Comparative Analysis Study for Air Quality Prediction in Smart Cities Using Regression Techniques
Shorouq Al-Eidi, Fathi Amsaad, Omar Darwish, Yahya Tashtoush, Ali Alqahtani, Niveshitha Niveshitha
Abstract
Air pollution has detrimental impacts on our physical health and the quality of our living environment, particularly in smart cities. Monitoring and predicting air pollution is crucial to empower individuals to make informed decisions that protect their health. Predicting air quality accurately plays an important effective action plan to mitigate air pollution and create healthier and more sustainable environments. This can be achieved by relying on the Air Quality Index, one of the most reliable indicators for air pollutant concentration levels in certain cities. This study provides a comparative analysis study for air quality prediction using three regression techniques: Random Forest regression, Linear regression, and Decision Tree regression, employing the AQI values. This comparison aims to identify the most efficient model based on various evaluation criteria, such as Mean Absolute Error and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> measures. Additionally, it considers both error rate minimization and processing time efficiency of each regression model evaluated within two distinct frameworks as other important measures to determine the best-fitted model. The findings of this study showcase the superiority of the Decision Tree regression technique over the other models, demonstrating its exceptional accuracy with a high <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score and low error rate. Moreover, integrating cloud computing technology has yielded significant improvements in model execution time, substantially enhancing the overall efficiency of the prediction process. By leveraging distributed computing resources, real-time air quality forecasting becomes feasible, enabling timely decision-making and proactive measures to address air pollution episodes.