Table 3 Modeling results of various methods for PM10, PM2.5, and nox without considering auto-correlation of the pollutants (RMSE, MAE in µg/m3; R2 is unitless).

From: Unravelling the importance of spatial and temporal resolutions in modeling urban air pollution using a machine learning approach

 

PM10 (Daily)

PM2.5 (Daily)

NOx (Daily)

RMSE

MAE

R2

RMSE

MAE

R2

RMSE

MAE

R2

MLP

92.564

54.165

0.02

61.096

25.807

0.09

7.905

5.770

0.58

RF

86.134

52.770

0.15

53.284

21.342

0.31

8.482

5.877

0.50