Table 3 Comparison of R2 values for pollutant CO 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

0.895

0.902

0.893

0.9

Changping

0.847

0.845

0.847

0.849

Dongsi

0.879

0.883

0.88

0.881

Guanyuan

0.881

0.904

0.904

0.9

Huairou

0.907

0.907

0.906

0.908

Nongzhanguan

0.923

0.923

0.921

0.926

Shunyi

0.907

0.904

0.9

0.905

Tiantan

0.908

0.908

0.901

0.913

Wanliu

0.897

0.904

0.901

0.904

Wanshouxigong

0.93

0.934

0.93

0.938

Back to article page