Akademik Veri Yönetim Sistemi
Smart Agricultural Technology, cilt.4, 2023 (Scopus)
The early prediction of crop yield is a vital component of agricultural planning and policy decision-making. In order to achieve this, many countries utilize conventional techniques such as crop growth models that simulate agricultural applications. Alternatively, some approaches involve the spatio-temporal monitoring of vegetation conditions. In this study, we aimed to evaluate the potential for silage maize yield estimation using vegetation indices, including the Normalized Difference Vegetation Index (NDVI), Soil-Adjustment Vegetation Index (SAVI), and Simple Ratio (SR), through the use of PlanetScope, Sentinel-2A, and Landsat 8 OLI satellite images. Linear regression was employed to examine the relationship between silage maize yield and calculated spectral vegetation indices (SVI) at various dates. The results revealed significant correlations between remotely sensed SVI and silage maize yield values for four large-scale plots. Specifically, it was found that silage maize yield could be estimated most accurately using SR between Days After Sowing (DAS) 73 and DAS 76 at a p-value of <0.01. Additionally, yield could be successfully estimated using these three satellite images and indices between DAS 33 and DAS 69 at the p<0.05 level.