PM2.5 concentration prediction using a whale optimization algorithm based hybrid deep learning model in Beijing, China
Wei Qing, Huijin Zhang, Ju Yang, Bin Niu, Zhijie Xu
Abstract
PM 2.5 is a significant global atmospheric pollutant impacting visibility, climate, and public health. Accurate prediction of PM 2.5 concentrations is critical for assessing air pollution risks and providing early warnings for effective management. This study proposes a novel hybrid machine learning model that combines the whale optimization algorithm (WOA) with a convolutional neural network (CNN), long short-term memory (LSTM), and an attention mechanism (AM) to predict daily PM 2.5 concentrations. Tested with meteorological and air pollution daily data from 2014 to 2018, the WOA-CNN-LSTM-AM model demonstrates substantial improvements. It achieves MAE, RMSE, MBE , and R 2 values of 14.29, 21.96, −0.23, and 0.93, respectively, showing a reduction in prediction errors by 39% compared to CNN and 34% compared to LSTM models. In the medium-term forecast, the accuracy of the hybrid model is 30%–54% over WOA-CNN-LSTM and 26%–39% over CNN-LSTM-AM. The R 2 value decreases by 2.5% from the 1-day to 5-day forecast, maintaining high accuracy. SHAP analysis reveals that NO 2 and CO are the primary drivers for PM 2.5 predictions. This study provides a reliable tool for short and medium-term PM 2.5 prediction and air pollution control .