Machine learning for air quality prediction using meteorological and traffic related features

Abstract

The presence of pollutants in the air has a direct impact on our health and causes detrimental changes to our environment. Air quality monitoring is therefore of paramount importance. The high cost of the acquisition and maintenance of accurate air quality stations implies that only a small number of these stations can be deployed in a country. To improve the spatial resolution of the air monitoring process, an interesting idea is to develop data-driven models to predict air quality based on readily available data. In this paper, we investigate the correlations between air pollutants concentrations and meteorological and road traffic data. Using machine learning, regression models are developed to predict pollutants concentration. Both linear and non-linear models are investigated in this paper. It is shown that non-linear models, namely Random Forest (RF) and Support Vector Regression (SVR), better describe the impact of traffic flows and meteorology on the concentrations of pollutants in the atmosphere. It is also shown that more accurate prediction models can be obtained when including some pollutants’ concentration as predictors. This may be used to infer the concentrations of some pollutants using those of other pollutants, thereby reducing the number of air pollution sensors.

Air Pollution: A Review of Its Impacts on Health and Ecosystems, and Analytical Techniques for Their Measurement and Modeling

“…In line with this, blockchain technology can provide a tamper-proof record of air quality data, ensuring data reliability in pollution monitoring systems (Gryech et al, 2020). Equipping gas sensors on mobile devices or vehicles is a mobile solution that enables active and cooperative detection of air pollution.…”

An improved method for recognizing pediatric epileptic seizures based on advanced learning and moving window technique

“…Apart from that tree-based classifier has been considered (decision tree) [19], along with newer method of ensemble learning [23]. Random forest [15,18] has been chosen as it works well with imbalanced data, and in seizure detection there is always a chance that the signal being analyzed may have class imbalance. The proposed method has been designed such that it will be first trained with a certain amount of data.…”

Machine Learning for Predicting the Risk for Childhood Asthma Using Prenatal, Perinatal, Postnatal and Environmental Factors

“…Support vector machine is a machine learning technique that relies on kernel functions to provide the best fit to observed data [15]. It aims to map a high-dimensional feature space to the considered output.…”