Akademik Veri Yönetim Sistemi
JOURNAL OF CROP SCIENCE AND BIOTECHNOLOGY, cilt.28, sa.3, ss.379-389, 2025 (ESCI)
The flowering stage of buckwheat plays a significant role in determining yield. UAV-based remote sensing using RGB imagery has emerged as a cost-effective and non-invasive tool for monitoring agricultural production. However, the dominance of white flowers in buckwheat canopies during the flowering period disrupts spectral signals, reducing the sensitivity of RGB vegetation indices. With the aim of examining the reliability of vegetative indices derived from UAV-captured RGB images during the flowering period to predict the yield of buckwheat, the correlation between six vegetative indices (ExG, ExR, ExGR, GLI, NDI, and VARI) and the yield components was analyzed. All the green band-based vegetative indices resulted insignificant negative correlations with the seed count and the seed weight. Only the red band-based ExR index showed a positive correlation; however, it was also not significant at p > 0.10. We examined RGB vegetative indices only at the peak flowering stage and UAV images were captured at only 10 m altitude. Overcoming these limitations, developing robust yield estimation methods during the flowering stage is essential to meet the growing demand for buckwheat while ensuring sustainable agricultural practices. We suggest that to integrate advanced multispectral or hyperspectral imagery and texture features in yield prediction models, which have shown promise in enhancing prediction accuracy.