Automated detection of downy mildew and powdery mildew symptoms for vineyard disease management

被引:0
作者
Ghiani, Luca [1 ,3 ]
Serra, Salvatorica [2 ,3 ]
Sassu, Alberto [2 ]
Deidda, Alessandro [2 ]
Deidda, Antonio [2 ]
Gambella, Filippo [2 ,3 ]
机构
[1] Univ Sassari, Dept Biomed Sci, Viale San Pietro 43-B, I-07100 Sassari, Italy
[2] Univ Sassari, Dept Agr Sci, Viale Italia 39a, I-07100 Sassari, Italy
[3] Interdept Ctr IA INNOVAT AGR Loc Surigheddu, SS 127 bis,Kim 28,500, Alghero Ss 07041, Italy
来源
SMART AGRICULTURAL TECHNOLOGY | 2025年 / 11卷
关键词
Plasmopara viticola; Erysiphe necator; Disease detection; Precision agriculture; Artificial intelligence; Deep learning;
D O I
10.1016/j.atech.2025.100877
中图分类号
S2 [农业工程];
学科分类号
0828 ;
摘要
This work focuses on developing an automated system for detecting downy mildew and powdery mildew symptoms in grapevines, with particular attention to the role of data partitioning and dataset diversity in ensuring reliable model performance. Leveraging deep learning techniques, specifically the YOLO (You Only Look Once) object detection model, we aimed to provide a robust tool for disease detection, which is crucial for optimizing vineyard management, increasing crop yield, and promoting sustainable agricultural practices. Over two years, we collected and expertly annotated a large dataset of images depicting downy and powdery mildew symptoms in field conditions. The YOLO model was trained and validated on this dataset, achieving a mean Average Precision (mAP) of 0.730, demonstrating good detection accuracy. A key contribution of this study is the emphasis on the importance of proper data partitioning strategies, showing that random image partitioning can lead to an overestimation of model performance. Our findings underscore that true improvements in detection accuracy are driven not merely by increasing the number of images but by enhancing the diversity of the dataset, particularly for the areas, seasons, growth stages, and conditions in which the images are captured. This approach ensures a more realistic assessment of the system's performance, critical for deploying such systems in practical, real-world agricultural scenarios. The results highlight the potential of deep learning models to enhance vineyard management through a reliable and efficient detection of diseases in real-world conditions.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Grapevine Powdery Mildew: Fungicides for Its Management and Advances in Molecular Detection of Markers Associated with Resistance
    Kunova, Andrea
    Pizzatti, Cristina
    Saracchi, Marco
    Pasquali, Matias
    Cortesi, Paolo
    MICROORGANISMS, 2021, 9 (07)
  • [42] Precision detection of grapevine downy and powdery mildew diseased leaves and fruits using enhanced ResNet50 with batch normalization
    Sagar, N.
    Suresh, K. P.
    Sridhara, Shankarappa
    Patil, Balanagouda
    Archana, C. A.
    Sekar, Yamini Sri
    Naveesh, Y. B.
    Nandan, A. S.
    Sushma, R.
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2025, 232
  • [43] Image analysis with deep learning for early detection of downy mildew in grapevine
    Hernandez, Ines
    Gutierrez, Salvador
    Tardaguila, Javier
    SCIENTIA HORTICULTURAE, 2024, 331
  • [44] Optimization of integrated pest management for powdery mildew (Unincula necator) control in a vineyard based on a combination of phenological, meteorological and aerobiological data
    Fernandez-Gonzalez, M.
    Rodriguez-Rajo, F. J.
    Escuredo, O.
    Aira, M. J.
    JOURNAL OF AGRICULTURAL SCIENCE, 2013, 151 (05) : 648 - 658
  • [45] Downy mildew management in protected cultivation of table grapes 'BRS Clara'
    Genta, Werner
    Tessmann, Dauri Jose
    Roberto, Sergio Ruffo
    Vida, Joao Batista
    Colombo, Larissa Abgariani
    Scapin, Claudia Regina
    Ricce, Willian da Silva
    Clovis, Luiz Rafael
    PESQUISA AGROPECUARIA BRASILEIRA, 2010, 45 (12) : 1388 - 1395
  • [46] Composition and Tissue-Specific Distribution of Stilbenoids in Grape Canes Are Affected by Downy Mildew Pressure in the Vineyard
    Houille, Benjamin
    Besseau, Sebastien
    Delanoue, Guillaume
    Oudin, Audrey
    Papon, Nicolas
    Clastre, Marc
    Simkin, Andrew John
    Guerin, Laurence
    Courdayault, Vincent
    Giglioli-Guiyarc'h, Nathalie
    Lanoue, Arnaud
    JOURNAL OF AGRICULTURAL AND FOOD CHEMISTRY, 2015, 63 (38) : 8472 - 8477
  • [47] Multivariate forecasting model to optimize management of grape downy mildew control
    Menesatti, P.
    Antonucci, F.
    Costa, C.
    Mandala, C.
    Battaglia, V.
    La Torre, A.
    VITIS, 2013, 52 (03) : 141 - 148
  • [48] Wheat Powdery Mildew Detection with YOLOv8 Object Detection Model
    Onler, Eray
    Koycu, Nagehan Desen
    APPLIED SCIENCES-BASEL, 2024, 14 (16):
  • [49] Cucumber powdery mildew detection method based on hyperspectra-terahertz
    Zhang, Xiaodong
    Wang, Pei
    Wang, Yafei
    Hu, Lian
    Luo, Xiwen
    Mao, Hanping
    Shen, Baoguo
    FRONTIERS IN PLANT SCIENCE, 2022, 13
  • [50] Effect of Fungicide Mobility and Application Timing on the Management of Grape Powdery Mildew
    Warneke, Brent
    Thiessen, Lindsey D.
    Mahaffee, Walter F.
    PLANT DISEASE, 2020, 104 (04) : 1167 - 1174