Deep Inferential Spatial-Temporal Network for Forecasting Air Pollution Concentrations
This addresses the need for accurate air pollution predictions to mitigate health and economic impacts, but it is incremental as it builds on existing deep learning approaches for spatio-temporal forecasting.
The paper tackles forecasting air pollution concentrations (PM2.5, PM10, O3) over 48 hours by proposing a Deep Inferential Spatial-Temporal Network that handles non-linear spatial and temporal correlations, outperforming state-of-the-art methods in terms of SMAPE and RMSE on a dataset from Beijing.
Air pollution poses a serious threat to human health as well as economic development around the world. To meet the increasing demand for accurate predictions for air pollutions, we proposed a Deep Inferential Spatial-Temporal Network to deal with the complicated non-linear spatial and temporal correlations. We forecast three air pollutants (i.e., PM2.5, PM10 and O3) of monitoring stations over the next 48 hours, using a hybrid deep learning model consists of inferential predictor (inference for regions without air pollution readings), spatial predictor (capturing spatial correlations using CNN) and temporal predictor (capturing temporal relationship using sequence-to-sequence model with simplified attention mechanism). Our proposed model considers historical air pollution records and historical meteorological data. We evaluate our model on a large-scale dataset containing air pollution records of 35 monitoring stations and grid meteorological data in Beijing, China. Our model outperforms other state-of-art methods in terms of SMAPE and RMSE.