Table 7 Comparison of R2 values for pollutant PM10 across locations.

From: Deep learning framework for hourly air pollutants forecasting using encoding cyclical features across multiple monitoring sites in Beijing

 

DNN-Unencoded

CNN-Unencoded

DNN-Encoded

CNN-Encoded

Aotizhongxin

0.927

0.933

0.932

0.933

Changping

0.907

0.912

0.911

0.912

Dongsi

0.937

0.94

0.938

0.939

Guanyuan

0.93

0.933

0.933

0.933

Huairou

0.912

0.912

0.916

0.911

Nongzhanguan

0.932

0.933

0.933

0.933

Shunyi

0.935

0.934

0.936

0.937

Tiantan

0.926

0.929

0.929

0.929

Wanliu

0.925

0.929

0.928

0.929

Wanshouxigong

0.934

0.932

0.935

0.935