Frontiers in Plant Science最新文献

{"title":"Combined biochar and DMPP reduce N₂O emissions in wheat crops via microbial community modulation.","authors":"Haizhong Wu, Dengxiao Zhang, Xiaobo Shen, Guozhen Ma, Qingsong Yuan, Hongjing Zhao, Shiliang Liu, Xiaolei Jie, Daichang Wang","doi":"10.3389/fpls.2025.1647453","DOIUrl":"https://doi.org/10.3389/fpls.2025.1647453","url":null,"abstract":"<p><p>Delayed nitrogen (N) application increases N use efficiency in a broadacre cropping system. However, its effect on N₂O emissions and the underlying microbial mechanisms remains poorly understood. A field-plot experiment was carried out to examine the effects of biochar and a nitrification inhibitor (DMPP) on soil N₂O emissions with six treatments: without N application (control), optimal N application (ON), farmer conventional N application (FN), biochar + ON (ONB), DMPP + ON (OND), and biochar + OND (ONDB). In comparison to the ON treatments, cumulative N₂O emissions from the OND and ONDB treatments were significantly reduced by 32% and 38%, respectively, whereas emissions from the FN and ONB treatments exhibited increases of 38% and 4%, respectively. N application or biochar amendment increased the abundance of AOA and AOB, whereas DMPP amendment led to a reduction in AOB abundance. The OND and ONDB treatments enhanced the relative proportion of <i>Nitrospira</i> in the AOB community. The ONB treatment altered the most dominant genus of <i>nirS</i> and <i>nosZ</i> communities. Correlation analysis revealed that AOB, <i>nirK</i>, and <i>nirK/nosZ</i> were the predominant microorganism communities influencing soil N₂O emissions. Random forest analysis identified <i>Nitrospira</i> in AOB communities, <i>Cronobacter</i> in <i>nirK</i>-containing communities, and <i>Ramlibacter</i> and <i>Methylobacillus</i> in the <i>nosZ</i>-containing community as key microbial taxa contributing to N₂O emissions. We propose that the ONBD treatment provides dual advantages by reducing N₂O emissions and enhancing N use efficiency under the delayed N application regime.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1647453"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521238/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307493","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":"SegFormer-based nectar source segmentation in remote sensing imagery.","authors":"Mengting Dong, Hao Cao, Tian Zhao, Xu Zhao","doi":"10.3389/fpls.2025.1666619","DOIUrl":"https://doi.org/10.3389/fpls.2025.1666619","url":null,"abstract":"<p><strong>Introduction: </strong>Beekeepers often face challenges in accurately determining the spatial distribution of nectar-producing plants, which is crucial for informed decision-making and efficient beekeeping.</p><p><strong>Methods: </strong>In this study, we present an efficient approach for automatically identifying nectar-producing plants using remote sensing imagery. High-resolution satellite images were collected and preprocessed, and an improved segmentation model based on the SegFormer architecture was developed. The model integrates the CBAM attention mechanism, deep residual structures, and a spatial feature enhancement module to improve segmentation accuracy.</p><p><strong>Results: </strong>Experimental results on rapeseed flower images from Wuyuan County demonstrate that the improved model outperforms the baseline SegFormer model. The mean Intersection over Union (mIoU) increased from 89.31% to 91.05%, mean Pixel Accuracy (mPA) improved from 94.15% to 95.02%, and both mean Precision and mean Recall reached 95.40% and 95.02%, respectively.</p><p><strong>Discussion: </strong>The proposed method significantly enhances the efficiency and accuracy of nectar plant identification, providing real-time and reliable technical support for precision beekeeping management, smart agriculture, and ecological monitoring. It plays a key role in optimizing bee colony migration, improving collection efficiency, and regulating honey quality.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1666619"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521987/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307642","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":"Seaweed and melatonin in the induction of tolerance to recurrent water deficit in papaya.","authors":"Thayanne Rangel Ferreira, Giuseppe Tognere Polonini, Letícia Freitas Fonseca, Cristhiane Tatagiba Franco Brandão, Antelmo Ralph Falqueto, Edilson Romais Schmildt, Vinicius de Souza Oliveira, Lúcio de Oliveira Arantes, Enilton Nascimento de Santana, Sara Dousseau-Arantes","doi":"10.3389/fpls.2025.1630028","DOIUrl":"https://doi.org/10.3389/fpls.2025.1630028","url":null,"abstract":"<p><strong>Introduction: </strong>Abiotic stresses cause physiological and biochemical imbalances, such as stomatal closure, reduced photosynthesis, and changes in water balance, biomass allocation, and carbohydrate metabolism, compromising growth and, consequently, productivity. One strategy to minimize the effects of these stresses in agriculture is the use of biostimulants. Therefore, the objective of this study was to evaluate the effects of foliar applications of melatonin, <i>Ascophyllum nodosum</i>, and <i>Lithothamnium calcareum</i> on papaya plants subjected to three recurring cycles of water deficit on physiological performance, carbohydrate allocation, and vegetative growth.</p><p><strong>Methods: </strong>Three water deficit and recovery trials were conducted on 'Aliança' papaya seedlings. Before imposing the water deficit, solutions of the biological regulator melatonin and seaweed extracts from <i>A. nodosum</i> and <i>L. calcareum</i> were applied via foliar application. Water potential, chlorophyll a fluorescence, photosynthetic pigments and vegetative growth of seedlings were evaluated.</p><p><strong>Results: </strong>Seaweed and melatonin promoted increased water retention by decreasing leaf water potential and maintaining and restoring photosynthetic functions. In the second cycle of water deficit, there were significant reductions in maximum photochemical quantum yield and an increase in the energy flux dissipated per reaction center. Seaweed and melatonin also reduced total soluble sugar levels. Melatonin also promoted increased growth in specific stem length and specific root length.</p><p><strong>Discussion: </strong>Foliar applications of melatonin, <i>A. nodosum</i>, and <i>L. calcareum</i> proved effective in mitigating the effects of water deficit in papaya seedlings. Chlorophyll a fluorescence indicated that photosynthetic functionality was most affected during the second drought cycle, with inhibition of the photosynthetic apparatus during this period. Water stress reduced chlorophyll levels, possibly as a strategy to minimize photooxidative damage. Among the biostimulants tested, melatonin stood out in terms of specific stem length and specific root length growth, indicating greater adaptation to water deficit.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1630028"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521097/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307701","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":"Decoding the mystery: AI-assisted bioinformatics and functional genomics technologies in medicinal plants.","authors":"Cheng Song, Irfan Ali Sabir, Wanli Zhao, Yunpeng Cao","doi":"10.3389/fpls.2025.1678483","DOIUrl":"https://doi.org/10.3389/fpls.2025.1678483","url":null,"abstract":"","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1678483"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521232/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307664","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":"Visible-near infrared hyperspectral imaging for non-destructive estimation of leaf nitrogen content under water-saving irrigation in protected tomato cultivation.","authors":"Caixia Hu, Tingting Zhao, Yingying Duan, Yungui Zhang, Xinxiu Wang, Jie Li, Guilong Zhang","doi":"10.3389/fpls.2025.1676457","DOIUrl":"https://doi.org/10.3389/fpls.2025.1676457","url":null,"abstract":"<p><p>Accurate estimation of leaf nitrogen content (LNC) is critical for optimizing fertilization strategies in greenhouse tomato production. This study developed a robust hyperspectral-based framework for non-destructive LNC prediction by combining advanced spectral preprocessing, feature selection, and machine learning. Hyperspectral reflectance data were collected across five nitrogen and irrigation treatments over key growth stages. Signal quality was enhanced through Savitzky-Golay smoothing (SG) and Standard Normal Variate normalization (SNV). Key nitrogen-sensitive wavelengths-centered around 725 nm and 730 - 780 nm-were identified using Competitive Adaptive Reweighted Sampling (CARS) and Principal Component Analysis (PCA). Four predictive models were compared, among which a hybrid Stacked Autoencoder-Feedforward Neural Network (SAE-FNN) achieved the highest accuracy (test R² = 0.77, RPD = 2.06), effectively capturing nonlinear spectral-nitrogen interactions. In contrast, Support Vector Machine (SVM) exhibited overfitting and Partial Least Squares Method (PLSR) underperformed due to its linear constraints. These results underscore the potential of integrating hyperspectral sensing with deep learning for intelligent nitrogen monitoring in controlled-environment agriculture.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1676457"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521146/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307714","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":"Unveiling the complete organelle genomes of <i>Gypsophila vaccaria: de novo</i> assembly and evolutionary insights into a medicinally important species.","authors":"Chaoqiang Zhang, Ruifeng Yang, Mengyue Wang, Jiayin Zhang, Jingting Shen, Bin Yang, Dongzhi Zhang, Liang Yin, Xiaoming Wang, Chien-Hsun Huang, Jinglong Li","doi":"10.3389/fpls.2025.1684062","DOIUrl":"https://doi.org/10.3389/fpls.2025.1684062","url":null,"abstract":"<p><strong>Introduction: </strong><i>Gypsophila vaccaria</i> (Caryophyllaceae) is a medicinal plant with over 2,000 years of documented use in China. Despite its known pharmacological properties and phytochemical profile, no organellar genomic resources are currently available, limiting evolutionary studies and molecular breeding efforts.</p><p><strong>Methods: </strong>We assembled the complete mitochondrial (361,814 bp) and quadripartite chloroplast (150,050 bp) genomes of <i>G. vaccaria</i> using HiFi sequencing. Codon usage, RNA editing, and selection pressure were analyzed, and phylogenomic relationships were inferred. Species-specific SSR markers were identified for potential molecular applications.</p><p><strong>Results: </strong>HiFi-based assembly revealed exceptional mitochondrial genome plasticity, with 15.6% (56.7 Kb) derived from chloroplast DNA transfers-the highest reported in Caryophyllaceae-including 12 functional genes (e.g., rps7, ndhB, rrn16S). Both organellar genomes show A/U-biased codon usage (mitochondrial RSCU: 29/44 codons) and divergent RNA editing (257 mitochondrial vs. 105 chloroplast C-to-U sites). Positive selection (Ka/Ks > 1) was detected in cytochrome c maturation genes (ccmFN, ccmB, ccmFC), contrasting with overall purifying selection (median ω = 0.32). Phylogenomic analyses robustly resolved Caryophyllaceae-Amaranthaceae sisterhood (BS = 100%).</p><p><strong>Discussion: </strong>As the first organellar genomes from Gypsophila, this study provides insights into lineage-specific adaptations through chloroplast-mitochondrial co-evolution. The 56.7 Kb MTPTs and positively selected cytochrome c genes serve as targets for adaptive evolution research, while 81 species-specific SSRs facilitate molecular marker development in Caryophyllaceae.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1684062"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521989/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307729","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":"Litter quality outweighs climate in driving grassland root decomposition.","authors":"Jingjing Yang, Zhanbo Yang, Runzhi Zhang, Pingting Guan, Taihai Xu, Yao Tang, Guoling Ren","doi":"10.3389/fpls.2025.1639369","DOIUrl":"https://doi.org/10.3389/fpls.2025.1639369","url":null,"abstract":"<p><strong>Introduction: </strong>Root decomposition plays a critical role in nutrient cycling and carbon storage in grassland ecosystems, yet its global drivers remain poorly understood.</p><p><strong>Methods: </strong>The study synthesized global data on root decomposition in grasslands to assess the relative importance of climate and litter quality, and to quantify the effects of environmental and biotic factors using a comprehensive meta-analysis.</p><p><strong>Results: </strong>Results indicated that, at the global scale, litter quality exerted a stronger influence on root decomposition than climatic variables. Random forest analysis identified the ratio of acid-unhydrolyzable residue to nitrogen (AUR:N) and AUR as the most important predictors of mass loss, both of which were significantly and negatively correlated with mass loss. The meta-analysis further demonstrated that both environmental and biotic factors significantly affected root decomposition. Among environmental factors, nitrogen addition (+4.49%), phosphorus addition (+16.26%), warming (+9.80%), increased precipitation (+5.95%), and elevated CO₂ (+14.03%) were found to promote root decomposition, while reduced precipitation (-15.60%) had the negative effect. With respect to biotic factors, grazing (+7.51%) significantly increased decomposition, whereas vegetated soil (-27.84%), increased plant species richness (-4.99%), increased root litter richness (-5.93%), home-field decomposition (-4.34%), and soil biota exclusion (-10.40%) decreased it.</p><p><strong>Discussion: </strong>These findings highlight the dominant role of litter quality over climate in regulating root decomposition at a global scale, and underscore the sensitivity of belowground processes to environmental and biotic disturbances in grassland ecosystems.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1639369"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521445/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307706","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 role of auxin transport through plasmodesmata in leaf vein canalization and patterning.","authors":"David M Holloway, Trausti K Eiriksson, Carol L Wenzel","doi":"10.3389/fpls.2025.1621815","DOIUrl":"https://doi.org/10.3389/fpls.2025.1621815","url":null,"abstract":"<p><p>Vein patterns in plant leaves are preceded by high concentration localized tracks of the phytohormone auxin. Auxin regulates downstream genes involved in vascular differentiation. Proposals for the mechanisms by which auxin canalizes from broad early distributions to later narrow provascular tracks have been made for many decades and tested in mathematical models. These have focused on PIN1, a membrane-bound protein involved in exporting auxin from cells. <i>PIN</i> mutations and interference with polar auxin transport (PAT) through PIN have strong effects on vein patterns. However, recent experiments show that even with PIN-dependent PAT presumably shut off, veins form and extend, albeit with altered patterning. This residual canalization and vein patterning has a dependence on flow through plasmodesmata (PD) intercellular channels. We developed a new mathematical framework for the regulation of auxin flow through both PIN and PD. This produces better fits to data than prior PIN-only models, especially with respect to vein number, directionality and extension in reduced PIN transport conditions. Varying PD area recapitulates known experimental results with PD mutants, in particular the loss of canalization at high PD permeability. Model parameters are consistent with measured permeabilities and predict effects for future experiments. This work updates the canalization hypothesis for auxin provascular strand formation in early leaf development in terms of the contributions from both PIN and PD.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1621815"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12523058/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307712","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":"Advances in WRKY regulation of immune responses in medicinal plants.","authors":"Xinying Zhong, Nana Chen, Hongwei Li, Yaxuan Wang, Ziyi Guo, Guiyuan Shi, Xingkai Zhan, Lin Li","doi":"10.3389/fpls.2025.1659732","DOIUrl":"https://doi.org/10.3389/fpls.2025.1659732","url":null,"abstract":"<p><p>Medicinal plants serve as a crucial source of traditional Chinese medicine and have garnered considerable attention due to their unique bioactive compounds and notable pharmacological properties. However, during natural growth, these plants are frequently susceptible to infection by various pathogenic microorganisms, pests and nematodes, leading to reduced yields and inconsistent accumulation of medicinal compounds, thereby significantly limiting their resource development and utilization. WRKY transcription factors (TFs) are central regulators of plant immunity that integrate pathogen-perception signals, coordinate signaling pathways, and transcriptionally control defense-gene expression<b>.</b> This review provides a systematic synthesis of current knowledge on the regulatory mechanisms of WRKY TFs in the immune responses of medicinal plants. Emphasis is placed on their roles in cellular metabolic regulation, activation of Mitogen-Activated Protein Kinase (MAPK) signaling pathways, integration of phytohormone signaling, and the biosynthesis of secondary metabolites. In addition, we highlight that WRKY TFs orchestrate immune responses at multiple levels through epigenetic mechanisms, including DNA methylation and histone modifications. Furthermore, it is proposed that transgenic approaches and Cut-Dip-Budding (CDB)-mediated transformation be integrated with gene editing technologies such as Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR), in conjunction with artificial intelligence (AI)-assisted identification of key regulatory elements. This integrated strategy offers novel insights and theoretical support for establishing efficient immune regulatory networks and breeding disease-resistant medicinal plant varieties.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1659732"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521257/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307827","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":"Early detection and severity classification of verticillium wilt in cotton stems using Raman spectroscopy and machine learning.","authors":"Xuanzhang Wang, Jianan Chi, Xiao Zhang, Guangshuai Lu, Xuan Li, Chunli Wang, Lijun Wang, Nannan Zhang","doi":"10.3389/fpls.2025.1649295","DOIUrl":"https://doi.org/10.3389/fpls.2025.1649295","url":null,"abstract":"<p><p>The early detection of Verticillium wilt (VW) in cotton is a critical challenge in agricultural disease management. Cotton, a vital global textile resource, is severely threatened by this devastating disease. Traditional diagnostic methods, which often rely on manual expertise or destructive sampling, are limited by low efficiency and high subjectivity. In recent years, Raman spectroscopy has emerged as a promising solution due to its rapid, non-destructive, and highly sensitive characteristics for plant disease detection. In this study, we analyzed cotton stems using Raman spectroscopy, applying Savitzky-Golay (SG) smoothing combined with multiple preprocessing methods including Scaling and Shifting (SS), Standard Normal Variate (SNV), inverse first-order differential (1/SG)', and multiplicative scatter correction (MSC). For baseline correction, we employed polynomial fitting (PolyFit) and adaptive iterative weighted penalized least squares (airPLS). Feature selection was performed using principal component analysis (PCA), successive projection algorithm (SPA), and competitive adaptive reweighted sampling (CARS).Three optimized models were developed: support vector machine (SVM) with weighted mean of vectors (INFO) algorithm, random forest (RF) enhanced by particle swarm optimization (PSO), and long short-term memory (LSTM) network optimized via chameleon swarm algorithm (CSA).The results show that the INFO-SVM model with SG-airPLS-(1/SG)' -CARS preprocessing demonstrated superior performance, achieving 97.5% accuracy (0.974 F1-score) on training data and 90.0% accuracy (0.867 F1-score) on validation data, outperforming both PSO-RF and CSA-LSTM models. These results confirm that Raman spectroscopy integrated with optimized machine learning enables accurate VW classification in cotton stems. This method enables early disease detection during infection, facilitating timely fungicide application and reducing yield losses.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1649295"},"PeriodicalIF":4.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12521921/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145307693","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}