Applying machine learning methods in managing urban concentrations oftraffic-related particulate matter (PM10and PM2.5)

Özet

This study presents a new method for evaluating the effectiveness of roadside PM10and PM2.5reduction sce-narios using Machine Learning (ML) based models. The ML methods include Artificial Neural Networks (ANN),Boosted Regression Trees (BRT) and Support Vector Machines (SVM). Traffic, meteorological and pollutant datacollected at nineteen Air Quality Monitoring (AQM) sites in London for a period between 2007 and 2012 wasused. The ML models performed very well in predicting the concentrations of PM10and PM2.5with around 95%of their predictions falling within the factor of two of the observed concentrations at the roadsides. The pre-diction errors observed were very small as indicated by the average normalised mean gross errors of 0.2. Also,the predictions of the models correlated well with the observed concentrations as shown by the average values ofR (0.8) and index of agreement (0.74). Additionally, when some PM10and PM2.5reduction scenarios weremodelled, the ML models predicted various degree of reductions in the roadside concentrations. In conclusion,well trained ANN and BRT models can be successfully applied in predictions of roadside PM10and PM2.5con-centrations. Moreover, they can be applied in measuring the effectiveness of roadside particle reduction sce-narios.