Smart City Air Pollution Monitoring and Prediction: A Case Study of Skopje

Abstract

One of the key aspects of smart cities is the enhancement of awareness of the key stakeholders as well as the general population regarding air pollution. Citizens often remain unaware of the pollution in their immediate surrounding which usually has strong correlation with the local environment and micro-climate. This paper presents an Internet of Things based system for real-time monitoring and prediction of air pollution. First, a general layered management model for an Internet of Things based holistic framework is given by defining its integral levels and their main tasks as observed in state-of-the-art solutions. The value of data is increased by developing a suitable data processing subsystem. Using deep learning techniques, it provides predictions for future pollution levels as well as times to reaching alarming thresholds. The sub-system is built and tested on data for the city of Skopje. Although the data resolution used in the experiments is low, the results are very promising. The integration of this module with an Internet of Things infrastructure for sensing the air pollution will significantly improve overall performance due to the intrinsic nature of the techniques employed.