AirMamba: A deep learning framework for long-term PM2.5 forecasting integrating multi-scale correlations and time-frequency dynamics

Abstract

Existing approaches for long-term forecasting of ${\text{PM}}_{2.5}$ typically focus either on time-domain or frequency-domain features in isolation, neglecting their complementary interactions. This limitation restricts their capacity to effectively capture long-term trends. Moreover, the absence of explicit modeling of multi-scale correlations among influencing factors under complex environmental conditions may undermine both the stability and accuracy of model predictions. To overcome these limitations, we introduce AirMamba, a novel deep learning framework designed to enhance long-term ${\text{PM}}_{2.5}$ forecasting by integrating multi-scale correlation analysis with time-frequency interactions. Specifically, a multi-scale inter-variable correlations extractor module is developed to capture the complex interdependencies among variables across diverse temporal scales. The framework leverages the Maximum Overlap Discrete Wavelet Transform (MODWT) to decompose time series data into multi-scale high-frequency and low-frequency components, thereby facilitating a comprehensive time-frequency analysis. An enhanced bidirectional Mamba structure is then employed to model both long- and short-term dependencies within the time series, informed by the identified time-frequency interactions. Extensive experiments demonstrate that the proposed method achieves superior forecasting performance compared to existing mainstream models.