Double-Diffusion: Diffusion Conditioned Diffusion Probabilistic Model For Air Quality Prediction

2025-06-28

AI Summary

To address the challenge of jointly modeling spatiotemporal dynamics and uncertainty in air quality forecasting, this paper proposes a dual-diffusion probabilistic generative framework. It pioneers the integration of physical laws—such as mass conservation and the diffusion equation—as conditional priors into a diffusion model, enabling synergistic incorporation of deterministic domain knowledge and stochastic uncertainty modeling. The framework features a graph neural network–enhanced spatial modeling module and a physics-constrained conditional denoiser; it further adopts insights from image restoration to optimize the sampling strategy. Evaluated on two real-world datasets, our method achieves state-of-the-art performance across most metrics: continuous ranked probability score improves by 3%–12%, inference speed increases by 30%–50%, and predictions exhibit enhanced accuracy, physical consistency, and computational efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Air quality prediction is a challenging forecasting task due to its spatio-temporal complexity and the inherent dynamics as well as uncertainty. Most of the current models handle these two challenges by applying Graph Neural Networks or known physics principles, and quantifying stochasticity through probabilistic networks like Diffusion models. Nevertheless, finding the right balancing point between the certainties and uncertainties remains an open question. Therefore, we propose Double-Diffusion, a novel diffusion probabilistic model that harnesses the power of known physics to guide air quality forecasting with stochasticity. To the best of our knowledge, while precedents have been made of using conditional diffusion models to predict air pollution, this is the first attempt to use physics as a conditional generative approach for air quality prediction. Along with a sampling strategy adopted from image restoration and a new denoiser architecture, Double-Diffusion ranks first in most evaluation scenarios across two real-life datasets compared with other probabilistic models, it also cuts inference time by 50% to 30% while enjoying an increase between 3-12% in Continuous Ranked Probabilistic Score (CRPS).

Problem

• Balancing certainty and uncertainty in air quality prediction
• Integrating physics principles with diffusion models for forecasting
• Reducing inference time while improving prediction accuracy

Innovation

• Physics-guided conditional diffusion model
• Image restoration-based sampling strategy
• Novel denoiser architecture reduces inference time