Frontiers in Plant Science最新文献

{"title":"Advancing precision agriculture with deep learning enhanced SIS-YOLOv8 for Solanaceae crop monitoring.","authors":"Ruiqian Qin, Yiming Wang, Xiaoyan Liu, Helong Yu","doi":"10.3389/fpls.2024.1485903","DOIUrl":"10.3389/fpls.2024.1485903","url":null,"abstract":"<p><strong>Introduction: </strong>Potatoes and tomatoes are important Solanaceae crops that require effective disease monitoring for optimal agricultural production. Traditional disease monitoring methods rely on manual visual inspection, which is inefficient and prone to subjective bias. The application of deep learning in image recognition has led to object detection models such as YOLO (You Only Look Once), which have shown high efficiency in disease identification. However, complex climatic conditions in real agricultural environments challenge model robustness, and current mainstream models struggle with accurate recognition of the same diseases across different plant species.</p><p><strong>Methods: </strong>This paper proposes the SIS-YOLOv8 model, which enhances adaptability to complex agricultural climates by improving the YOLOv8 network structure. The research introduces three key modules: 1) a Fusion-Inception Conv module to improve feature extraction against complex backgrounds like rain and haze; 2) a C2f-SIS module incorporating Style Randomization to enhance generalization ability for different crop diseases and extract more detailed disease features; and 3) an SPPF-IS module to boost model robustness through feature fusion. To reduce the model's parameter size, this study employs the Dep Graph pruning method, significantly decreasing parameter volume by 19.9% and computational load while maintaining accuracy.</p><p><strong>Results: </strong>Experimental results show that the SIS-YOLOv8 model outperforms the original YOLOv8n model in disease detection tasks for potatoes and tomatoes, with improvements of 8.2% in accuracy, 4% in recall rate, 5.9% in mAP50, and 6.3% in mAP50-95.</p><p><strong>Discussion: </strong>Through these network structure optimizations, the SIS-YOLOv8 model demonstrates enhanced adaptability to complex agricultural environments, offering an effective solution for automatic crop disease detection. By improving model efficiency and robustness, our approach not only advances agricultural disease monitoring but also contributes to the broader adoption of AI-driven solutions for sustainable crop management in diverse climates.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1485903"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11755099/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028622","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":"Comparative response mechanisms of two cultivars of <i>Musa paradisiaca L.</i> to <i>Fusarium oxysporum</i> f.sp. <i>cubense</i> infection.","authors":"Yajie Duan, Zhiwei Jia, Zhiwei Lu, Huigang Hu, Rulin Zhan","doi":"10.3389/fpls.2024.1492711","DOIUrl":"10.3389/fpls.2024.1492711","url":null,"abstract":"<p><p>With the aim of enhancing plants' ability to respond to pathogenic fungi, this study focuses on disease resistance genes. We commenced a series of investigations by capitalizing on the pronounced differences in resistance to Fusarium wilt between resistant and susceptible varieties. Through an in-depth exploration of the metabolic pathways that bolster this defense, we identified genes associated with resistance to <i>Fusarium oxysporum</i> f. sp. <i>cubense</i> (Foc). For our analysis, root tissues from seedlings that had been in contact with <i>Fusarium oxysporum</i> for four days were harvested, including both infected and uninfected samples, which served as our study specimens. The crude extract treatment led to a significant increase in malondialdehyde (MDA) levels, lignin content, and phenylalanine ammonia lyase (PAL) activity. Conversely, there was a notable decline in protein content, ergosterol levels, and pectinase activity. In the control group, it was observed that 4,474 genes in the resistant varieties were significantly up-regulated compared to the susceptible varieties. The functional annotation of these differentially expressed genes (DEGs) emphasized their predominant participation in biological processes. Further analysis via the KEGG database revealed that 14 DEGs in the susceptible varieties were particularly enriched in pathways related to plant hormone signaling. Through the perspective of transcriptome data, we focused on genes associated with lignin and cell wall development for Q-PCR validation. Notably, the expression levels of Macma4_02_g07840 (COMT) and Macma4_10_g06530 (CCOAOMT) were relatively elevated. Our findings suggest that the resistance of these varieties to wilt infection can be ascribed to the accumulation of lignin metabolites, which inhibits pathogenic fungus growth by restricting the synthesis of cellular metabolites. The evidence documented in our research provides a framework for a deeper understanding of the disease resistance mechanisms in bananas, laying a solid theoretical foundation for future studies in this area.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1492711"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11754190/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028627","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":"Application and development of CRISPR technology in the secondary metabolic pathway of the active ingredients of phytopharmaceuticals.","authors":"Haixin Gao, Xinyi Pei, Xianshui Song, Shiying Wang, Zisong Yang, Jianjun Zhu, Qiupeng Lin, Qinlong Zhu, Xiangna Yang","doi":"10.3389/fpls.2024.1477894","DOIUrl":"10.3389/fpls.2024.1477894","url":null,"abstract":"<p><p>As an efficient gene editing tool, the CRISPR/Cas9 system has been widely employed to investigate and regulate the biosynthetic pathways of active ingredients in medicinal plants. CRISPR technology holds significant potential for enhancing both the yield and quality of active ingredients in medicinal plants. By precisely regulating the expression of key enzymes and transcription factors, CRISPR technology not only deepens our understanding of secondary metabolic pathways in medicinal plants but also opens new avenues for drug development and the modernization of traditional Chinese medicine. This article introduces the principles of CRISPR technology and its efficacy in gene editing, followed by a detailed discussion of its applications in the secondary metabolism of medicinal plants. This includes an examination of the composition of active ingredients and the implementation of CRISPR strategies within metabolic pathways, as well as the influence of Cas9 protein variants and advanced CRISPR systems in the field. In addition, this article examines the long-term impact of CRISPR technology on the progress of medicinal plant research and development. It also raises existing issues in research, including off-target effects, complexity of genome structure, low transformation efficiency, and insufficient understanding of metabolic pathways. At the same time, this article puts forward some insights in order to provide new ideas for the subsequent application of CRISPR in medicinal plants. In summary, CRISPR technology presents broad application prospects in the study of secondary metabolism in medicinal plants and is poised to facilitate further advancements in biomedicine and agricultural science. As technological advancements continue and challenges are progressively addressed, CRISPR technology is expected to play an increasingly vital role in the research of active ingredients in medicinal plants.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1477894"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11753916/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028626","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":"Inheritance of resistance to maize lethal necrosis in tropical maize inbred lines.","authors":"Hilda M Kavai, Dan Makumbi, Felister M Nzuve, Vincent W Woyengo, L M Suresh, William M Muiru, Manje Gowda, Boddupalli M Prasanna","doi":"10.3389/fpls.2024.1506139","DOIUrl":"10.3389/fpls.2024.1506139","url":null,"abstract":"<p><p>Maize (<i>Zea mays</i> L.) production in sub-Saharan Africa can be improved by using hybrids with genetic resistance to maize lethal necrosis (MLN). This study aimed to assess the general (GCA) and specific combining ability (SCA), reciprocal effects, and quantitative genetic basis of MLN resistance and agronomic traits in tropical maize inbred lines. A total of 182 hybrids from a 14-parent diallel, along with their parents, were evaluated under artificial MLN inoculation and rainfed conditions for 3 years in Kenya. Disease ratings at four time points, grain yield (GY), and other agronomic traits were analyzed using Griffing's Method 3 and Hayman's diallel models. Significant (<i>P</i> < 0.001) GCA and SCA mean squares were observed for all traits under disease conditions and most traits under rainfed conditions, highlighting the importance of both additive and non-additive genetic effects. However, additive gene action predominated for all traits. Narrow-sense heritability estimates for MLN resistance (<i>h</i> ² = 0.52-0.56) indicated a strong additive genetic component. Reciprocal effects were not significant for MLN resistance, suggesting minimal maternal or cytoplasmic inheritance. Four inbred lines showed significant negative GCA effects for MLN resistance and positive GCA effects for GY under artificial MLN inoculation. Inbred lines CKL181281 and CKL182037 (GCA effects for MLN4 = -0.45 and -0.24, respectively) contained the most recessive alleles for MLN resistance. The minimum number of groups of genes involved in MLN resistance was estimated to be three. Breeding strategies that emphasize GCA could effectively be used to improve MLN resistance in this germplasm.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1506139"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11753913/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028565","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":"Effect of operational parameters on droplet deposition characteristics using an unmanned aerial vehicle for banana canopy.","authors":"Jiaxiang Yu, Xing Xu, Jieli Duan, Yinlong Jiang, Haotian Yuan, Huazimo Liang, Shuaijie Jing, Zhou Yang","doi":"10.3389/fpls.2024.1491397","DOIUrl":"10.3389/fpls.2024.1491397","url":null,"abstract":"<p><p>In recent years, as an important part of precision agricultural aviation, the plant protection unmanned aerial vehicle (UAV) has been widely studied and applied worldwide, especially in East Asia. Banana, as a typical large broad-leaved crop, has high requirements for pests and diseases control. The mechanization degree of plant protection management in banana orchard is low. Therefore, our study focuses on the effects of different flight heights (3-5 m) and droplet sizes (50-150 μm) of plant protection UAV on the droplet deposition distribution characteristics of banana canopy. And the droplet deposition distribution in banana canopy and spraying drift of plant protection UAV and ground air-assisted sprayer were compared. The results showed that droplet size was the main factor affecting droplet deposition density, coverage, uniformity and penetration on both sides of banana canopy leaves. The droplet deposition density and coverage on the adaxial side of leaves were mostly significantly larger than that on the abaxial side. The flight height of 4 m and the droplet size of 100 μm could make the adaxial side of banana canopy leaves have higher droplet deposition density (63.77 droplets per square cm) and coverage (12.75%), and can make the droplets effectively deposit on the abaxial side of banana canopy leaves, with droplet deposition density of 17.46 droplets per square cm and coverage of 1.24%. Choosing an appropriate flight height and a droplet size could improve the droplet deposition uniformity on both sides of banana canopy leaves, but the improvement was not significant. Moreover, at a same operational parameter combination, it was difficult to achieve the best droplet deposition density, coverage, uniformity and penetration at the same time. In addition, appropriately increasing the flight height and droplet size could help to improve the droplet deposition penetration on the adaxial side of banana canopy leaves, but there were few significant improvements. Compared with the plant protection UAV, the ground air-assisted sprayer had higher droplet deposition density and coverage on the abaxial side of banana canopy leaves, but had smaller droplet deposition coverage on the adaxial side. The droplet deposition density and coverage on the abaxial side of banana canopy leaves were obviously larger than the adaxial side during the spraying of ground air-assisted sprayer. The droplet drift distance of the ground air-assisted sprayer was farther than the plant protection UAV. The test results of this study can provide practical and data support for the UAV aerial application in banana orchard, and provide a valuable reference for the implementation of air-ground cooperation spraying strategy in banana orchard, which is of great significance to promote sustainable and intelligent phytoprotection of banana orchard.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1491397"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11754204/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028415","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":"Effects of salt stress on plant and rhizosphere bacterial communities, interaction patterns, and functions.","authors":"Maoxing Fu, Liying Liu, Bingzhe Fu, Meiling Hou, Yanzi Xiao, Yinghao Liu, Duowen Sa, Qiang Lu","doi":"10.3389/fpls.2024.1516336","DOIUrl":"10.3389/fpls.2024.1516336","url":null,"abstract":"<p><strong>Introduction: </strong>Salt stress significantly affects plant growth, and Na⁺ has gained attention for its potential to enhance plant adaptability to saline conditions. However, the interactions between Na⁺, plants, and rhizosphere bacterial communities remain unclear, hindering a deeper understanding of how Na⁺ contributes to plant resilience under salt stress.</p><p><strong>Methods: </strong>This study aimed to investigate the mechanisms through which Na⁺ promotes alfalfa's adaptation to salt stress by modifying rhizosphere bacterial communities. We examined the metabolic activity and community composition of both plant and rhizosphere bacteria under Na⁺ treatment.</p><p><strong>Results and discussion: </strong>Our results revealed significant changes in the metabolism and community composition of both plant and rhizosphere bacteria following Na⁺ addition. Na⁺ not only promoted the growth of rhizosphere bacteria but also induced shifts in the plant-associated bacterial community, increasing the abundance of bacterial species linked to alfalfa's resistance to salt stress. Furthermore, the chemical characteristics of alfalfa were strongly correlated with the composition and network complexity of both plant and rhizosphere bacterial communities. These interactions suggest that Na⁺ plays a crucial role in enhancing alfalfa's adaptability to salt stress by fostering beneficial bacterial communities in the rhizosphere. This finding highlights the potential of leveraging Na⁺ interactions with plant-microbe systems to improve crop resilience and productivity in saline agricultural environments.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1516336"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11753915/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028418","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":"Odyssey of environmental and microbial interventions in maize crop improvement.","authors":"Alok Kumar Singh, Alok Kumar Srivastava, Parul Johri, Manish Dwivedi, Radhey Shyam Kaushal, Mala Trivedi, Tarun Kumar Upadhyay, Nadiyah M Alabdallah, Irfan Ahmad, Mohd Saeed, Sorabh Lakhanpal","doi":"10.3389/fpls.2024.1428475","DOIUrl":"10.3389/fpls.2024.1428475","url":null,"abstract":"<p><p>Maize (<i>Zea mays</i>) is India's third-largest grain crop, serving as a primary food source for at least 30% of the population and sustaining 900 million impoverished people globally. The growing human population has led to an increasing demand for maize grains. However, maize cultivation faces significant challenges due to a variety of environmental factors, including both biotic and abiotic stresses. Abiotic stresses such as salinity, extreme temperatures, and drought, along with biotic factors like bacterial, fungal, and viral infections, have drastically reduced maize production and grain quality worldwide. The interaction between these stresses is complex; for instance, abiotic stress can heighten a plant's susceptibility to pathogens, while an overabundance of pests can exacerbate the plant's response to environmental stress. Given the complexity of these interactions, comprehensive studies are crucial for understanding how the simultaneous presence of biotic and abiotic stresses affects crop productivity. Despite the importance of this issue, there is a lack of comprehensive data on how these stress combinations impact maize in key agricultural regions. This review focuses on developing abiotic stress-tolerant maize varieties, which will be essential for maintaining crop yields in the future. One promising approach involves the use of Plant Growth-Promoting Rhizobacteria (PGPR), soil bacteria that colonize the rhizosphere and interact with plant tissues. Scientists are increasingly exploring microbial strategies to enhance maize's resistance to both biotic and abiotic stresses. Throughout the cultivation process, insect pests and microorganisms pose significant threats to maize, diminishing both the quantity and quality of the grain. Among the various factors causing maize degradation, insects are the most prevalent, followed by fungal infections. The review also delves into the latest advancements in applying beneficial rhizobacteria across different agroecosystems, highlighting current trends and offering insights into future developments under both normal and stress conditions.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1428475"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11755104/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028523","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":"Prediction of the potentially suitable areas of <i>Paeonia lactiflora</i> in China based on Maxent and Marxan models.","authors":"Yongji Wang, Wentao Huo, Kefan Wu, Jiaying Cao, Guanghua Zhao, Fenguo Zhang","doi":"10.3389/fpls.2024.1516251","DOIUrl":"10.3389/fpls.2024.1516251","url":null,"abstract":"<p><p><i>Paeonia lactiflora</i> Pall. (<i>P. lactiflora</i>) is an important medicinal plant in China with high ornamental value. Predicting the potential habitat of <i>P. lactiflora</i> is crucial for identifying its geographic distribution characteristics and ensuring its ecological and economic importance. Therefore, we aimed to predict the potential geographic distribution of <i>P. lactiflora</i> in China under future climate change scenarios. To this end, we used an optimized Maxent model and ArcGIS software to analyze the influence of 12 environmental variables on <i>P. lactiflora</i> potential distribution in China based on 291 effective distribution records. The key factors limiting the potential geographic distribution of <i>P. lactiflora</i> were evaluated by combining the contribution rates of the environmental variables with the significance of their replacement. The jackknife method was employed to assess the importance of these factors. Response curves were used to determine the appropriate intervals for the environmental factor variables and to analyze the changes in spatial patterns. The Maxent model exhibited a low degree of overfitting and good prediction accuracy. The main variables influencing <i>P. lactiflora</i> distribution were precipitation in the wettest month and hottest quarter, lowest temperature in the coldest month, and highest temperature in the warmest month. Under current climatic conditions, <i>P. lactiflora</i> could theoretically grow across and area of 231.1 × 10⁴ km² in China. Under the six future climate change scenarios, the potential geographic distribution area was reduced compared with the current distribution area, and the potentially suitable areas shifted southwestward. The majority of priority conservation sites for <i>P. lactiflora</i> are located in northern and northeastern China, which align with the highly favorable areas predicted by the Maxent model. The findings of this investigation can guide the selection of future introductions as well as artificial cultivation and preservation of <i>P. lactiflora</i> resources.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1516251"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11754415/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028529","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":"LiDAR point cloud denoising for individual tree extraction based on the Noise4Denoise.","authors":"Xiangfei Lu, Zongyu Ye, Liyong Fu, Huaiyi Wang, Kaiyu Wang, Yaquan Dou, Dongbo Xie, Xiaodi Zhao","doi":"10.3389/fpls.2024.1490660","DOIUrl":"10.3389/fpls.2024.1490660","url":null,"abstract":"<p><p>The processing of LiDAR point cloud data is of critical importance in the context of forest resource surveys, as well as representing a pivotal element in the realm of forest physiological and ecological studies.Nonetheless, conventional denoising algorithms frequently exhibit deficiencies with regard to adaptability and denoising efficacy, particularly when employed in relation to disparate datasets.To address these issues, this study introduces DEN4, an unsupervised, deep learning-based point cloud denoising algorithm designed to improve the accuracy of single tree segmentation in LiDAR point clouds.DEN4 introduces a multilevel noise separation module that effectively distinguishes between signal and noise, thereby improving the signal-to-noise ratio (SNR) and reducing the error.The experimental results demonstrate that DEN4 significantly outperforms traditional denoising methods in several key metrics, including mean square error (MSE), SNR, Hausdorff distance, and structural similarity index (SSIM).In the 60 sample dataset, DEN4 achieved the best mean and standard deviation on all metrics: Specifically, the MSE mean was found to be 0.0094, with a standard deviation of 0.0008, the SNR mean was 149.1570, with a standard deviation of 0.5628, the Hausdorff mean was 0.8503, with a standard deviation of 0.0947, and the SSIM mean was 0.8399, with a standard deviation of 0.0054. For instance, in the S10 dataset, DEN4 attained a 70.2% diminution in MSE and a 37.8% augmentation in SNR in comparison with PTD.The findings demonstrate the efficacy of DEN4 in multiple forest datasets, its ability to maintain geometric integrity, and its enhanced stability without the necessity for pre-labelled data. The algorithm's superior performance and robustness in diverse forest environments underscores its potential application in single tree segmentation and forest resource management.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1490660"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11754224/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028569","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":"Monitoring of agricultural progress in rice-wheat rotation area based on UAV RGB images.","authors":"Jianliang Wang, Chen Chen, Senpeng Huang, Hui Wang, Yuanyuan Zhao, Jiacheng Wang, Zhaosheng Yao, Chengming Sun, Tao Liu","doi":"10.3389/fpls.2024.1502863","DOIUrl":"10.3389/fpls.2024.1502863","url":null,"abstract":"<p><p>Real-time monitoring of rice-wheat rotation areas is crucial for improving agricultural productivity and ensuring the overall yield of rice and wheat. However, the current monitoring methods mainly rely on manual recording and observation, leading to low monitoring efficiency. This study addresses the challenges of monitoring agricultural progress and the time-consuming and labor-intensive nature of the monitoring process. By integrating Unmanned aerial vehicle (UAV) image analysis technology and deep learning techniques, we proposed a method for precise monitoring of agricultural progress in rice-wheat rotation areas. The proposed method was initially used to extract color, texture, and convolutional features from RGB images for model construction. Then, redundant features were removed through feature correlation analysis. Additionally, activation layer features suitable for agricultural progress classification were proposed using the deep learning framework, enhancing classification accuracy. The results showed that the classification accuracies obtained by combining Color+Texture, Color+L08CON, Color+ResNet50, and Color+Texture+L08CON with the random forest model were 0.91, 0.99, 0.98, and 0.99, respectively. In contrast, the model using only color features had an accuracy of 85.3%, which is significantly lower than that of the multi-feature combination models. Color feature extraction took the shortest processing time (0.19 s) for a single image. The proposed Color+L08CON method achieved high accuracy with a processing time of 1.25 s, much faster than directly using deep learning models. This method effectively meets the need for real-time monitoring of agricultural progress.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1502863"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11754401/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143028574","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}