AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting

TL;DR

AirDDE introduces a novel neural delay differential equation framework for air quality forecasting, effectively modeling delays in pollutant dynamics with physical guidance, leading to improved prediction accuracy.

Contribution

The paper presents the first neural delay differential equation model for air quality forecasting, integrating delay modeling with physical diffusion-advection principles.

Findings

Achieves state-of-the-art forecasting performance with 8.79% MAE reduction.

Introduces a memory-augmented attention module for delay effect capture.

Develops a physics-guided delay evolving function based on diffusion-advection equations.

Abstract

Accurate air quality forecasting is essential for public health and environmental sustainability, but remains challenging due to the complex pollutant dynamics. Existing deep learning methods often model pollutant dynamics as an instantaneous process, overlooking the intrinsic delays in pollutant propagation. Thus, we propose AirDDE, the first neural delay differential equation framework in this task that integrates delay modeling into a continuous-time pollutant evolution under physical guidance. Specifically, two novel components are introduced: (1) a memory-augmented attention module that retrieves globally and locally historical features, which can adaptively capture delay effects modulated by multifactor data; and (2) a physics-guided delay evolving function, grounded in the diffusion-advection equation, that models diffusion, delayed advection, and source/sink terms, which can capture delay-aware pollutant accumulation patterns with physical plausibility. Extensive experiments on three real-world datasets demonstrate that AirDDE achieves the state-of-the-art forecasting performance with an average MAE reduction of 8.79\% over the best baselines. The code is available at https://github.com/w2obin/airdde-aaai.