Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery

Harvester-mounted yield monitor sensors are expensive and require calibration data cleaning. Therefore, we evaluated six vegetation indices (VI) from unmanned aerial system (Quantix™ Mapper) imagery for corn (Zea mays L.) prediction. A field trial was conducted with N sidedress treatments applied at four growth stages (V4, V6, V8, or V10) compared against zero-N N-rich controls. Normalized difference index (NDVI) enhanced 2 (EVI2), based on flights R4, resulted in the most accurate estimations, as long sidedressing performed before V6. Yield estimations earlier were less accurate. Estimations when both control plots included, but elimination of only slightly reduced accuracy. Use a ratio approach (VITrt/VIN-rich YieldTrt/YieldN-rich) enables extension findings across fields model performance. Finally, smaller plot size (9 75 m2 to 150 m2) We concluded that estimates can be obtained using NDVI EVI2, there is an strip field, prior sensing takes place R3 R4.