IN-FIELD VARIABILITY DETECTION AND SPATIAL YIELD MODELING FOR CORN USING DIGITAL AERIAL IMAGING

摘要: High-resolution color infrared (CIR) images acquired with an airborne digital camera were used to detect infield spatial variability in soil type, crop nutrient stress, and analyze spatial yield. Images processed using unsupervised learning (clustering) method. The clustered geo-referenced, spatially analyzed using a GIS package. image patterns processed of bare matched well type map 76% accuracy. CIR cornfield indicated nitrogen stress areas from 75 days after planting (DAP). CIR reflectance was better correlated the yield pollination corn compared early images. variation in linearly variation individual reflectance bands (NIR, R, G) as as normalized intensity (NI) image. Spatial models on uncalibrated could predict 76 to 98% each field. A linear regression model NI developed one field predicted yield with accuracy 55 91% different fields seasons. Digital aerial imaging proves be promising tool for obtaining in-field for site-specific management prediction.