Neural Models for Imputation of Missing Ozone Data in Air-Quality Datasets

Table 2

Percentage of missing and corrupted data for each one of the analyzed variables.

	O3	NO	NO2	CO	PM10	SO2
Missing		8.020%	8.034%	8.554%	9.131%	8.196%
Corrupted		2.047%	1.815%	2.926%	2.413%	1.801%
Total		10.067%	9.849%	11.480%	11.544%	9.997%