Skip to main content

Official Journal of the Japan Wood Research Society

Table 4 Prediction performance for carbonization characteristics of random forest regression models and comparison with other regression models

From: Feature importance measures from random forest regressor using near-infrared spectra for predicting carbonization characteristics of kraft lignin-derived hydrochar

Output variable

RF

DT

MLP

PLS [12]

R2

RMSE

R2

RMSE

R2

RMSE

R2

RMSE

C (wt%)

0.989

0.254

0.983

0.229

0.969

0.357

0.976

0.246

O/C

0.993

0.003

0.963

0.005

0.946

0.007

0.964

0.006

H/C

0.985

0.008

0.984

0.006

0.908

0.022

0.984

0.004

  1. RF, random forest; DT, decision tree for regression, MLP, multilayer perceptron; R2, coefficient of determination; RMSE, root mean square error