Time series prediction of the chemical components of PM_2.5 based on a deep learning model

Modeling-based prediction methods enable rapid, reagent-free air pollution detection based on inexpensive multi-source data than traditional chemical reaction-based detection methods in order to quickly understand the air pollution situation. In this study, a convolutional neural network (CNN) and long and short-term memory (LSTM) neural networks are integrated to create a CNN-LSTM time series prediction model to predict the concentration of PM_2.5 and its chemical components (i.e., heavy metals, carbon component, and water-soluble ions) using meteorological data and air pollutants (PM_2.5, SO₂, NO₂, CO, and O₃). In the integrated CNN-LSTM model, the CNN uses convolutional and pooling layers to extract features from the data, whereas the powerful nonlinear mapping and learning capabilities of LSTM enable the time series prediction of air pollution. The experimental results showed that the CNN-LSTM exhibited good generalization ability in the prediction of As, Cd, Cr, Cu, Ni, and Zn, with a mean R² above 0.9. Mean R² predicted for PM_2.5, Pb, Ti, EC, OC, SO₄^2-, and NO₃^- ranged from 0.85 to 0.9. Shapley value showed that PM_2.5, NO₂, SO₂, and CO had a greater influence on the predicted heavy metal results of the model. Regarding water-soluble ions, the predicted results were dominantly influenced by PM_2.5, CO, and humidity. The prediction of the carbon fraction was affected mainly by the PM_2.5 concentration. Additionally, several input variables for various components were eliminated without affecting the prediction accuracy of the model, with R² between 0.70 and 0.84, thereby maximizing modeling efficiency and lowering operational costs. The fully trained model prediction results showed that most predicted components of PM_2.5 were lower during January to March 2020 than those in 2018 and 2019. This study provides insight into improving the accuracy of modeling-based detection methods and promotes the development of integrated air pollution monitoring toward a more sustainable direction.