Table 3 Variable importance for different habitat suitability models for European Turtle Doves.

From: Species distribution models of European Turtle Doves in Germany are more reliable with presence only rather than presence absence data

Variable

GBM PA data

GBM PO data

GLM PA data

GLM PO data

RF PA data

RF PO data

Wet areas

<0.01

<0.01

0.05

0.01

<0.01

0.01

Permanent cultures

0.01

<0.01

0.02

0.01

0.01

<0.01

Forest

0.20

0.04

0.16

0.06

0.11

0.03

Pasture

0.01

0.02

0.14

0.01

0.02

0.05

Herbs and shrubs

<0.01

0.03

0.02

0.05

0.01

0.01

No/little vegetation

<0.01

<0.01

0.14

<0.01

0.01

<0.01

Urban areas

0.01

0.03

0.01

0.06

0.02

0.03

Bio 2

0.05

0.12

0.01

0.02

0.04

0.07

Bio 6

0.04

0.01

0.39

0.84

0.04

0.04

Bio 7

0.01

0.02

0.10

0.50

0.01

0.04

Bio 8

0.01

0.05

0.07

0.13

0.01

0.03

Bio 9

0.02

0.02

0.04

0.03

0.03

0.04

Bio 11

0.01

0.07

0.13

0.30

0.02

0.05

Bio 15

0.01

0.03

0.01

0.11

0.01

0.06

Bio 18

0.25

0.34

0.20

0.07

0.07

0.14

  1. The highest variable importance value for each model is highlighted with bold and underlined numbers.