Sunflower crop yield prediction by advanced statistical modeling using satellite-derived vegetation indices and crop phenology

Timely crop yield information is needed for agricultural land management and food security. We investigated using remote sensing data from the Earth observation mission Sentinel-2 to monitor phenology predict of sunflowers at field scale. Ten sunflower fields in Mezőhegyes, southeastern Hungary, were monitored 2021, was measured by a combine harvester. Images collected throughout monitoring period, vegetation indices (VIs) extracted growth. Multiple linear regression two different machine learning approaches applied predicting yield, best-performing one selected further analysis. The results as follows. VIs showed highest correlation with (R > 0.6) during inflorescence emergence stage. most suitable time 86–116 days after sowing. Random forest (RFR) best approach field-scale variability (R2 ∼ 0.6 RMSE 0.284–0.473 t/ha). Our can be used develop timely robust prediction method yields scale support decision-making policymakers regarding