Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting

Binqing Wu, Zongjiang Shang, Shiyu Liu, Jianlong Huang, Jiahui Xu, Ling Chen

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.

AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting

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.
Paper Structure (20 sections, 11 equations, 5 figures, 6 tables)

This paper contains 20 sections, 11 equations, 5 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminary
  4. Methodology
  5. Overview
  6. Spatiotemporal Encoder
  7. Diffusion-Advection Graph Construction
  8. Memory-Augmented Attention Module
  9. Physics-Guided Delay Evolving Function
  10. Spatiotemporal Decoder
  11. Experiments
  12. Experimental Setup
  13. Overall Comparison
  14. Ablation Study
  15. Long-Term Study
  16. ...and 5 more sections

Figures (5)

  • Figure 1: The architecture of AirDDE.
  • Figure 2: Results of the long-term study on China-AQI.
  • Figure 3: Station distribution of China-AQI (left) and US-PM (right).
  • Figure 4: Case of city-wise advection with delay effects.
  • Figure 5: Case of region-wise advection with delay effects.