ACBiGRU-DAO: Attention Convolutional Bidirectional Gated Recurrent Unit-based Dynamic Arithmetic Optimization for Air...

Area of Science:

• Environmental Science
• Computer Science
• Data Science

Background:

• Air pollution is a significant environmental and health concern, especially in developing nations.
• Accurate air quality assessment is crucial for urban and industrial monitoring.
• Existing prediction models require enhancement for improved accuracy.

Purpose of the Study:

• To propose a novel air quality prediction model, ACBiGRU-DAO.
• To enhance prediction accuracy using Attention Convolutional Bidirectional Gated Recurrent Unit (ACBiGRU) and Dynamic Arithmetic Optimization (DAO).
• To classify air quality into six severity stages.

Main Methods:

• Utilized Indian air quality data including AQI, PM2.5, PM10, CO, NO2, SO2, and O3.
• Preprocessed data through missing value imputation and data transformation.
• Developed and optimized the ACBiGRU-DAO model for prediction and classification.

Main Results:

• The ACBiGRU-DAO approach achieved an accuracy of 95.34%.
• Demonstrated superior performance compared to other evaluated methods.
• Successfully predicted air quality and classified it into six AQI stages.

Conclusions:

• The proposed ACBiGRU-DAO model offers a highly accurate solution for air quality prediction.
• This approach can aid in monitoring and mitigating air pollution impacts.
• Effective air quality prediction is vital for public health and environmental protection.