Conditional Generative Adversarial Networks to Model Urban Outdoor Air Pollution

TL;DR

This paper introduces a conditional GAN approach to generate synthetic outdoor air pollution data, aiding urban planning by overcoming data scarcity and improving pollution modeling accuracy.

Contribution

It presents a novel conditional generative adversarial network model for producing realistic nitrogen dioxide time series to enhance pollution forecasting with limited data.

Findings

Generated data is accurate and diverse.

Requires less computational time.

Helps improve pollution modeling accuracy.

Abstract

This is a relevant problem because the design of most cities prioritizes the use of motorized vehicles, which has degraded air quality in recent years, having a negative effect on urban health. Modeling, predicting, and forecasting ambient air pollution is an important way to deal with this issue because it would be helpful for decision-makers and urban city planners to understand the phenomena and to take solutions. In general, data-driven methods for modeling, predicting, and forecasting outdoor pollution requires an important amount of data, which may limit their accuracy. In order to deal with such a lack of data, we propose to train models able to generate synthetic nitrogen dioxide daily time series according to a given classification that will allow an unlimited generation of realistic data. The main experimental results indicate that the proposed approach is able to generate accurate and diverse pollution daily time series, while requiring reduced computational time.