ACP-2023-38 paper submission support: code and data for 3-days prediction of Air Quality using Machine Learning algorithms

<p>As air pollution is regarded as the single largest environmental health risk in Europe it is important that communication to the public is up-to-date, accurate and provides means to avoid exposure to high air pollution levels. Air quality forecasts can be based on deterministic dispersion modelling, but to be accurate this requires detailed information on future emissions, meteorological conditions and process oriented dispersion modelling. In our study, different machine learning (ML) algorithms including Random forest (RF), Extreme Gradient Boosting (XGB) and Long-Short Term Memory (LSTM) are applied to improve 1-, 2- and 3-day deterministic forecasts of PM<sub>10</sub>, NO<sub>x</sub>, and O<sub>3</sub> at different sites in Greater Stockholm, Sweden.</p> <p>The published software files contain the python codes for machine learning models applied in the paper and processed data being used for training and testing the models.</p&gt