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

Abstract

Ozone is one of the pollutants with most negative efects on human health and in general on the biosphere. Many data-acquisition networks collect data about ozone values in both urban and background areas. Usually, these data are incomplete or corrupt and the imputation of the missing values is a priority in order to obtain complete datasets, solving the uncertainty and vagueness of existing problems to manage complexity. In the present paper, multiple-regression techniques and Artifcial Neural Network models are applied to approximate the absent ozone values from fve explanatory variables containing air-quality information. To compare the diferent imputation methods, real-life data from six data-acquisition stations from the region of Castilla y Leon (Spain) are gathered ´ in diferent ways and then analyzed. Te results obtained in the estimation of the missing values by applying these techniques and models are compared, analyzing the possible causes of the given response.