The air quality index trend forecasting based on improved error correction model and data preprocessing for 17 port...

Area of Science:

• Environmental Science
• Data Science
• Climate Science

Background:

• Air pollution poses significant risks to human health and ecosystems, necessitating effective prediction and control strategies.
• Accurate air quality forecasting is crucial for implementing timely prevention and mitigation measures in China.
• Existing error correction models lack data preprocessing, limiting their predictive capabilities.

Purpose of the Study:

• To develop and evaluate an improved hybrid model for air pollution prediction and early warning.
• To enhance the accuracy of air quality forecasting by integrating advanced data preprocessing techniques.
• To provide a more reliable tool for environmental management and public health protection.

Main Methods:

• Development of a hybrid model: Complementary Set Empirical Mode Decomposition-Statistical Learning Model-Error Correction Model (CEEMD-SLM-ECM).
• Integration of CEEMD for data preprocessing to refine input for the prediction model.
• Utilizing Statistical Learning Models (SLM) and Error Correction Models (ECM) within the hybrid framework.
• Testing the model's efficacy using Air Quality Index (AQI) data from 17 port cities along the 21st Century Maritime Silk Road Economic Belt.

Main Results:

• The CEEMD-SLM-ECM model demonstrated substantially higher prediction accuracy than traditional error correction models.
• The CEEMD data preprocessing significantly improved the performance of the air quality forecasting model.
• Empirical testing confirmed the model's superior forecasting ability for air quality.

Conclusions:

• The CEEMD-SLM-ECM model represents a significant advancement in air pollution prediction technology.
• This model offers a highly effective solution for accurate air quality early warning systems.
• The findings support the adoption of advanced hybrid models for environmental monitoring and management.