Particulate matter (PM₁, PM_2.5 and PM₁₀) concentration forecasting through an artificial neural network in port city environment

The city of Tampico has one of the main ports on the east coast of Mexico, on the Gulf of Mexico. The city is considered part of five human settlement nuclei metropolitan areas. It has a significant industrial, port, petrochemical, commercial, tourist, and residential zone, causing a significant positive economic impact in the region. These activities directly impact air quality with the presence of anthropogenic emission sources. Air pollution is one of the most investigated causes of health risk; early warnings protect the population and create public policies to avoid exposure and identify control measures to reduce atmospheric emissions. Therefore, the objective of this study is to analyze the effect of maritime traffic on air quality through a multiple regression effect using an artificial neural network (ANN), allowing to forecast the daily concentration of particulate matter (PM₁₀, PM_2.5, and PM₁) and ozone (O₃). The data set used the hourly average of the pollutant concentration levels and meteorological factors from May 1^st, 2021, to January 31^st, 2022, and the entry and exit of ships to the port area in the same range of dates. The regression model based on the ANN reaches an acceptable precision with a root- mean-squared error (RMSE) of 5.9554 and a mean absolute error (MAE) of 4.5732.