Flemming Ekelund","doi":"10.1186/s13007-025-01397-2","DOIUrl":"10.1186/s13007-025-01397-2","url":null,"abstract":"<p><p>Total RNA sequencing is a crucial technique in microbial ecology for profiling active microbial communities in various environments, including the rhizosphere. Since total RNA sequencing yields both 16 S and 18 S ribosomal RNA (rRNA), it is effective for taxonomic profiling of the full microbial community in a sample. However, the effectiveness of this approach with limited initial sample amounts remains unclear. In this study, we grew barley in a growth system designed for highly controlled plant experiments using an inert growth medium inoculated with a soil microbiome. Our objectives were two-fold: firstly, to test the feasibility of extracting total RNA from the rhizosphere of barley grown in an inert growth medium consisting of sand and perlite. Secondly, we aimed to address the challenge of extracting comprehensive taxonomic information from minimal amounts of rhizosphere samples from barley plants, using three different amounts of freeze-dried rhizosphere material: 10, 40, and 200 mg. We showed that although smaller sample amounts yielded lower concentrations of extracted RNA, this did not significantly influence the diversity or composition of the rhizosphere microbiome as indicated by SSU rRNA. Our results demonstrate that total RNA sequencing, focusing on SSU rRNA, robustly captures the taxonomic diversity of active rhizosphere microbial communities, even in small initial sample amounts. Effective use of smaller samples opens new possibilities for detailed studies in environments where sample quantity is limited. We also conclude that the growth system applied in this experiment is suitable for highly controlled plant experiments focusing on total RNA extraction from the rhizosphere.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"79"},"PeriodicalIF":4.7,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12135520/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144216580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leaf spectroscopy as a tool for predicting the presence of isoprene emissions and terpene storage in central Amazon forest trees.","authors":"Michelle Robin, Flavia Machado Durgante, Caroline Lorenci Mallmann, Hilana Louise Hadlich, Christine Römermann, Lucas de Souza Falcão, Caroline Dutra Lacerda, Sérgio Duvoisin, Florian Wittmann, Maria Teresa Fernandez Piedade, Jochen Schöngart, Eliane Gomes Alves","doi":"10.1186/s13007-025-01400-w","DOIUrl":"10.1186/s13007-025-01400-w","url":null,"abstract":"<p><strong>Background: </strong>Volatile isoprenoids (VIs), such as isoprene, monoterpenes, and sesquiterpenes, participate in various forest-atmosphere processes ranging from plant cell regulation to atmospheric particle formation. The Amazon Forest is the greatest and most diverse source of VI emissions, but the lack of leaf-level studies and the logistical challenges of measuring in such remote and highly biodiverse sites bring high levels of uncertainty to modeled emission estimates. Studies indicate that leaf spectroscopy is an effective tool for estimating leaf morphological, physiological, and chemical traits, being a promising tool for more easily assessing VI emissions from vegetation. In this study, we tested the ability of leaf reflectance spectroscopy to predict the presence of VI emissions and storage in central Amazon Forest trees. We measured leaf-level isoprene emission capacity (E_c; emission measured at standard conditions: light of 1000 µmol m^- 2 s^- 1 photosynthetically active radiation and leaf temperature of 30 ˚C), stored monoterpene and sesquiterpene contents, and hyperspectral visible to short-wave infrared (VSWIR) reflectance from dry and fresh leaves of 175 trees from 124 species of angiosperms.</p><p><strong>Results: </strong>We found that dry leaf hyperspectral reflectance data, and fresh leaf reflectance measured at selected wavelengths (616, 694, and 1155 nm), predicted the presence of isoprene emissions with accuracies of 0.67 and 0.72, respectively. Meanwhile, fresh leaf hyperspectral reflectance data predicted monoterpene and sesquiterpene storage with accuracies of 0.65 and 0.67, respectively.</p><p><strong>Conclusions: </strong>Our results indicate the possibility of using spectral readings from botanical collections or field inventories to orient sampling efforts toward potential isoprene-emitting or terpene-storing trees, or to identify key spectral features (most informative selected wavelengths) for potential future incorporation into remote sensing models. The use of spectral tools for detecting potential isoprene-emitting and terpene-storing species can help to improve current VI emission datasets, reduce modeling emission uncertainties, and contribute to a better understanding of the roles of VIs within forest-atmosphere interactions, atmospheric chemistry, and the carbon cycle.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"78"},"PeriodicalIF":4.7,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12135534/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144216579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology.","authors":"Qi Wang, Jinzhu Lu, Yuanhong Wang, Fajun Miao, Senping Liu, Qiyang Shui, Junfeng Gao, Yingwang Gao","doi":"10.1186/s13007-025-01354-z","DOIUrl":"10.1186/s13007-025-01354-z","url":null,"abstract":"<p><p>Rapid and accurate assessment of the citrus ripening stage in the field is important for determining harvest timing and improving industrial economic efficiency; however, the lack of effective nondestructive detection methods in the current orchard leads to flaws in ripening stage assessment, which affects harvesting decisions. To solve this problem, this study utilized hyperspectral technology to collect data from 22 fruit trees in an orchard (in the range of 400-1000 nm) and explored the effectiveness of five regions of interest selection methods (x-axis, y-axis, four-quadrant, threshold segmentation, and raw) for the delineation of the citrus ripening stage. The data quality was enhanced via wavelet transform (WT)-multiple scattering correction (MSC) preprocessing, and the effective wavelengths were extracted via the successive projections algorithm (SPA). On the basis of these wavelengths, backpropagation neural network (BP) and convolutional neural network (CNN) models were built for maturity prediction. The results show that the x-axis region of interest selection method outperforms the other methods, and the SPA-BP model based on this method performs best. An accuracy of 99.19% for the correction set and 100% for the prediction set was achieved when only 0.03% of the wavelength was used. This groundbreaking study highlights the significant potential of hyperspectral technology for in situ assessment of citrus ripening stages. Furthermore, it offers crucial technical support and serves as a valuable reference for the advancement of precision agriculture.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"77"},"PeriodicalIF":4.7,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12131661/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144216578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}