Frontiers in Plant Science最新文献

{"title":"Optimizing plant density to improve the soil microenvironment and enhance crop productivity in cotton/cumin intercropping systems.","authors":"Humei Zhang, Liwen Tian, Xianzhe Hao, Nannan Li, Xiaojuan Shi, Feng Shi, Yu Tian, Wenbo Wang, Honghai Luo","doi":"10.3389/fpls.2025.1533211","DOIUrl":"https://doi.org/10.3389/fpls.2025.1533211","url":null,"abstract":"<p><strong>Introduction: </strong>Residual film pollution has become a key factor that affects the sustainable development of cotton, and intercropping may be an economical and environmentally friendly method to reduce the negative effects of nonmulched conditions on cotton growth. We hypothesized that optimizing the cotton/cumin intercropping density would improve the soil environment and increase crop productivity and resource utilization.</p><p><strong>Methods: </strong>Therefore, in this study, singlecropping cotton (CK) was used as the control, and three intercropping cumin seeding densities were used (plants ha^-1: 5×10⁵, ID1; 8×10⁵, ID2; and 11×10⁵, ID3). Through a two-year field experiment, the effects of cotton-cumin intercropping on the soil moisture, temperature, salt, respiration rate, weed density, cotton yield formation and intercropping advantages were studied.</p><p><strong>Results and discussion: </strong>Compared with the CK treatment, the ID2 treatment decreased the water content in the 0-30 cm soil layer by 8.3%, increased the water consumption by 9.1%, increased the soil temperature by 0.5°C, and decreased the electrical conductivity of the 0-15 cm soil layer by 17.7%. Compared with the CK treatment, the ID1 treatment significantly decreased the soil respiration rate by 33.6%, and the weed density decreased in the following order: CK>ID1>ID2>ID3. During the nonsymbiotic period, compared with CK, ID2 increased the soil water content by 5.7%, increased the soil respiration rate by 17.7%, and decreased the electrical conductivity by 15.6%. Compared with those for CK and ID3, the seed yield for ID2 increased by 2.0% and 5.8%, respectively, and that for ID1 decreased by 1.6%. However, the land equivalent of the ID2 treatment was 4.3% greater than that for the ID1 treatment. Therefore, intercropping cumin at a density of 8×10⁵ plants ha^-1 is beneficial for increasing surface coverage, significantly increasing crop water consumption, increasing surface temperature, reducing soil electrical conductivity and carbon emissions, and improving the crop yield and economic benefits. This model can be used as an agroecologically friendly and sustainable planting model.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1533211"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11848522/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491743","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":"Evaluation of novel fungicides (FRAC groups 7, 9, 12) for managing cranberry fruit rot.","authors":"Leela Saisree Uppala, Salisu Sulley","doi":"10.3389/fpls.2024.1508744","DOIUrl":"https://doi.org/10.3389/fpls.2024.1508744","url":null,"abstract":"<p><p>Cranberry fruit rot (CFR) is a major disease complex that significantly impacts cranberry crops, leading to substantial yield losses. Over the past decade, CFR has become increasingly problematic, particularly in high-yielding and newer cultivars, with reported losses ranging from 50% to 100%. Additionally, the cranberry industry faces increasing restrictions on the use of broad-spectrum fungicides, such as chlorothalonil and mancozeb, necessitating the exploration of alternative management strategies. This study, conducted from 2021 to 2024 at the University of Massachusetts-Amherst Cranberry Station, evaluated novel fungicides from FRAC Groups 7, 9, and 12. The active ingredients-benzovindiflupyr, pydiflumetofen, cyprodinil, and fludioxonil-were tested individually and in combination with azoxystrobin (FRAC 11). The efficacy of these fungicides in reducing CFR incidence and improving yield was assessed on cranberry cultivars 'Demoranville', 'Ben Lear,' and 'Stevens' with applications made at early, mid, and late bloom stages. Significant differences in fruit rot incidence and yield were observed in 2021, 2023 and 2024. Treatments containing pydiflumetofen, pydiflumetofen & fludioxonil, and benzovindiflupyr, when applied in combination with azoxystrobin, consistently resulted in lower rot incidence and higher yields. The treatment containing cyprodinil & fludioxonil plus azoxystrobin, tested only in 2021, also resulted in lower rot incidence and higher yield. These findings highlight the potential of novel fungicides from FRAC Groups 7, 9, and 12 as effective alternatives for CFR management. Their use could diversify the CFR management toolkit, mitigate fungicide resistance, and reduce environmental impacts, addressing the challenges posed by increasing fungicide regulations.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1508744"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847797/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491737","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":"Duckweed: a starch-hyperaccumulating plant under cultivation with a combination of nutrient limitation and elevated CO₂.","authors":"Ling Guo, Yang Fang, Songhu Wang, Yao Xiao, Yanqiang Ding, Yanling Jin, Xueping Tian, Anping Du, Zhihua Liao, Kaize He, Shuang Chen, Yonggui Zhao, Li Tan, Zhuolin Yi, Yuqing Che, Lanchai Chen, Jinmeng Li, Leyi Zhao, Peng Zhang, Zhengbiao Gu, Fangyuan Zhang, Yan Hong, Qing Zhang, Hai Zhao","doi":"10.3389/fpls.2025.1531849","DOIUrl":"https://doi.org/10.3389/fpls.2025.1531849","url":null,"abstract":"<p><strong>Introduction: </strong>The increasing global demand for starch has created an urgent need to identify more efficient and sustainable production methods. However, traditional starch sources, such as crop-based options, experience significant bottlenecks due to limitations in land use, water consumption, and the impacts of climate change. Therefore, there is a pressing need to explore and develop new sources of starch.</p><p><strong>Methods: </strong>We develop a novel duckweed cultivation technology that combines nutrients limitation and CO₂ supplementation to achieve very high starch content. In this study, we integrated whole-genome sequencing, epigenomics, transcriptomics, enzyme activity, and composition variation to elucidate the mechanisms of efficient starch accumulation in duckweed in terms of starch accumulation and carbon partitioning, regulation of the expression of genes in the starch metabolic pathway, and sucrose biosynthesis and transportation.</p><p><strong>Results and discussion: </strong>Although <i>Landoltia punctata</i> exhibits dramatic gene family contraction, its starch content and productivity reached 72.2% (dry basis) and 10.4 g m^-2 d^-1, respectively, in 10 days, equivalent to a yield of 38.0 t ha^-1 y^-1, under nutrient limitation treatment with elevated CO₂ levels. We also examined the mechanism of high starch accumulation in duckweed. This phenomenon is associated with the regulation of DNA methylation and transcription factors as well as the significantly upregulated transcription levels and the increased activities of key enzymes involved in starch biosynthesis. Moreover, while nitrogen redistribution was increased, sucrose biosynthesis and transportation and lignocellulose biosynthesis were reduced. These alterations led to a reduction in lignocellulose and protein contents and ultimately an increase in the accumulation of starch in the chloroplasts.</p><p><strong>Conclusion: </strong>This work demonstrates the potential of duckweed as a highly efficient starch producer.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1531849"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847889/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491740","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":"Differential expression and localization of expansins in <i>Arabidopsis</i> shoots: implications for cell wall dynamics and drought tolerance.","authors":"Darina Balkova, Katerina Mala, Jan Hejatko, Klara Panzarova, Lamis Abdelhakim, Barbora Pleskacova, Marketa Samalova","doi":"10.3389/fpls.2025.1546819","DOIUrl":"https://doi.org/10.3389/fpls.2025.1546819","url":null,"abstract":"<p><p>Expansins are cell wall-modifying proteins implicated in plant growth and stress responses. In this study, we explored the differential localization of expansins in <i>Arabidopsis thaliana</i> shoots, with a focus on <i>EXPA1, EXPA10, EXPA14</i>, and <i>EXPA15</i> utilizing <i>pEXPA::EXPA</i> translational fusion lines. Employing the chemically inducible system pOp6/LhGR for <i>EXPA1</i> overexpression and high-throughput automatic phenotyping we evaluated the drought response and photosynthetic efficiency under stress conditions. We observed distinct expression patterns of expansins, with <i>EXPA1</i> primarily localized in stomatal guard cells, while <i>EXPA10</i> and <i>EXPA15</i> showed strong cell wall (CW) localization in epidermal and other tissues. Overexpression of <i>EXPA1</i> resulted in pronounced changes in CW-related gene expression, particularly during early stages of induction, including the upregulation of other expansins and CW-modifying enzymes. The induced <i>EXPA1</i> line also displayed significant morphological changes in shoots, including smaller plant size, delayed senescence, and structural alterations in vascular tissues. Additionally, <i>EXPA1</i> overexpression conferred drought tolerance, as evidenced by enhanced photosynthetic efficiency (F_v/F_M), and low steady-state non-photochemical quenching (NPQ) values under drought stress. These findings highlight the critical role of <i>EXPA1</i> in regulating plant growth, development, and stress response, with potential applications in improving drought tolerance in crops.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1546819"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847903/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491739","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":"Interactions between N, P in the overlying water and flooding-induced decomposition of <i>Cynodon dactylon</i> in the water-level fluctuation zone.","authors":"Jitao Huang, Ze Luo, Zuopeng Xu, Yanxue Jiang, Jinsong Guo","doi":"10.3389/fpls.2025.1526507","DOIUrl":"https://doi.org/10.3389/fpls.2025.1526507","url":null,"abstract":"<p><p>During flooding in the Water Level Fluctuation Zone (WLFZ), nutrient levels of nitrogen (N) and phosphorus (P) in the overlying water fluctuate due to soil nutrient release, impacting the decomposition of plants like <i>Cynodon dactylon</i>. However, limited research on the effects of these nutrient changes on plant nutrient release and water dynamics complicates accurate assessments of water quality impacts. This study used 8 water samples with varying initial nutrient levels to simulate N and P changes induced by WLFZ soil nutrients and examined the decomposition and nutrient dynamics of <i>Cynodon dactylon</i>. Results showed that flooding significantly increased initial levels of N and P, especially as particulate nitrogen (PN) and particulate phosphorus (PP), affecting both plant decomposition and nutrient dynamics in the water. After 60 days, <i>Cynodon dactylon</i> lost 47.97%-56.01% dry matter, 43.58%-54.48% total nitrogen (TN), and 14.28%-20.50% total phosphorus (TP). Initial PN and total dissolved nitrogen (TDN) promoted dry matter loss, PN and PP promoted TP loss, while PN and TDN inhibited TN loss. By day 60, no positive correlation was found between plant-released N and P and TN or TP in the overlying water. However, initial PP and PN levels were negatively correlated with TN and TP, indicating an inhibitory effect. Further analysis indicates that PN and PP released from the soil supported the formation of microbial aggregates, enhancing denitrification and phosphorus removal and thus improving water purification over time.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1526507"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847792/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491742","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":"Optimizing the selection of quantitative traits in plant breeding using simulation.","authors":"Rafael Augusto Vieira, Ana Paula Oliveira Nogueira, Roberto Fritsche-Neto","doi":"10.3389/fpls.2025.1495662","DOIUrl":"https://doi.org/10.3389/fpls.2025.1495662","url":null,"abstract":"<p><p>This review summarizes findings from simulation studies on quantitative traits in plant breeding and translates these insights into practical schemes. As agricultural productivity faces growing challenges, plant breeding is central to addressing these issues. Simulations use mathematical models to replicate biological conditions, bridging theory and practice by validating hypotheses early and optimizing genetic gain and resource use. While strategies can improve trait value, they reduce genetic diversity, making a combination of approaches essential. Studies emphasize the importance of aligning strategy with trait heritability and selection timing and maintaining genetic diversity while considering genotype-environment interactions to avoid biases in early selection. Using markers accelerates breeding cycles when marker placement is precise, foreground and background selection are balanced, and QTL are effectively managed. Genomic selection increases genetic gains by shortening breeding cycles and improving parent selection, especially for low heritability traits and complex genetic architectures. Regular updates of training sets are critical, regardless of genetic architecture. Bayesian methods perform well with fewer genes and in early breeding cycles, while BLUP is more robust for traits with many QTL, and RR-BLUP proves flexible across different conditions. Larger populations lead to greater gains when clear objectives and adequate germplasm are available. Accuracy declines over generations, influenced by genetic architecture and population size. For low heritability traits, multi-trait analysis improves accuracy, especially when correlated with high heritability traits. Updates including top-performing candidates, but conserving variability enhances gains and accuracy. Low-density genotyping and imputation offer cost-effective alternatives to high-density genotyping, achieving comparable results. Targeting populations optimizes genetic relationships, further improving accuracy and breeding outcomes. Evaluating genomic selection reveals a balance between short-term gains and long-term potential and rapid-cycling genomic programs excel. Diverse approaches preserve rare alleles, achieve significant gains, and maintain diversity, highlighting the trade-offs in optimizing breeding success.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1495662"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847808/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491744","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":"ASD-YOLO: a lightweight network for coffee fruit ripening detection in complex scenarios.","authors":"Baofeng Ye, Renzheng Xue, Haiqiang Xu","doi":"10.3389/fpls.2025.1484784","DOIUrl":"https://doi.org/10.3389/fpls.2025.1484784","url":null,"abstract":"<p><p>Coffee is one of the most popular and widely used drinks worldwide. At present, how to judge the maturity of coffee fruit mainly depends on the visual inspection of human eyes, which is both time-consuming and labor-intensive. Moreover, the occlusion between leaves and fruits is also one of the challenges. In order to improve the detection efficiency of coffee fruit maturity, this paper proposes an improved detection method based on YOLOV7 to efficiently identify the maturity of coffee fruits, called ASD-YOLO. Firstly, a new dot product attention mechanism (L-Norm Attention) is designed to embed attention into the head structure, which enhances the ability of the model to extract coffee fruit features. In addition, we introduce SPD-Conv into backbone and head to enhance the detection of occluded small objects and low-resolution images. Finally, we replaced upsampling in our model with DySample, which requires less computational resources and is able to achieve image resolution improvements without additional burden. We tested our approach on the coffee dataset provided by Roboflow. The results show that ASD-YOLO has a good detection ability for coffee fruits with dense distribution and mutual occlusion under complex background, with a recall rate of 78.4%, a precision rate of 69.8%, and a mAP rate of 80.1%. Compared with the recall rate, accuracy rate and mAP of YOLOv7 model, these results are increased by 2.0%, 1.1% and 2.1%, respectively. The enhanced model can identify coffee fruits at all stages more efficiently and accurately, and provide technical reference for intelligent coffee fruit harvesting.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1484784"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847874/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491738","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":"Exploring the potential role of EPSPS mutations for enhanced glyphosate resistance in <i>Nicotiana tabacum</i>.","authors":"Bingjie Li, Chen Chen, Mengmeng Cui, Yuhe Sun, Jing Lv, Changbo Dai","doi":"10.3389/fpls.2025.1516963","DOIUrl":"https://doi.org/10.3389/fpls.2025.1516963","url":null,"abstract":"<p><p>Glyphosate is a widely used non-selective, broad-spectrum, systemic herbicide by interfering with the biosynthesis of aromatic amino acids. However, the emergence of glyphosate-resistant weeds has driven the need for enhanced herbicide resistance in crops. In this study, we engineered two mutant variants of the tobacco EPSPS gene through amino acid substitution (TIPS-NtEPSPS and P180S-NtEPSPS). These mutated <i>EPSPS</i> genes were overexpressed in tobacco under the control of CaMV35S promoters. Our results demonstrate that overexpression of TIPS-NtEPSPS significantly enhances glyphosate tolerance, allowing plants to withstand up to four times the recommended dose without compromising their fitness. This research highlights the potential of the TIPS-NtEPSPS mutant to improve herbicide resistance in tobacco, offering a viable approach for effective weed management.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1516963"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847837/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491741","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":"Unpacking the benefits of black soldier fly frass fertilizer towards nematode suppression and potato production.","authors":"Emmanuel O Anedo, Dennis Beesigamukama, Benson Mochoge, Nicholas K Korir, Solveig Haukeland, Xavier Cheseto, Moses Nyongesa, Patrick Pwaipwai, Sevgan Subramanian, Abdou Tenkouano, Betty Kibaara, Chrysantus M Tanga","doi":"10.3389/fpls.2025.1509643","DOIUrl":"https://doi.org/10.3389/fpls.2025.1509643","url":null,"abstract":"<p><p>Potato production is hindered by soil degradation and nematode infestation. Mineral fertilizers and synthetic nematicides are costly and cause negative impacts on humans and the environment, while organic fertilizers are less effective for soil health and nematode management. This study demonstrates the contribution of black soldier fly frass fertilizer (BSFFF) in nematode suppression and potato productivity when compared to commercial mineral fertilizer, organic fertilizer (SAFI), and nematicide. The on-farm experiments consisted of eight treatments: BSFFF, SAFI, BSFFF+5%chitin, NPK+nematicide, 50%BSFFF+50%NPK, 50%SAFI+50%NPK, 50%BSFFF+5% chitin+50%NPK, and control (unfertilized soil). Results revealed that all fertilizer treatments significantly increased potato growth, number of tubers (34 - 61%), and tuber yield (20 - 72%) relative to the control. Application of BSFFF+5% chitin produced 9 - 28% higher tubers per plant compared to other treatments. Over 26% higher tuber yield was achieved using BSFFF+5% chitin compared to NPK+nematicide treatment. Soil amendment with BSFFF+5% chitin caused 5-35% higher reduction in the number of cysts per 200 g soil^-1 compared to NPK+nematicide and SAFI treatments. The same treatment reduced the PCN reproduction rate by 20% and 75% compared to NPK + nematicide and SAFI, respectively. Both BSFFF and NPK+nematicide treatments achieved comparable suppression of the number of eggs and infective juveniles (J2) per cyst^-1 and eggs g^-1 of soil. However, BSFFF+5% chitin reduced the number of eggs and J2 per cyst^-1 and eggs g^-1 of soil by 55-92% compared to SAFI. Our findings demonstrate that chitin-fortified BSFFF can significantly contribute to potato cyst nematode suppression and boost potato yields in smallholder farming systems, thus, making it a promising and sustainable alternative to commercial fertilizers and nematicides. Adopting this regenerative and multipurpose fertilizer will reduce reliance on synthetic fertilizers and nematicides, which are costly and harmful to the environment and human health.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1509643"},"PeriodicalIF":4.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491745","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":"Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field.","authors":"Siqiao Tan, Qiang Xie, Wenshuai Zhu, Yangjun Deng, Lei Zhu, Xiaoqiao Yu, Zheming Yuan, Yuan Chen","doi":"10.3389/fpls.2025.1507442","DOIUrl":"10.3389/fpls.2025.1507442","url":null,"abstract":"<p><p>Barnyard grass, a pernicious weed thriving in rice fields, poses a significant challenge to agricultural productivity. Detection of barnyard grass before the four-leaf stage is critical for effective control measures. However, due to their striking visual similarity, separating them from rice seedlings at early growth stages is daunting using traditional visible light imaging models. To explore the feasibility of hyperspectral identification of barnyard grass and rice in the seedling stage, we have pioneered the DeepBGS hyperspectral feature parsing framework. This approach harnesses the power of deep convolutional networks to automate the extraction of pertinent information. Initially, a sliding window-based technique is employed to transform the one-dimensional spectral band sequence into a more interpretable two-dimensional matrix. Subsequently, a deep convolutional feature extraction module, ensembled with a bilayer LSTM module, is deployed to capture both global and local correlations inherent within hyperspectral bands. The efficacy of DeepBGS was underscored by its unparalleled performance in discriminating barnyard grass from rice during the critical 2-3 leaf stage, achieving a 98.18% accuracy rate. Notably, this surpasses the capabilities of other models that rely on amalgamations of machine learning algorithms and feature dimensionality reduction methods. By seamlessly integrating deep convolutional networks, DeepBGS independently extracts salient features, indicating that hyperspectral imaging technology can be used to effectively identify barnyard grass in the early stages, and pave the way for the development of advanced early detection systems.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1507442"},"PeriodicalIF":4.1,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11842386/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143482815","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}