Plate 3. Top Row: observed values versus the linear regression model predicted values for each population. The shading of light gray to
black denotes the density of predicted values where the observed values were inside the 95 percent prediction interval. The red dots
denote observed values that where outside the 95 percent prediction interval. Middle Row: histogram of predicted values for the 500
samples used to parameterize each model. Bottom Row: the percent of observed values within the 95 percent prediction interval for
each population. The red line denotes 95 percent in the prediction interval, the solid blue lines denote minimum and maximum predicted
values based on the sample, and the dashed blue lines represent the 99 percent quantile of predicted values for the 500 samples.
(a)
(b)
Plate 4. Half-width of the 95 percent prediction interval for percent tree canopy cover for a portion of (A) the Georgia study area, and
masked predicted percent tree canopy cover with 5 percent error rate for area of no canopy cover overlaid on (B) the NAIP imagery.
196
March 2016
PHOTOGRAMMETRIC ENGINEERING & REMOTE SENSING
