Model Validation

To validate the dynamic forest structure model, we iteratively withheld 1/10th of the training data in a k-fold crossvalidation exercise on 25,000 training locations distributed across the Cascadia region. Each fold was spatially independent, so the withheld fold did not overlap in space with the training folds. The table below shows the r2 adjusted, root mean square error (RMSE) for each variable, averaged across the 10 folds in the crossvalidation.

Variable	r2 Adjusted	RMSE	Units
Canopy Cover	0.960	14.50	%
Tree Diameter	0.905	1.40	cm
Canopy Height	0.884	9.38	m