Table 3 Evaluation results of different models for AQI prediction in Xi'an City.
From: Air quality prediction model based on mRMR–RF feature selection and ISSA–LSTM
Model | Evaluation index | |||
|---|---|---|---|---|
MAPE (\(\mathrm{\upmu g}/{\mathrm{m}}^{3}\)) | MAE (\(\mathrm{\upmu g}/{\mathrm{m}}^{3}\)) | RMSE (\(\mathrm{\upmu g}/{\mathrm{m}}^{3}\)) | R2 (%) | |
SVR | 0.221 | 9.501 | 11.23 | 0.891 |
BP | 0.109 | 6.891 | 9.815 | 0.917 |
CNN | 0.064 | 4.113 | 5.806 | 0.971 |
LSTM | 0.103 | 6.410 | 8.963 | 0.931 |
SSA-LSTM | 0.035 | 2.414 | 3.144 | 0.945 |
ISSA–LSTM | 0.013 | 2.137 | 2.368 | 0.996 |
