Comparison of multiple machine learning algorithms for urban air quality forecasting

Abstract

Environmental air pollution has become one of the major threats to human lives nowadays in developed and developing countries. Due to its importance, there exist various air pollution forecasting models, however, machine learning models proved one of the most efficient methods for prediction. In this paper, we assessed the ability of machine learning techniques to forecast NO₂, SO₂, and PM₁₀ in Amman, Jordan. We compared multiple machine learning methods like artificial neural networks, support vector regression, decision tree regression, and extreme gradient boosting. We also investigated the effect of the pollution station and the meteorological station distance on the prediction result as well as explored the most relevant seasonal variables and the most important minimal set of features required for prediction to improve the prediction time. The experiments showed promising results for predicting air pollution in Amman with artificial neural network outperforming the other algorithms and scoring RMSE of 0.949 ppb, 0.451 ppb, and 5.570 µg/m³ for NO₂, SO₂, and PM₁₀ respectively. Our results indicated that when the meteorological variables were obtained from the same pollution station the results were better. We were also able to reduce the time by reducing the set of variables required for prediction from 11 down to 3 and achieved major time improvement by about 80% for NO₂, 92% for SO₂, and 90% for PM₁₀. The most important variables required for predicting NO₂ were the previous day values of NO₂, humidity and wind direction. While for SO₂ they were the previous day values of SO₂, temperature, and wind direction values of the previous day. Finally, for PM10 they were the previous day values of PM₁₀, humidity, and day of the year.