Validation of Unmanned Aerial System (UAS) Data for Cotton Research

Unmanned Aerial System (UAS) technologies are rapidly evolving, enabling high throughput temporal data collection of growth, health, and yield parameters during the growing season. Automated computer algorithms extract biological information from images, creating a new opportunity to study crops' response to the environment. A field trial was conducted in 2017 to test and validate UAS measurements for use in agriculture research and plant breeding applications. Ground data was collected weekly. The field trial consisted of 5 genotypes, replicated four times. Plots were either 1 (skip pattern) or 2 rows wide by 10m long in a randomized complete block design. The skip pattern was used to test if it would improve estimates of boll-counting computer algorithms, as compared to ground assessments. UAS platforms equipped with natural color (RGB) and multispectral sensors were used to collect data over the test field on a weekly basis during the growing season. Crop data such as plant height, growth rate, canopy cover, canopy cover progression, and boll count and size estimates were extracted. The multi-temporal data was analyzed to find the best trait combination to characterize plant growth and development, and predict crop yield.