GNN Trend Tool

Olofsson et al. (2013) provide a method to use a confusion matrix of observed vs. predicted map classes to adjust modeled area estimates based on class accuracies. The error matrix to the right provides the accuracy associated with the currently selected series' classes at selected FIA annual plot locations. Each mapped series also has a corresponding error-adjusted area estimate and 95% confidence interval for each class in the chart below (excluding grouped classes).

Use the checkbox below to control the visibility of these error-adjusted series.

Olofsson, P, GM Foody, SV Stehman, CE Woodcock. 2103. Making better use of accuracy data in land change studies: Estimating accuracy and area and quantifying uncertainty using stratified estimation. Remote Sensing of Environment 129: 122-131