BY-PLANT PREDICTION OF CORN GRAIN YIELD USING OPTICAL SENSOR READINGS AND MEASURED PLANT HEIGHT

Abstract

Indirect sensor-based measurements have made on-the-go by-plant recognition possible. This in turn has enabled high resolution by-plant management. The objective of this study was to estimate final grain yield of each corn (Zea mays L.) plant by collecting the normalized difference vegetation index (NDVI), plant height, and distance between plants at the 8-leaf growth stage (V8). The NDVI readings were collected every 1.2 cm in rows 15 to 30 m in length, and average NDVI per plant was calculated by assuming each plant occupied half the distance between it and its neighbors and calculating an average NDVI value within that respective area. First, an equation was developed to calculate the distance occupied by each plant. Then plant height was used in an equation to estimate competition among plants. A combined model employing plant height, area occupied, and NDVI were used to successfully predict by-plant corn grain yields at V8.