Table 1 Average MAE (in eV) and R of the twelve used ML regressors, including LR, for Eads and Eb target properties, obtained through 30-fold cross validation

From: Accurate Prediction of Adsorption and Diffusion Energies of Single Metal Atoms Supported on MXenes from Machine Learning

ML Model

Eads

Eb

Eb < 0.4 eV

 

MAE

R

MAE

R

MAE

R

DTR

0.28

0.97

0.10

0.26

0.07

0.30

RFR

0.21

0.99

0.07

0.72

0.05

0.73

ADR

0.45

0.95

0.09

0.62

0.07

0.65

ENR

1.53

0.03

0.12

0.03

0.10

0.05

GBR

0.22

0.99

0.07

0.72

0.05

0.73

KNR

0.74

0.86

0.09

0.56

0.08

0.51

KRR

0.55

0.93

0.08

0.71

0.06

0.69

LASSO

1.53

0.03

0.12

0.03

0.09

0.05

PLS

0.75

0.87

0.09

0.64

0.07

0.65

SVR

038

0.96

0.08

0.70

0.06

0.69

RR

0.55

0.93

0.08

0.70

0.07

0.65

LR

0.55

0.93

0.08

0.70

0.06

0.69

  1. In the case of Eb, an analysis is also carried out considering only cases with Eb < 0.4 eV
Back to article page