Longer Time Span Air Pollution Prediction: The Attention and Autoencoder Hybrid Learning Model

Table 2

Experiment on the dataset of Shanghai with time span of 48, node size of 32, and data segmentation of [24, 72].

Model	MAE	MAPE	COR
LSTM	11.36	73.02	0.28
GRU	11.38	69.20	0.30
SEQ2SEQ	12.69	76.01	0.26
Attention	11.21	70.45	0.35
A&A learning	10.93	61.72	0.37