Skip to main content
Environmental Sciences Europe

Table 4 Comparison of accuracy among OK, MLR, RF, and Cubist predictive models

From: Improving soil organic carbon mapping in farmlands using machine learning models and complex cropping system information

 

OK

MLR

RF

Cubist

RMSE (g/kg)

0.497

0.499

0.481

0.479

R2

0.211

0.207

0.263

0.292

LCCC

0.380

0.342

0.431

0.482

  1. OK ordinary kriging, MLR multiple linear regression, RF random forest, RMSE root mean square error, R2 coefficient of determination, LCCC Lin’s concordance correlation coefficient
Back to article page