EUVIMEDEUVIMED entdecken
Crossref

Early detection of banana fusarium wilt caused by Fusarium oxysporum f. sp. cubense using hyperspectral with a metric learning strategy

Hao-Tian Yuan iD, Jie-Li Duan, Wei-Gui Ke, Shu-Jie Feng, Chao-Wei Huang, Yin-Long Jiang, Dan-Dan Xiang, Zhou Yang

Pest Management Science · 2026

DOI: 10.1002/ps.70561 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pest Management Science, 2026. Verfasst von Hao-Tian Yuan und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering, South China Agricultural University, Guangzhou, China. Hauptthemen laut MEDLINE: Musa, Fusarium, Plant Diseases, Hyperspectral Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: Jie-liDuan, National Natural Science Foundation of China, China Agriculture Research System of MOF and MARA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND Fusarium wilt of banana, caused by Fusarium oxysporum f. sp. cubense Tropical Race 4 ( Foc TR4), poses a severe threat to global banana production. Early detection of this disease remains a major challenge, as infection is often widespread before visible symptoms appear. The identification of plants in the crucial asymptomatic stage is therefore paramount for effective control. To address this, we explored the potential of short‐wave infrared (SWIR) hyperspectral sensing combined with deep metric learning for early‐stage disease diagnosis. RESULTS Based on hyperspectral data acquired from inoculated banana plantlets, a two‐stage genetic algorithm‐Shapley additive explanation (GA‐SHAP) strategy was employed for band selection, yielding a compact subset of physiologically meaningful spectral bands. A hyperspectral classification framework integrating a one‐dimensional convolutional neural network (1D‐CNN) with an improved metric learning loss function was then developed to enhance sensitivity to subtle infection‐induced changes. The proposed method achieved an average classification accuracy of 85.73% using only six selected bands. Crucially, the framework demonstrated exceptional early detection capability, achieving a diagnostic sensitivity exceeding 90%. Furthermore, spectral variations and underlying physiological mechanisms associated with Foc infection were analyzed, providing insights for scalable remote sensing applications. CONCLUSION This study demonstrates that the integration of band selection and metric learning enables accurate and efficient early detection of Foc ‐induced banana wilt. The proposed framework not only offers a powerful tool for the early diagnosis of this devastating disease but also holds great promise for monitoring other plant–pathogen systems. © 2026 Society of Chemical Industry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MusaFusariumPlant DiseasesHyperspectral ImagingConvolutional Neural Networks

Stichwörter der Autor:innen

banana fusarium wiltearly disease detectionhyperspectral classificationmetric learning

Autor:innen und Institutionen

  • College of Engineering, South China Agricultural University, Guangzhou, China.
  • College of Horticulture, South China Agricultural University, Guangzhou, China.
  • Institute of Fruit Tree Research, Guangdong Academy of Agricultural Sciences, Guangzhou, China.
  • School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang, China.

ORCID-Profile: Hao-Tian Yuan

Förderung

  • Jie-liDuan
  • National Natural Science Foundation of China
  • China Agriculture Research System of MOF and MARA
  • Science and Technology Planning Project of Guangzhou

Zitieren

APA

Yuan, H. T., Duan, J. L., Ke, W. G., Feng, S. J., Huang, C. W., Jiang, Y. L., Xiang, D. D., & Yang, Z. (2026). Early detection of banana fusarium wilt caused by Fusarium oxysporum f. sp. cubense using hyperspectral with a metric learning strategy. Pest Management Science. https://doi.org/10.1002/ps.70561

Vancouver

Yuan HT, Duan JL, Ke WG, Feng SJ, Huang CW, Jiang YL, et al. Early detection of banana fusarium wilt caused by Fusarium oxysporum f. sp. cubense using hyperspectral with a metric learning strategy. Pest Management Science. 2026. doi:10.1002/ps.70561

BibTeX
@article{Yuan2026,
  author = {Yuan, Hao-Tian and Duan, Jie-Li and Ke, Wei-Gui and Feng, Shu-Jie and Huang, Chao-Wei and Jiang, Yin-Long and Xiang, Dan-Dan and Yang, Zhou},
  title = {Early detection of banana fusarium wilt caused by Fusarium oxysporum f. sp. cubense using hyperspectral with a metric learning strategy},
  journal = {Pest Management Science},
  year = {2026},
  doi = {10.1002/ps.70561}
}
Kostenlos starten →