Table 3.

Performance and validation of the final models

Area	Evaluation	Pearson r		R2		RMSE
		Log (μg/m3)	μg/m3	Log (μg/m3)	μg/m3	μg/m3
Rural	Model	0.79	0.78	0.63	0.61	5.86
	Internal cross-validation	0.80	0.78	0.63	0.61	5.86
	External validation	0.77	0.82	0.58	0.68	3.21
Urban	Model	0.74	0.67	0.54	0.45	6.96
	Internal cross-validation	0.74	0.67	0.54	0.45	6.96
	External validation	0.82	0.83	0.67	0.69	3.35

Internal cross-validation was based on ten-fold cross-validation, and external validation used the study dataset. We compared measured and predicted values on the log scale, on which the models were developed, and as concentrations by exponentiating the predictions. The root mean square errors (RMSE) are derived from the comparison of NO₂ concentrations only