Skip to main content

Table 2 Variables used as predictors in random forest models

From: Classifying forest inventory data into species-based forest community types at broad extents: exploring tradeoffs among supervised and unsupervised approaches

Category

Variable

Description

Climate

Bio2

Mean diurnal range (Mean of monthly (max temp - min temp))

 

Bio6

Minimum temperature of coldest month

 

Bio8

Mean temperature of wettest quarter

 

Bio15

Precipitation seasonality (coefficient of variation)

 

Bio16

Precipitation of wettest quarter

 

Bio18

Precipitation of warmest quarter

Landscape

Landsc. cond.

Landscape condition

 

Prop. forest

Forest area density

Landscape soil

DI

Soil drainage index

 

PI

Soil productivity index

Local soil

Bedrock depth

Depth to bedrock (cm

 

Pct. clay

Percent clay (< 0.002 mm size)

 

Pct. org. Matt.

Organic matter content (% by weight)

 

Pct. sand

Percent sand (0.05–2.0 mm size)

 

Pct. silt

Percent silt (0.02–0.05 mm size)

 

pH

Soil pH

 

Sieve 10

Percent soil passing sieve No. 10 (coarse)

Topographic

East

Easting: sin(aspect)

 

Elevation

Elevation

 

North

Northing: cos(aspect)

 

Slope

Slope

 

TPI

Topographic Position Index

  1. See Additional file 1 for a list of all variables considered as well as data sources for all