Table 1.

Assessment of cross-validated predictions from the daily mean PM_2.5 model by year.

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

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