Modeling air quality PM2.5 forecasting using deep sparse attention-based transformer networks

Abstract Air quality forecasting is of great importance in environmental protection, government decision-making, people's daily health, etc. Existing research methods have failed to effectively modeling long-term and complex relationships in time series PM2.5 data and exhibited low precision in long-term prediction. To address this issue, in this paper a new lightweight deep learning model using sparse attention-based Transformer networks (STN) consisting of encoder and decoder layers, in which a multi-head sparse attention mechanism is adopted to reduce the time complexity, is proposed to learn long-term dependencies and complex relationships from time series PM2.5 data for modeling air quality forecasting. Extensive experiments on two real-world datasets in China, i.e ., Beijing PM2.5 dataset and Taizhou PM2.5 dataset, show that our proposed method not only has relatively small time complexity, but also outperforms state-of-the-art methods, demonstrating the effectiveness of the proposed STN method on both short-term and long-term air quality prediction tasks. In particular, on singe-step PM2.5 forecasting tasks our proposed method achieves R 2 of 0.937 and reduces RMSE to 19.04 µg/m 3 and MAE to 11.13 µg/m 3 on Beijing PM2.5 dataset. Also, our proposed method obtains R 2 of 0.924 and reduces RMSE to 5.79 µg/m 3 and MAE to 3.76 µg/m 3 on Taizhou PM2.5 dataset. For long-term time step prediction, our proposed method still performs best among all used methods on multi-step PM2.5 forecasting results for the next 6, 12, 24, and 48 h on two real-world datasets.