Skip to main content

Table 2 Variable importance (0–1) for SDM of current Scots pine and downy oak distribution fitted by generalized linear model (GLM), artificial neural network (ANN), and multiple adaptive regression spline (MARS)

From: An improved species distribution model for Scots pine and downy oak under future climate change in the NW Italian Alps

  Scots pine Downy oak
Variable GLM MARS ANN GLM MARS ANN
AI 0.650 0.645 0.733 0.848 0.830 1.000
Slope 0.000 0.086 0.006 0.038 0.087 0.023
TPI 0.145 0.162 0.000 0.099 0.103 0.000
Southness 0.180 0.393 0.283 0.210 0.269 0.220
ATC 0.000 0.017 0.000 0.078 0.042 0.000
AWC 0.000 0.000 0.000 0.000 0.000 0.000
DR 0.000 0.000 0.000 0.251 0.138 0.000
ERO 0.000 0.000 0.000 0.000 0.000 0.000
OC 0.000 0.000 0.000 0.044 0.000 0.000
VS 0.000 0.000 0.000 0.160 0.000 0.000
Avalanches 0.000 0.000 0.000 0.000 0.000 0.000
Wildfires 0.010 0.000 0.000 0.000 0.000 0.000
Erosion 0.000 0.061 0.319 0.011 0.028 0.109
Depop 0.069 0.029 0.000 0.027 0.041 0.000
Roads 0.000 0.000 0.459 0.016 0.029 0.159
Buildings 0.000 0.017 0.367 0.027 0.155 0.201
VCF 0.000 0.028 0.018 0.000 0.024 0.023
NDVI 0.134 0.093 0.000 0.006 0.074 0.000
  1. Codes for explanatory variables are given in Table 1