Table 1 Assessment of cross-validated predictions from the daily mean PM2.5 model by year.

From: Prediction of daily mean and one-hour maximum PM2.5 concentrations and applications in Central Mexico using satellite-based machine-learning models

Year

Number of stations

Observations

R2

SD

RMSE

MAD

MAE

2004

8

2751

0.76

12.02

5.86

9.12

3.91

2005

8

2701

0.81

14.80

6.43

11.28

4.38

2006

8

2685

0.68

13.19

7.48

9.55

5.04

2007

9

2855

0.71

10.87

5.85

8.16

4.28

2008

9

3040

0.64

12.16

7.29

9.27

4.61

2009

9

2670

0.75

10.14

5.09

7.71

3.61

2010

9

2844

0.79

11.70

5.41

8.83

3.64

2011

12

3019

0.77

11.53

5.56

8.90

3.88

2012

13

4025

0.76

10.10

4.95

7.63

3.59

2013

13

4362

0.80

11.75

5.25

8.85

3.87

2014

14

4203

0.73

9.87

5.10

7.50

3.86

2015

19

5194

0.77

10.78

5.11

7.90

3.76

2016

17

5307

0.83

11.44

4.73

8.56

3.37

2017

17

4901

0.80

10.79

4.78

8.42

3.15

2018

17

4633

0.84

9.91

3.94

7.19

2.83

2019

20

5175

0.86

11.50

4.26

7.98

2.85

  1. SD Standard deviation, RMSE Root mean squared error, MAD Mean absolute deviation, MAE Mean Absolute Error.