Table 4 Comparative performance of machine learning algorithms for predicting nepetalactone concentration (n = 62 samples; 10-fold cross-validation).

From: Predicting nepetalactone accumulation in Nepeta persica using machine learning algorithms and geospatial analysis

Algorithm

RMSE

MAE

R2

CCC

CI95% (RMSE)

RF vs. ΔRMSE (%)

RF-SVM-GBM Hybrid

0.015

0.012

0.82

0.88

0.012–0.018

−21.1% (Improvement)

RF

0.019

0.015

0.74

0.81

0.016–0.022

Reference

SVM

0.021

0.017

0.68

0.76

0.018–0.024

+ 10.5%

GBM

0.028

0.023

0.54

0.63

0.024–0.032

+ 47.4%

Back to article page