Principal Investigator: Prof. Mohamed-Slim Alouini
Poster Presenter: Bodhibrata Mukhopadhyay
Lab: CTL
It is necessary to critically assess the spatial and temporal variation of air pollutants (particle matters, nitrogen dioxide (NO2), ozone (O3), sulfur dioxide (SO2), and black carbon (BC)) in order to identify and categorize the emergence and disappearance of Jeddah's traffic-related air pollution hotspots. This proposal aims to develop sets of mobile environmental monitoring units (EMU(s)) which will be equipped with the above-mentioned pollutant sensors to record and store time-location stamped in-vehicle and on-road pollutant levels (in real-time). The recorded data will be used to produce high-resolution concentration maps of anthropogenic air pollutants in Jeddah. Traffic congestion data will also be collected corresponding to the path of the mobile vehicle to establish a correlation between traffic congestion and the elevation in pollutant levels. A machine learning model will be trained using the data mentioned above, and it will be able to predict accurately/coarsely the roadside pollutant levels by observing the traffic congestion pattern and other meteorological data.