Fig. 5From: High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV dataBox plots of differences between actual and predicted fresh soybean biomass (kg/m2) obtained with random forest (RF) and partial least squares regression (PLSR) with reduced set of predictors. The error bars show the 95% confidence interval while the line inside the boxes represent the median valueBack to article page