Skip to main content

Table 2 The features and performance of ALS-based models for predicting ratio-scaled ES proxy values. W – Shapiro-Wilk test statistic

From: Predicting the provisioning potential of forest ecosystem services using airborne laser scanning data and forest resource maps

ES Predictor Wa RMSE RMSELOOCV
BIOD ccshrub × h40first 0.965*** 0.259 0.266
+ propfirst/FP_ground × d50first 0.981 0.235 NA
+ diffonly–LP × hstdLP 0.986 0.217 0.226
+ h95first × h10LP 0.977* 0.203 NA
TIMB cconly_ground × hmeanFP 0.977* 0.220 0.228
+ h40last × ccLP_ground 0.970** 0.202 0.213
+ h05last × d05first 0.989 0.182 NA
+ cconly_ground × h10FP 0.988 0.174 NA
CARB ccshrub × h60first 0.980 0.158 0.163
+ h20last × cconly_ground 0.988 0.144 0.152
+ d60first × d30LP 0.987 0.138 0.148
+ propfirst/FP_ground × d05first 0.984 0.132 NA
BILB h60first × h70LP 0.987 0.279 0.286
+ d50only × ccFP_ground 0.984 0.255 0.274
+ runderstory × d05FP 0.982 0.238 NA
+ d70first × d50only 0.984 0.222 0.267
COWB d20LP × h40FP 0.966*** 0.281 0.295
+ diffonly–FP 2 0.981 0.250 NA
+ propfirst/FP_ground × d05first 0.983 0.233 NA
+ d60first × h05only 0.971** 0.217 NA
AMEN h10first × hmeanFP 0.993 0.239 0.246
+ d30last × d70first 0.991 0.219 0.229
+ h20last × ccFP_ground 0.994 0.204 NA
+ hstdfirst × hmeanLP 0.991 0.187 NA
  1. aThe asterisks refer to the significance of the test statistic at the 90% (*), 95% (**), and 99% (***) confidence level