Rochelle C. Olana, Sukanya Haituk, Anuruddha Karunarathna, Christian Joseph R. Cumagun
{"title":"Review: Elucidating the Efficacy of Antagonistic Yeasts by Using Multiple Mechanisms in Controlling Fungal Phytopathogens","authors":"Rochelle C. Olana, Sukanya Haituk, Anuruddha Karunarathna, Christian Joseph R. Cumagun","doi":"10.1111/jph.70097","DOIUrl":"https://doi.org/10.1111/jph.70097","url":null,"abstract":"<div>\u0000 \u0000 <p>The widespread and indiscriminate application of synthetic fungicides against phytopathogens has led to ecological damage and health risks, highlighting the urgent need for eco-friendly alternatives. Antagonistic yeasts provide an environmentally sound alternative to chemical fungicides for crop productivity and environmental conservation, exhibiting direct and indirect control mechanisms against phytopathogens. These microorganisms possess simple nutritional requirements, compatibility with low doses of fungicides and promote public health safety by releasing non-hazardous secondary metabolites. Also, the commercialisation of yeast-based products shows significant potential for protection to a range of commodities, both pre- and postharvest. However, there was only a little literature on the complex control mechanisms working together by various yeast genera against phytopathogens, which were particularly stressed in the review. In addition, the different challenges of biocontrol yeast application and the standard commercialisation protocol were discussed. Future research should focus on optimising formulations and understanding environmental interactions to support biocontrol yeasts' commercialisation and widespread application for crop management.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144315200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julie Pedersen, Isaac K. Abuley, Jennie L. Brierley, Alison K. Lees, Sabine Ravnskov
{"title":"Impact of Potato Crop Rotation on Verticillium dahliae, Colletotrichum coccodes and Potato Early Dying","authors":"Julie Pedersen, Isaac K. Abuley, Jennie L. Brierley, Alison K. Lees, Sabine Ravnskov","doi":"10.1111/jph.70099","DOIUrl":"https://doi.org/10.1111/jph.70099","url":null,"abstract":"<p>The influence of different potato rotations on potato early dying (PED) and infections by the soilborne pathogen <i>Verticillium dahliae</i> was investigated. The study also considered the co-occurrence of the PED-associated fungus <i>Colletotrichum coccodes</i> in the fields. Furthermore, a pot experiment was carried out to explore the correlation between wilt progression and <i>V. dahliae</i> levels in plants, and to assess the effects of biofumigating cover crops in the potato rotations. In the fields studied, the density of <i>V. dahliae</i> observed in soil and plants was significantly higher in a 2-year potato rotation, compared to growing potatoes every 3–4 years. In addition, the study confirmed very low quantities of <i>V. dahliae</i> and <i>C. coccodes</i> in soils with an extended break (> 15 years) from potatoes. In the pot experiment, there was no direct effect of the cover crops, yellow mustard and oats, on either incidence of <i>V. dahliae</i> infections, plant biomass, or premature wilting of potato plants. However, a strong positive correlation between <i>V. dahliae</i> and wilt severity was observed in potatoes without prior growing of oat or yellow mustard, which was not evident in potato plants grown after the incorporation of these cover crops. The findings demonstrate a clear association between potato crop rotation and the incidence of <i>V. dahliae</i> in the field; however, the inconclusive results of the effect of oat and yellow mustard cover crops on <i>V. dahliae</i> and PED require further investigation. This study suggests that the development of more strategic potato rotation management could reduce PED levels.</p>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jph.70099","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Efficacy of a Beauveria bassiana-Based Biofungicide Against Strawberry Powdery Mildew Caused by Podosphaera aphanis Under Various Conditions and Its Potential Mode of Action","authors":"Shunsuke Asano, Yoshihiko Hirayama, Kandai Yoshida, Masahiro Katsuma, Kotaro Hori, Yuichiro Iida, Satoshi Yamanaka, Masaharu Kubota","doi":"10.1111/jph.70100","DOIUrl":"https://doi.org/10.1111/jph.70100","url":null,"abstract":"<div>\u0000 \u0000 <p>Powdery mildew, caused by <i>Podosphaera aphanis</i>, is a severe disease affecting strawberry production in Japan. The biofungicide BotaniGard ES, whose active ingredient is <i>Beauveria bassiana</i> strain GHA, was reported to be effective against <i>P. aphanis</i>. In the present study, the efficacy of BotaniGard was clarified under a range of conditions to evaluate its practicality in the greenhouse. In greenhouse efficacy trials, the control efficacy of BotaniGard was relatively high (70.4%–100%) against the disease under low disease pressure, but low (28.1%–53.4%) under high disease pressure. In addition, the application 6 h before inoculation was the most effective compared with application 7 days before or 7 days after inoculation. The application of BotaniGard at 1-week intervals (control efficacy of 66.5%) was more effective against powdery mildew on leaves than at 2- or 3-week intervals. In contrast, the application of BotaniGard was not effective against powdery mildew on fruits, regardless of application interval, although most of the chemical fungicides tested for comparison were effective. RNA-seq analysis indicated that the application of BotaniGard upregulated the defence response, systemic acquired resistance and chitinase activity in leaves. These results indicate that BotaniGard is effective in controlling strawberry powdery mildew on leaves under low disease pressure, but not on fruits, and the mode of action might be the activation of induced plant defences. This study encourages a detailed evaluation of the efficacy of biofungicides to promote their appropriate use in greenhouse production.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Reshma Nazirkar Atole, Navnath B Pokale, Anjali Devi Patil
{"title":"Crop Leaf Segmentation and Disease Detection Based on Shepherd Wide Residual Network","authors":"Reshma Nazirkar Atole, Navnath B Pokale, Anjali Devi Patil","doi":"10.1111/jph.70080","DOIUrl":"https://doi.org/10.1111/jph.70080","url":null,"abstract":"<div>\u0000 \u0000 <p>The rapid rise in population necessitates a significant increase in agricultural productivity to satisfy the increasing demand for food. Timely identification of crop diseases is essential to ensure food security. Timely identification of crop disorders is vital for effective disease management and mitigating declines in crop yields. However, manually monitoring leaf diseases is labour-intensive and requires extensive knowledge of plant pathogens and considerable time and effort. The primary objective of this study is to develop an efficient and accurate deep learning-based approach named Shepherd Wide Residual Network (ShWRes-Net) for the automated detection and classification of crop leaf diseases, thereby reducing reliance on manual diagnosis and improving disease management in agriculture. The process begins with collecting crop leaf images from various datasets, then subjecting them to pre-processing leveraging a Wiener filter to mitigate noise. Leaf segmentation is then performed utilising the Dual-Branch U-Net model. Additionally, feature extraction is performed using a Complete Local Binary Pattern and Pyramid Histogram of Oriented Gradients. Finally, the identification of crop diseases is accomplished through the introduction of the ShWRes-Net model, which combines the Shepard Convolutional Neural Network with the Wide Residual Network. The ShWRes-Net method achieved a True Negative Rate of 90.877%, a True Positive Rate of 94.876% and an accuracy of 92.986%.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Farhan Ullah, Liaqat Shah, Muhammad Khalid, Akhlaq Ahmad, Chen Can, Si Hongqi, Ma Chuanxi
{"title":"Molecular Characterisation of Diverse Wheat Germplasm for Enhanced Resistance to Puccinia triticina","authors":"Farhan Ullah, Liaqat Shah, Muhammad Khalid, Akhlaq Ahmad, Chen Can, Si Hongqi, Ma Chuanxi","doi":"10.1111/jph.70095","DOIUrl":"https://doi.org/10.1111/jph.70095","url":null,"abstract":"<div>\u0000 \u0000 <p>Leaf rust (LR) epidemics present a persistent threat to global wheat production, despite the presence of resistance (Lr) genes in wheat. The evolving pathogen <i>Puccinia triticina</i> continually challenges these resistance mechanisms. This study assessed 10 wheat lines for relative resistance index (RRI) and screened them for <i>Lr</i> genes or quantitative trait loci (QTLs) using microsatellite markers. The lines were classified into three groups: Ssusceptible (< 5; 4.32 ± 0.68), moderate (5–7; 6.05 ± 0.67) and resistant (> 7; 8.50 ± 0.22) (<i>p</i> < 0.001). Genetic analysis with 12 polymorphic markers revealed 186 alleles with varying allelic diversity. Markers <i>Xbarc124</i> and <i>Xgwm512</i> showed greater diversity, and resistance-related alleles were linked to markers <i>Xgwm512</i> and <i>Xgwm493</i>, associated with the <i>Lr34</i> gene. Moderate associations were found with <i>Lr37</i> (<i>Xbarc1138</i> and <i>Xgwm400</i>) and <i>Lr24</i> (<i>Xgwm273</i>), while <i>Lr26</i> (<i>Xwmc407</i>) was linked to susceptibility. Parental line crosses resulted in higher RRI, indicating beneficial recombination. Structure analysis revealed genetic diversity among resistance groups, with susceptible groups showing distinct clustering. Lines AN179 and PR127 clustered together, showing key resistance alleles, particularly in crosses with resistant PR123. The findings highlight novel pathogen races contributing to resistance breakdown and suggest combining all-stage resistance genes (<i>Lr9</i>, <i>Lr24</i>, <i>Lr37</i>) with adult plant resistance (APR) genes (<i>Lr48</i>, <i>Lr22a</i>, <i>Lr34</i>, <i>Lr46</i>) for durable LR resistance. The identified alleles offer valuable insights for marker-assisted breeding to enhance wheat resistance to LR.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jesús Christopher Castillo-Batista, Francisco Roberto Quiroz-Figueroa, Edgar Antonio Rodríguez-Negrete, Genaro Diarte-Plata, Ruben Felix-Gastelum, Norma Elena Leyva-López, María Elena Santos-Cervantes
{"title":"Identification of Fusarium Species Associated With Dry Rot of Potato Tubers in Sinaloa, Mexico","authors":"Jesús Christopher Castillo-Batista, Francisco Roberto Quiroz-Figueroa, Edgar Antonio Rodríguez-Negrete, Genaro Diarte-Plata, Ruben Felix-Gastelum, Norma Elena Leyva-López, María Elena Santos-Cervantes","doi":"10.1111/jph.70102","DOIUrl":"https://doi.org/10.1111/jph.70102","url":null,"abstract":"<div>\u0000 \u0000 <p>Northern Sinaloa is one of the most important potato-producing regions in Mexico. Potato dry rot caused by species of <i>Fusarium</i> is one of the major threats to potato production. The aim of this study was to identify and characterize <i>Fusarium</i> species associated with potato dry rot. A total of 146 <i>Fusarium</i> isolates were obtained from potato tubers with dry rot symptoms from fields in different geographic regions in northern Sinaloa, Mexico, in 2018–2019. A subgroup of 39 representative isolates was selected for further morphological and molecular characterization as well as pathogenicity tests. According to morphological features and phylogenetic analyses of the transcription elongation factor 1-α (EF1-α) gene, the isolates were identified as <i>F. oxysporum</i> clade 3, <i>F. falciforme</i> (FSSC 3 + 4) and <i>F. nygamai</i>. All representative <i>Fusarium</i> species isolates were pathogenic to potato tubers. Furthermore, a significant difference in virulence between species was observed. Future research should focus on understanding the genetic diversity and population structure of these pathogens in the field.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144292738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Novel Feature Extraction and Siamese Zeiler and Fergus Forward Taylor Network-Based Rice Plant Leaf Disease Detection","authors":"Karthick Muthusamy, Ramprasath Jayaprakash, Vivek Duraivelu, Satheesh Kumar Sabapathy","doi":"10.1111/jph.70074","DOIUrl":"https://doi.org/10.1111/jph.70074","url":null,"abstract":"<div>\u0000 \u0000 <p>Rice leaf disease affects the leaves of the rice plant that are caused by fungi, bacteria or viruses. Leaf disease leads to yellowing, wilting or lesions on the leaves, which affects photosynthesis and minimises crop production. General rice leaf diseases include rice blast, bacterial blight, and leaf smut, which reduce food production and the economic stability of farmers. Hence, rice plant leaf disease detection is an important aspect, which ensures healthy crop yields. Many methods have been proposed for rice plant leaf disease detection, but they did not fully handle the variability in disease symptoms. Therefore, Siamese Zeiler and Fergus Forward Taylor Network (S-ZFFTNet) is developed for rice plant leaf disease detection. First, leaf disease images are collected from the rice leaf bacterial and fungal disease dataset and denoised by anisotropic diffusion. The plant leaf is segmented by conditional Generative Adversarial Network (cGAN). Then, the segmented image is augmented by rotation, colour change, and scaling factor. Then, Fuzzy Local Binary Patterns (FLBP) with wavelet transform features are excerpted from an augmented image. In the rice plant leaf disease detection phase, a new hybrid S-ZFFTNet is utilised, which is the unification of the Siamese Convolutional Neural Network (SCNN), Zeiler and Fergus Network (ZF-Net), and Taylor's series. The results acquired by S-ZFFT-Net are 92.654% of accuracy, 94.654% True Positive Rate (TPR), 91.757% True Negative Rate (TNR), 90.866% precision, and 92.721% F1-score for k fold value 8.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hayfa Jabnoun-Khiareddine, Rania Aydi Ben Abdallah, Messaoud Mars, Mejda Daami-Remadi
{"title":"Neofusicoccum parvum Associated With Dieback and Fruit Rot of Pomegranate in Tunisia","authors":"Hayfa Jabnoun-Khiareddine, Rania Aydi Ben Abdallah, Messaoud Mars, Mejda Daami-Remadi","doi":"10.1111/jph.70091","DOIUrl":"https://doi.org/10.1111/jph.70091","url":null,"abstract":"<div>\u0000 \u0000 <p>Tunisia is one of the main pomegranate (<i>Punica granatum</i> L.) producing countries. During surveys conducted in 2018–2020 in pomegranate orchards along Tunisia's East Coast (Sousse governorate), disease symptoms were observed on cvs. Gabsi and Kalai. Disease incidence was estimated at approximately 10%–20% and disease severity varied from dieback of one shoot or branch to almost complete tree decline. The current study aimed to characterise the etiological agent(s) associated with these symptoms. Fungal isolates associated with the symptoms were identified as <i>Neofusicoccum parvum</i> based on morphological and molecular phylogenetic analyses, using combined sequences of ITS, <i>tef1</i> and β-tubulin (<i>tub2</i>) loci. Pathogenicity tests performed on 1-year-old detached shoots and on fruits demonstrated that <i>N. parvum</i> was pathogenic to pomegranate cv. Gabsi. The response toward <i>N. parvum</i> of pomegranate cultivars commonly grown throughout Tunisia, namely cvs. Gabsi, Garroussi, Zehri, Khedhri and Kalai, was evaluated using artificial inoculation. Results revealed that all cultivars tested were susceptible to fruit infection and rotted completely within 12–15 days post-inoculation. In the detached shoot tests, the eight tested cultivars responded differently to <i>N. parvum</i> isolates. To our knowledge, this is the first report on pomegranate dieback and fruit rot caused by <i>N. parvum</i> in Tunisia and in Africa. In a host range study on eight fruit tree species, all species (fig, olive, apricot, pear, loquat, lemon, cherimoya and guava) displayed symptoms on artificially inoculated shoots, with significant host species–<i>N. parvum</i> isolate interactions observed.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144273382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Plant Disease Detection: PyramidNet-ICNN Architecture With Modified BIRCH Segmentation","authors":"Aarti P. Pimpalkar, Arvind M. Jagtap","doi":"10.1111/jph.70068","DOIUrl":"https://doi.org/10.1111/jph.70068","url":null,"abstract":"<div>\u0000 \u0000 <p>Agriculture stands as the primary occupation in India, yet it faces a substantial annual loss of 35% in crop productivity due to plant diseases. These diseases pose a significant task in the sector of agriculture, emphasising the critical need for their automatic identification to efficiently monitor plant health. The conventional technique of analysis by specialists in laboratories is costly and time-consuming, even though the signs of the majority of diseases appear in plant leaves. Recognising the vital importance of early issue identification, this research proposes a novel hybrid Architecture, a hybrid of PyramidNet and ICNN models (Py-ICNN) for plant disease detection and classification with an Improved BIRCH (I-BIRCH) segmentation model, which uses an image as input. This framework follows a systematic approach, comprising preprocessing, segmentation, extraction of features and detection and classification of diseases. Using median and Contrast Limited Adaptive Histogram Equalisation (CLAHE) filtering, the input image first undergoes enhanced preprocessing. The preprocessed outcome is then subjected to I-Balanced Iterative Reducing and Clustering Using Hierarchies (BIRCH) segmentation. Then, features including IPHOG, multi-texton features and MBP-based features are extracted from the segmented image. These extracted features are then individually processed using PyramidNet and improved convolutional neural network (ICNN) to detect and classify the plant disease. Furthermore, the proposed Py-ICNN model is evaluated and compared with traditional methods. The findings demonstrate that the Py-ICNN framework obtained an accuracy of 93.70% and a specificity of 95.82%. These results demonstrate how well the Py-ICNN approach detects and classifies plant diseases.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144256331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Rice Plant Disease Diagnosis Using SqueezeNet and Deep Transfer Learning","authors":"Santosh Kumar Upadhyay, Anshu Kumar Dwivedi","doi":"10.1111/jph.70092","DOIUrl":"https://doi.org/10.1111/jph.70092","url":null,"abstract":"<div>\u0000 \u0000 <p>Rice serves as a fundamental food source for around 50% of the world's population, mostly in Asia, where agriculturalists have difficulties due to several rice illnesses that may result in substantial crop losses. Timely identification of these illnesses is essential to avert such losses; yet swift and precise diagnosis continues to be challenging owing to constrained knowledge and resources. This research investigates the use of deep transfer learning for the automation of identifying and classifying rice leaf diseases, including blast, brown spot, blight, sheath blight and tungro. We have sourced dataset consisting of 2550 image samples divided into five categories from the Kaggle. Each category has 510 images of infected leaves. By using contrast stretching for image enhancement and data augmentation for data enrichment, we applied a modified SqueezeNet pre-trained deep network on processed dataset, achieved 99.30% accuracy in disease recognition. The final convolutional layer (conv. layer 10) of the pre-trained SqueezeNet is modified by applying multiscale feature aggregation (MFA) in place of 1 × 1 standard convolution. MFA consists of two parallel convolution paths with different kernel size to captures diverse features of the infected lesions. The model's proficiency is highlighted by precision values ranging from 0.972 to 1.000 and recall values between 0.980 and 1.000, whereas maintaining an extremely low error rate between 0.0% and 0.3%, highlighting its high effectiveness. In a comparison with state-of-the-art (SOTA) models under a similar experimental setup, the proposed model demonstrates superior performance in terms of precision, recall, F1-score and accuracy. The proposed method offers a fast, cost-effective and accurate solution to assist farmers in disease detection, even with small datasets and complex backgrounds.</p>\u0000 </div>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"173 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}