Skip to main content

Advertisement

Table 6 Model improvement ratio (MIR) scores of explanatory variables in random forest (RF) models predicting percent recovery of the Normalized Burn Ratio (NBR) nine years post fire. Variable importance scores range between 0 and 1, with 1 indicating most important and 0 indicating least important. dNBR = diffrenced Normalzed Burn Ratio. See Table 2 for definitions of variables

From: Examining post-fire vegetation recovery with Landsat time series analysis in three western North American forest types

Variable Model improvement ratio scores
Ponderosa pine Mixed conifer Conifer−oak−chaparral
Pre-fire NBR 0.9 1.0 1.0
dNBR 0.3 0.5 0.6
MAP 0.9 0.8 0.7
GSP 0.7 0.7 0.6
WINP 0.8 0.8 0.8
MAT 1.0 0.6 0.7
MMAX 0.7 0.9 0.8
MMIN 0.8 0.7 0.8
DIST 0.1 0.1 0.3
CURV 0.1 0.2 0.2
SLOPE 0.2 0.2 0.4
TRASP 0.1 0.1 0.2