EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hyperspectral Imaging and Machine Learning for Huanglongbing Detection on Leaf-Symptoms

Ruihao Dong, Aya Shiraiwa, Katsuya Ichinose, Achara Pawasut, Kesaraporn Sreechun, Sumalee Mensin, Takefumi Hayashi

Plants · 03.02.2025 · 14 (3) · 451

DOI: 10.3390/plants14030451 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plants, online erschienen am 03.02.2025. Verfasst von Ruihao Dong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Informatics, Kansai University, Osaka 569-1095, Japan. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI in Japan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Huanglongbing is one of the most destructive diseases of citrus worldwide. Infected trees die due to the absence of practical cures. Thus, the removal of HLB-infected trees is one of the principal HLB managements for the regulation of disease spread. Here, we propose a non-destructive HLB detection method based on hyperspectral leaf reflectance. In total, 72 hyperspectral leaf images were collected in an HLB-invaded citrus orchard in Thailand and each image was visually distinguished into either any HLB symptom appearance (symptomatic) or no symptoms (asymptomatic) on the leaf. Principal component analysis was applied on the hyperspectral data and revealed 16 key wavelengths at red-edge to near-infrared regions (715, 718, 721, 724, 727, 730, 733, 736, 930, 933, 936, 939, 942, 945, 957, and 997 nm) that were characteristically differentiated in the symptomatic group. Seven models learnt on the spectral data at these 16 wavelengths were examined for the potential to separate these two image groups: random forest, decision tree, support vector machine, k-nearest neighbor, gradient boosting, logistic regression, linear discriminant. F1-score was employed to select the best-fit model to distinguish the two categories: random forest achieved the best score of 99.8%, followed by decision tree and k-nearest neighbor. The reliability of the visual grouping was evaluated by nearest neighbor matching and permutation test. These three models separated the two image categories as precisely as PCR results, indicating their potential as alternative tool instead of PCR.

Schlagwörter

Stichwörter der Autor:innen

Citrus reticulatacitrus greening diseasedisease diagnosisfeature extractionmultivariate analysis

Autor:innen und Institutionen

  • Faculty of Informatics, Kansai University, Osaka 569-1095, Japan.
  • Electrical Engineering and Computer Science, Tottori University, Tottori 680-8552, Japan.
  • Independent Researcher, Tsukuba 300-1252, Japan.
  • Royal Project Foundation, 910 Moo 3, T. Maehia, Muang, Chiang Mai 50200, Thailand.

Förderung

  • JSPS KAKENHI in Japan

Zitieren

APA

Dong, R., Shiraiwa, A., Ichinose, K., Pawasut, A., Sreechun, K., Mensin, S., & Hayashi, T. (2025). Hyperspectral Imaging and Machine Learning for Huanglongbing Detection on Leaf-Symptoms. Plants, 14(3), 451. https://doi.org/10.3390/plants14030451

Vancouver

Dong R, Shiraiwa A, Ichinose K, Pawasut A, Sreechun K, Mensin S, et al. Hyperspectral Imaging and Machine Learning for Huanglongbing Detection on Leaf-Symptoms. Plants. 2025;14(3):451. doi:10.3390/plants14030451

BibTeX
@article{Dong2025,
  author = {Dong, Ruihao and Shiraiwa, Aya and Ichinose, Katsuya and Pawasut, Achara and Sreechun, Kesaraporn and Mensin, Sumalee and Hayashi, Takefumi},
  title = {Hyperspectral Imaging and Machine Learning for Huanglongbing Detection on Leaf-Symptoms},
  journal = {Plants},
  year = {2025},
  volume = {14},
  number = {3},
  pages = {451},
  doi = {10.3390/plants14030451}
}
Kostenlos starten →