AQsensor: data-driven modeling of urban air quality and traffic emissions using smart IoT sensors

NAISS 2023/7-29



Principal Investigator:

Xiaoliang Ma


Kungliga Tekniska högskolan

Start Date:


End Date:


Primary Classification:

20105: Transport Systems and Logistics

Secondary Classification:

10299: Other Computer and Information Science



Many people living in cities are exposed to higher levels of pollutants than the limit values according to EU and Swedish legislation. Road traffic emissions are the main cause of air pollution (AP) in urban environments. Traffic pollutants are a definite health concern: studies show that critical pollutants from traffic can lead to a large number of premature deaths, and traffic generated greenhouse chemicals are also directly related to global climate changes. Monitoring air quality and environmental conditions is an important activity. Smart IoT sensors are one of the promising technologies today. They have recently been introduced for monitoring traffic emissions on Swedish roads after an initial test evaluation. Compared to the traditional precision equipment, these smart sensors have the advantages of low cost and being easy to install and maintain. In addition, these sensors make it feasible to collect AP data for a large spatial coverage area. The main idea of this project is to test cloud computing for running the IoT sensors as well as deploying a prediction model based on deep-learning trained by Berzelius HPC machine.