Developing Machine learning models for hyperlocal traffic related particulate matter concentration mapping

摘要: Recently, estimating air pollution concentrations and contributions from various sources has become a major research focus. Our research adds to the body of knowledge by developing machine learning (ML) models to avoid intermediate modeling steps using traffic and meteorological data. The ML model's overall performance in predicting air pollution concentrations at receptors outperforms previous methods. Our best model, Convolutional Long Short-Term Memory (ConvLSTM), has a Mean Relative Error (MRE) of 38.9%, which is …