Prediction of Ratoon Sugarcane Family Yield and Selection Using Remote Imagery

Remote sensing techniques and the use of Unmanned Aerial Systems (UAS) have simplified estimation yield plant health in many crops. Family selection sugarcane breeding programs relies on weighed plots at harvest, which is a labor-intensive process. In this study, we utilized UAS-based remote imagery plant-cane first ratoon crops to estimate family yields for second crop. Multiple families from commercial program were planted randomized complete block design by family. Standard red, green, blue was acquired with commercially available UAS equipped Red–Green–Blue (RGB) camera. Color indices using CIELab color space model estimated each plot. The cane mechanically harvested combine harvester plot weights obtained (kg) field wagon load cells. Stepwise regression, correlations, variance inflation factors used identify best multiple linear regression (kg). A model, included family, five different produced significant R2 0.88. This indicates that it possible make predictions weight without collecting weights. adoption technology has potential decrease labor requirements increase efficiency.