Hour-by-Hour Prediction Model of Air Pollutant Concentration Based on EIDW-Informer—A Case Study of Taiyuan

Prediction of air pollutant concentrations is currently one the most important methods for prevention and control urban pollution in countries, accurate timely prediction great significance control. Using Taiyuan, China, as a case study, this study examines how to predict hourly over longer periods time while ensuring their accuracy. In paper, an concentration method based on improved inverse distance interpolation Informer model (EIDW-Informer), hour-by-hour PM2.5, NO2, O3 China carried out. historical data from seven environmental monitoring stations Taiyuan City were used build multidimensional vectors calculate similarity between sample points. Then, missing values dataset interpolated according weights, long series was performed by Informer. The experimental results show that EIDW-Informer has advantages compared LSTM, CNN-LSTM, Attention-LSTM models, which improves 20%, 27%, 43% 1 h, 8 72 h scales, respectively.