Developing a Real-Time Atmospheric Pollutant Monitoring Method with High Accuracy and Wide Measurement Range

Air quality is important for the well-being of urban populations. However, the degradation of this quality is a major problem worldwide, caused by rapid urbanization, population growth, increased industrial activities and road traffic. This leads to emissions of fine particles (PM2.5 and PM10), toxic gases as nitrogen dioxide (NO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>) and ozone (O<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</inf>), as well as other pollutants that seriously affect public health, the environment and the climate. Addressing these challenges, the development of efficient air pollution monitoring systems has become essential. This paper focuses on the deployment of a method to monitor air pollutants in real time, one based on low-cost sensors and mathematical methods to correct measurement errors, in order to support the accuracy and amplitude of measurements to have a reliable assessment of air quality. The former allows easy access and a large amount of data, while the latter, such as machine learning, are adopted to normalize the data continuously and in real time to compensate for the reading system. To this extent, the procedures explained above guarantee reliable and easy monitoring of pollution levels, providing important information for public health and environmental management.