Enhancing multi-step air quality prediction with deep learning using residual neural network and adaptive decomposition-based multi-objective optimization

Abstract

Accurate air quality prediction is crucial for health and ecology. However, existing studies often overlook the impact of data quality, feature extraction, external factors, and prediction uncertainty after data decomposition. To address this, we propose an enhanced multi-step air quality prediction approach using deep learning, incorporating residual neural networks and adaptive decomposition-based multi-objective optimization. This framework integrates meteorological factors and air pollutants, extracting trend and periodic features while ensuring smooth decomposition with minimal residuals. Training and prediction utilize a deep learning model based on residual networks, optimized with an improved arithmetic algorithm. Uncertainty prediction is implemented by modeling and sampling the prediction error. Experimental validation on data from Beijing, Shanghai, and Guangzhou demonstrates significant advantages over other models, confirming the reliability and accuracy of our framework in handling time series data and forecasting future trends. Additionally, uncertainty forecasting enhances forecast reliability and accuracy by describing the range of possible outcomes.