EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Chlorophyll attention network using MobileViTv2 for on-device plant health monitoring

Rabia Zafar, Muhammad Shahid Farid, Muhammad Hassan Khan, Rashid Mahmood

Plant Protection · 01.03.2026 · 10 (1) · 125-133

DOI: 10.33804/pp.010.01.6011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plant Protection, online erschienen am 01.03.2026. Verfasst von Rabia Zafar und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate assessment of leaf chlorophyll content is critical for precision nitrogen management in maize (Zea mays L.), yet conventional SPAD meters are labor-intensive and limited in scalability. To address this, a regression framework integrating MobileViT, Chlorophyll Attention (CA), and a multi-modal fusion mechanism for rapid, image-based SPAD value prediction was proposed. An ablation study quantified the contribution of each architectural component. The full model achieved a baseline coefficient of determination (R²) of 0.6832, confirming robust predictive capability. Removal of the MobileViT block caused the largest performance decline (R² = 0.6564), emphasizing its critical role in feature representation. Excluding the CA module (R² = 0.6721) or the multi-modal fusion mechanism (R² = 0.6368) further highlighted the necessity of synergistic component integration for optimal performance. Using 5-fold cross-validation, the base model attained a mean R² of 0.7099, which was further enhanced to 0.7345 through ensemble learning and four-way test-time augmentation. The improved model achieved a Root Mean Square Error (RMSE) of 4.264 SPAD units and Mean Absolute Error (MAE) of 3.649 SPAD units. Comparative evaluation demonstrated that the proposed approach outperformed state-of-the-art architectures, including EfficientNet-B3 (R² = 0.7078) and deeper ResNet variants, highlighting its robustness and generalization capability. The model’s rapid inference ensures suitability for real-time, edge-device deployment in field conditions. The study confirms that each component enhances predictive accuracy, and that ensemble learning with TTA further improves reliability, providing a scalable, high-throughput solution for efficient, data-driven chlorophyll assessment.

Zitieren

APA

Zafar, R., Farid, M. S., Khan, M. H., & Mahmood, R. (2026). Chlorophyll attention network using MobileViTv2 for on-device plant health monitoring. Plant Protection, 10(1), 125-133. https://doi.org/10.33804/pp.010.01.6011

Vancouver

Zafar R, Farid MS, Khan MH, Mahmood R. Chlorophyll attention network using MobileViTv2 for on-device plant health monitoring. Plant Protection. 2026;10(1):125-133. doi:10.33804/pp.010.01.6011

BibTeX
@article{Zafar2026,
  author = {Zafar, Rabia and Farid, Muhammad Shahid and Khan, Muhammad Hassan and Mahmood, Rashid},
  title = {Chlorophyll attention network using MobileViTv2 for on-device plant health monitoring},
  journal = {Plant Protection},
  year = {2026},
  volume = {10},
  number = {1},
  pages = {125--133},
  doi = {10.33804/pp.010.01.6011}
}
Kostenlos starten →