EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Early surveillance of rice bakanae disease using deep learning and hyperspectral imaging

Sishi Chen, Xuqi Lu, Hongda Fang, Anand Babu Perumal, Ruyue Li, Lei Feng, Mengcen Wang, Yufei Liu

aBIOTECH · 2024-09 · 5 (3) · 281-297

DOI: 10.1007/s42994-024-00169-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift aBIOTECH, 2024-09. Verfasst von Sishi Chen und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, 310058 China. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Key Research and Development Project, Zhejiang province agricultural machinery research, manufacturing and application integration project, International S&T Cooperation Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bakanae disease, caused by Fusarium fujikuroi, poses a significant threat to rice production and has been observed in most rice-growing regions. The disease symptoms caused by different pathogens may vary, including elongated and weak stems, slender and yellow leaves, and dwarfism, as example. Bakanae disease is likely to cause necrosis of diseased seedlings, and it may cause a large area of infection in the field through the transmission of conidia. Therefore, early disease surveillance plays a crucial role in securing rice production. Traditional monitoring methods are both time-consuming and labor-intensive and cannot be broadly applied. In this study, a combination of hyperspectral imaging technology and deep learning algorithms were used to achieve in situ detection of rice seedlings infected with bakanae disease. Phenotypic data were obtained on the 9th, 15th, and 21st day after rice infection to explore the physiological and biochemical performance, which helps to deepen the research on the disease mechanism. Hyperspectral data were obtained over these same periods of infection, and a deep learning model, named Rice Bakanae Disease-Visual Geometry Group (RBD-VGG), was established by leveraging hyperspectral imaging technology and deep learning algorithms. Based on this model, an average accuracy of 92.2% was achieved on the 21st day of infection. It also achieved an accuracy of 79.4% as early as the 9th day. Universal characteristic wavelengths were extracted to increase the feasibility of using portable spectral equipment for field surveillance. Collectively, the model offers an efficient and non-destructive surveillance methodology for monitoring bakanae disease, thereby providing an efficient avenue for disease prevention and control. Supplementary Information: The online version contains supplementary material available at 10.1007/s42994-024-00169-1.

Schlagwörter

Stichwörter der Autor:innen

Bakanae diseaseDeep learningDisease monitoringEarly surveillanceHyperspectral imaging

Autor:innen und Institutionen

  • College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, 310058 China.
  • State Key Laboratory of Rice Biology and Breeding, Zhejiang University, Hangzhou, 310058 China.
  • Computational Modeling and Nanoscale Processing Unit, National Institute of Food Technology, Entrepreneurship and Management - Thanjavur, Ministry of Food Processing Industries, Thanjavur, 613005 India.
  • College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, 310058 China.
  • Global Education Program for AgriScience Frontiers, Graduate School of Agriculture, Hokkaido University, Sapporo, 060-8589 Japan.

Förderung

  • National Key Research and Development Project
  • Zhejiang province agricultural machinery research, manufacturing and application integration project
  • International S&T Cooperation Program of China
  • National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Chen, S., Lu, X., Fang, H., Perumal, A. B., Li, R., Feng, L., Wang, M., & Liu, Y. (2024). Early surveillance of rice bakanae disease using deep learning and hyperspectral imaging. aBIOTECH, 5(3), 281-297. https://doi.org/10.1007/s42994-024-00169-1

Vancouver

Chen S, Lu X, Fang H, Perumal AB, Li R, Feng L, et al. Early surveillance of rice bakanae disease using deep learning and hyperspectral imaging. aBIOTECH. 2024;5(3):281-297. doi:10.1007/s42994-024-00169-1

BibTeX
@article{Chen2024,
  author = {Chen, Sishi and Lu, Xuqi and Fang, Hongda and Perumal, Anand Babu and Li, Ruyue and Feng, Lei and Wang, Mengcen and Liu, Yufei},
  title = {Early surveillance of rice bakanae disease using deep learning and hyperspectral imaging},
  journal = {aBIOTECH},
  year = {2024},
  volume = {5},
  number = {3},
  pages = {281--297},
  doi = {10.1007/s42994-024-00169-1}
}
Kostenlos starten →