This replication study builds upon previous research on the use of drones for crop monitoring in vineyards within South Africa. Drone imagery was collected at six vineyards annually for one year following the same protocol as the original study. Data were analysed using a linear mixed-effects model to predict crop yields based on drone-derived metrics such as leaf area index (LAI) and canopy height. The average prediction error of yield varied between sites, with an overall mean absolute percentage error (MAPE) of 12%, indicating that while there was variability, the general trend in accuracy remained consistent over time. Consistent findings were observed across all vineyards, confirming the reliability and effectiveness of drone technology for crop monitoring and yield prediction. Further research could focus on integrating drones with other precision agriculture tools to enhance decision-making processes in vineyard management. Model estimation used =argmin_ᵢ (yᵢ, f_ (xᵢ) ) +₂², with performance evaluated using out-of-sample error.
Nkosingiphani Khumalo (Wed,) studied this question.