Self-Organizing Maps Applied to the Analysis of Atmospheric Pollutants
Machine Learning, Air Pollutants, Self-Organizing Maps, Data analysis, Clustering.
Air pollution is a problem that is increasingly present in our society due to the growing development of countries. In the study of air pollutants, multivariate statistical methods are commonly used, however, machine learning has proved to be a great alternative, presenting techniques capable of dealing with highly complex problems, such as air pollution. In this work, the machine learning technique, Self-Organizing Maps (SOM), was used to explore and analyze data on atmospheric pollutants and meteorological parameters from an air quality monitoring network, with stations located in the city of Salvador - Bahia. SOM offers several resources capable of making the study of data more comprehensive, which were used for the development of an individual and mutual analysis on the stations, being also briefly compared with a principal component analysis. From the visualization of the component planes, patterns between the air quality variables could be identified, as well as the observation of the present correlations, which were more specifically described by a hierarchical analysis of similarity, allowing to raise assumptions about their influence, formations and possible sources of emission, with a better description of the results. In addition, based on the arrangement of the neurons on the map, a study regarding data clusters could be carried out, enabling a balance on the samples and formation of clusters, characterizing in this way information related to the concentrations of pollutants, with their specificities and how they can be related to each monitoring station according to the division and arrangement of neurons.