An interval AQI combination prediction model based on multiple data decomposition and information aggregation...

Area of Science:

• Environmental Science
• Data Science
• Time Series Analysis

Background:

• Accurate air quality index (AQI) prediction is crucial for public health and environmental monitoring.
• Complex AQI data presents challenges for traditional prediction models.
• Existing models may lack the capability to effectively extract features from intricate time-series data.

Purpose of the Study:

• To propose a novel interval AQI combination prediction model.
• To enhance AQI prediction accuracy and generalization ability.
• To leverage data decomposition techniques for improved time-series forecasting.

Main Methods:

• Utilizing Ensemble Empirical Mode Decomposition (EEMD) for data decomposition.
• Employing Variational Mode Decomposition (VMD) for effective data decomposition.
• Integrating a Weighted Power Average (WPA) operator for aggregating prediction results.
• Validating the model with daily interval AQI data from Shenzhen.

Main Results:

• Data decomposition methods significantly improve prediction accuracy.
• The WPA operator further enhances the model's prediction capability.
• EEMD and VMD incorporation provide stronger feature extraction for complex time series.
• The proposed model demonstrates superior generalization ability and accuracy compared to other models.

Conclusions:

• The developed EEMD-VMD-WPA model offers high prediction accuracy and strong generalization.
• This approach is effective for complex time-series forecasting in air quality prediction.
• The model's applicability extends to other domains like economics and environmental studies.