EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Deep Learning for Sigatoka and Cordana Disease Classification in Peruvian Amazon Banana Crops

Yasiel Pérez Vera, Iván Edgardo Reaño-Soto, Rodrigo Alonso Sucapuca Santamarina, Leonardo Oliver Lonasco-Santamarina

AgriEngineering · 19.11.2026 · 8 (11) · 499

DOI: 10.3390/agriengineering8110499 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AgriEngineering, online erschienen am 19.11.2026. Verfasst von Yasiel Pérez Vera und 3 weiteren Autor:innen. Die Arbeit nennt 90 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Catholic University of Santa María.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sigatoka and Cordana leaf spot are major fungal diseases that severely reduce banana crop yields. In-field diagnosis currently relies on manual visual inspection by trained personnel, a time-consuming process that cannot scale effectively across all cultivation plots. Diagnostic complexity is further heightened because both pathogens produce visually similar necrotic lesions with chlorotic yellow margins. To address this, this study benchmarks six deep learning architectures for classifying Sigatoka, Cordana, and healthy banana leaf images under field conditions. Three convolutional neural networks (ResNet50, EfficientNetB0, MobileNetV2), two Vision Transformers (ViT-B/16, Swin-T), and one hybrid model (CoAtNet-0) were evaluated. All models were initialized with ImageNet weights and trained under identical conditions with five random seeds on 1886 of the 2354 images. Performance was assessed on an independent test set of 232 images gathered across four full sampling days omitted from training, utilizing Wilson confidence intervals, a bootstrap of burst groups, and McNemar’s test. Swin-T achieved the highest mean accuracy (97.76%), followed by ResNet50 (96.47%), while MobileNetV2 had the lowest mean accuracy (93.79%). Following Bonferroni correction, no pair of models differed in all five seeds, and the group bootstrap separated only Swin-T from MobileNetV2 and ViT-B/16. At the same time, 211 of 298 total errors stemmed from mutual confusion between Sigatoka and Cordana. These results show that differences in a few test images between models are not statistically significant, and that field use requires validation on mobile devices and in other regions.

Förderung

  • Catholic University of Santa María

Zitieren

APA

Vera, Y. P., Reaño-Soto, I. E., Santamarina, R. A. S., & Lonasco-Santamarina, L. O. (2026). Hybrid Deep Learning for Sigatoka and Cordana Disease Classification in Peruvian Amazon Banana Crops. AgriEngineering, 8(11), 499. https://doi.org/10.3390/agriengineering8110499

Vancouver

Vera YP, Reaño-Soto IE, Santamarina RAS, Lonasco-Santamarina LO. Hybrid Deep Learning for Sigatoka and Cordana Disease Classification in Peruvian Amazon Banana Crops. AgriEngineering. 2026;8(11):499. doi:10.3390/agriengineering8110499

BibTeX
@article{Vera2026,
  author = {Vera, Yasiel Pérez and Reaño-Soto, Iván Edgardo and Santamarina, Rodrigo Alonso Sucapuca and Lonasco-Santamarina, Leonardo Oliver},
  title = {Hybrid Deep Learning for Sigatoka and Cordana Disease Classification in Peruvian Amazon Banana Crops},
  journal = {AgriEngineering},
  year = {2026},
  volume = {8},
  number = {11},
  pages = {499},
  doi = {10.3390/agriengineering8110499}
}
Kostenlos starten →