EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal RGB–Thermal Deep Learning for Red Palm Weevil Damage Classification in Date Palms with a Tree-Level Evaluation of Six Backbone Architectures

Jumana Mohamed Ahmed, Mohammed Melhi, A. A. Somaie

Computational Discovery and Intelligent Systems (CDIS) · 30.06.2026 · 4 (1) · 1-19

DOI: 10.66279/cv4ss337 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Discovery and Intelligent Systems (CDIS), online erschienen am 30.06.2026. Verfasst von Jumana Mohamed Ahmed und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The red palm weevil (Rhynchophorus ferrugineus) is the most destructive pest of date palm (Phoenix dactylifera L.), feeding inside the trunk and destroying vascular tissue well before any external symptom becomes visible. Field surveys, acoustic sensing, and single-modality imaging each address part of this early-detection problem but none jointly exploits the complementary visual and thermal symptoms that a weevil infestation produces. This study introduces a dual-branch deep learning framework that fuses paired RGB and thermal photographs of individual date palms for four-class health classification (non-infected, infected, badly damaged, dead). Six convolutional and transformer backbones, namely ResNet-50, EfficientNet-B0, ConvNeXt-Tiny, Xception, ViT-Small, and ConvNeXt V2-Tiny, are trained under one identical protocol that combines a multi-scale feature-pyramid fusion neck, thermal-guided spatial attention, efficient channel attention, class-balanced focal loss, prototype-based contrastive regularization, curriculum-scheduled mixup and CutMix, and a stochastic weight averaging tail phase. Evaluation uses a leakage-free, tree-level split of 179 field-surveyed palms (125 train, 27 validation, 27 test trees) with 95% bootstrap confidence intervals and paired McNemar and DeLong significance testing. The strongest individual backbone, ConvNeXt-Tiny, reaches 74.6% test accuracy and a macro-F1 of 0.764; a calibration-weighted ensemble of all six backbones reaches 76.2% accuracy with a macro-F1 of 0.756 (95% bootstrap interval, 0.65 to 0.86 for accuracy). Ensembling yields a statistically significant gain over the two weakest backbones but not over the stronger individual models at this sample size, indicating that multimodal fusion and ensembling provide measurable, architecture-dependent gains that remain modest on a dataset of this scale.

Zitieren

APA

Ahmed, J. M., Melhi, M., & Somaie, A. A. (2026). Multimodal RGB–Thermal Deep Learning for Red Palm Weevil Damage Classification in Date Palms with a Tree-Level Evaluation of Six Backbone Architectures. Computational Discovery and Intelligent Systems (CDIS), 4(1), 1-19. https://doi.org/10.66279/cv4ss337

Vancouver

Ahmed JM, Melhi M, Somaie AA. Multimodal RGB–Thermal Deep Learning for Red Palm Weevil Damage Classification in Date Palms with a Tree-Level Evaluation of Six Backbone Architectures. Computational Discovery and Intelligent Systems (CDIS). 2026;4(1):1-19. doi:10.66279/cv4ss337

BibTeX
@article{Ahmed2026,
  author = {Ahmed, Jumana Mohamed and Melhi, Mohammed and Somaie, A. A.},
  title = {Multimodal RGB–Thermal Deep Learning for Red Palm Weevil Damage Classification in Date Palms with a Tree-Level Evaluation of Six Backbone Architectures},
  journal = {Computational Discovery and Intelligent Systems (CDIS)},
  year = {2026},
  volume = {4},
  number = {1},
  pages = {1--19},
  doi = {10.66279/cv4ss337}
}
Kostenlos starten →