Skip to main content

Table 4 Characteristics of the random forest models for the relationship between the log-transformed (ln) HM contents and N contents in moss samples and the predictors given in the following figures

From: Correlating elements content in mosses collected in 2015 across Germany with spatially associated characteristics of sampling sites and their surroundings

Predictors model parameters

Target variable (element content in moss samples)

ln Cd

In Cu

ln Hg

In Ni

In Pb

ln Zn

N

N

400

400

400

400

400

400

400

ntree

500

500

500

500

500

500

500

mtry

3

4

3

3

3

2

3

Model quality indices

 MSE

0.1882

0.0774

0.1878

0.2239

0.2617

0.077

0.0992

 RSQ

30.70

41.62

19.83

34.50

21.99

38.71

50.18

  1. ln log-transformed values, n sample size, ntree number of regression trees in the random forest model, mtry number of variables used for each split, MSE mean squared residuals, RSQ share of explained variance