Air quality and urban sustainable development: the application of machine learning tools

Abstract

Air quality has an effect on a population’s quality of life. As a dimension of sustainable urban development, governments have been concerned about this indicator. This is reflected in the references consulted that have demonstrated progress in forecasting pollution events to issue early warnings using conventional tools which, as a result of the new era of big data, are becoming obsolete. There are a limited number of studies with applications of machine learning tools to characterize and forecast behavior of the environmental, social and economic dimensions of sustainable development as they pertain to air quality. This article presents an analysis of studies that developed machine learning models to forecast sustainable development and air quality. Additionally, this paper sets out to present research that studied the relationship between air quality and urban sustainable development to identify the reliability and possible applications in different urban contexts of these machine learning tools. To that end, a systematic review was carried out, revealing that machine learning tools have been primarily used for clustering and classifying variables and indicators according to the problem analyzed, while tools such as artificial neural networks and support vector machines are the most widely used to predict different types of events. The nonlinear nature and synergy of the dimensions of sustainable development are of great interest for the application of machine learning tools.