A Novel Hybrid Framework for Hourly PM2.5 Concentration Forecasting Using CEEMDAN and Deep Temporal Convolutional Neural Network

no code implementations • 7 Dec 2020 • Fuxin Jiang, ChengYuan Zhang, Shaolong Sun, Jingyun Sun

For hourly PM2. 5 concentration prediction, accurately capturing the data patterns of external factors that affect PM2. 5 concentration changes, and constructing a forecasting model is one of efficient means to improve forecasting accuracy.

Time Series Time Series Analysis