NeuroDDAF: Neural Dynamic Diffusion-Advection Fields with Evidential Fusion for Air Quality Forecasting
2026-04-01 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new method called NeuroDDAF to better predict air quality by combining knowledge of physics with advanced neural networks. Their approach uses wind information and models how pollution spreads over time in cities. Tests in multiple cities showed that NeuroDDAF predicts air quality more accurately than existing methods, especially for forecasts 1 to 3 days ahead. It also gives reliable estimates of uncertainty and works well when applied to different cities. Overall, the authors provide a more precise and robust tool for forecasting air pollution.
Air quality forecastingSpatiotemporal dynamicsDiffusion-advectionGraph Attention NetworkNeural ODEEvidential fusionRMSEMAEUncertainty quantificationCross-city generalization
Authors
Prasanjit Dey, Soumyabrata Dev, Angela Meyer, Bianca Schoen-Phelan
Abstract
Accurate air quality forecasting is crucial for protecting public health and guiding environmental policy, yet it remains challenging due to nonlinear spatiotemporal dynamics, wind-driven transport, and distribution shifts across regions. Physics-based models are interpretable but computationally expensive and often rely on restrictive assumptions, whereas purely data-driven models can be accurate but may lack robustness and calibrated uncertainty. To address these limitations, we propose Neural Dynamic Diffusion-Advection Fields (NeuroDDAF), a physics-informed forecasting framework that unifies neural representation learning with open-system transport modeling. NeuroDDAF integrates (i) a GRU-Graph Attention encoder to capture temporal dynamics and wind-aware spatial interactions, (ii) a Fourier-domain diffusion-advection module with learnable residuals, (iii) a wind-modulated latent Neural ODE to model continuous-time evolution under time-varying connectivity, and (iv) an evidential fusion mechanism that adaptively combines physics-guided and neural forecasts while quantifying uncertainty. Experiments on four urban datasets (Beijing, Shenzhen, Tianjin, and Ancona) across 1-3 day horizons show that NeuroDDAF consistently outperforms strong baselines, including AirPhyNet, achieving up to 9.7% reduction in RMSE and 9.4% reduction in MAE on long-term forecasts. On the Beijing dataset, NeuroDDAF attains an RMSE of 41.63 $μ$g/m$^3$ for 1-day prediction and 48.88 $μ$g/m$^3$ for 3-day prediction, representing the best performance among all compared methods. In addition, NeuroDDAF improves cross-city generalization and yields well-calibrated uncertainty estimates, as confirmed by ensemble variance analysis and case studies under varying wind conditions.