Short-Term Prediction of Daily O3, NO2, and SO2 Using a Novel Hybrid Model with Additive Correction

Accurate forecasts of O3, NO2, and SO2 from regulatory daily summary records support early warning and environmental management, whereas the inherent nonlinearity, non-stationarity, and multi-scale fluctuations of pollutant sequences severely hinder prediction precision. This paper develops a hybrid CEEMDAN-VMD-GRU-AC model for one-step-ahead concentration prediction of three typical air pollutants. Chronologically ordered valid daily summary records from the Los Angeles–North Main Street monitoring station from 2015 to 2025 were used for evaluation. The original pollutant sequences are first decomposed into multi-scale intrinsic mode functions via complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Variational mode decomposition (VMD) is further applied to refine high-frequency IMF1 and IMF2 to decouple irregular short-term oscillations. A gated recurrent unit (GRU) equipped with an additive correction (AC) branch is constructed to predict each decomposed component, and all subseries predictions are aggregated to obtain the final concentration forecasts. The evaluation was conducted under an offline full-series decomposition protocol, in which CEEMDAN and VMD were applied to the complete pollutant sequence before the chronological training–validation–test split; therefore, the reported metrics should not be interpreted as fully prospective rolling-origin forecasting performance. Because the extracted records were not reindexed to a complete daily calendar, the 30-step input represents 30 consecutive valid records rather than 30 uninterrupted calendar days. Compared with benchmark prediction methods, the proposed framework yields the lowest RMSE and MAE, together with the highest R2 values of 0.9646, 0.9516, and 0.9035 for O3, NO2, and SO2, respectively. The ablation results reveal pollutant-dependent effects: VMD refinement provides the largest improvement for O3, whereas the final GRU-AC configuration performs best for NO2 and SO2. These results demonstrate the feasibility of the proposed framework under the stated offline protocol, while calendar-complete rolling-origin and multi-station validation remains necessary before operational deployment.