Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data

2025-05-07

ACM transactions on sensor networks

AI Summary

Urban air quality monitoring—particularly in socioeconomically disadvantaged areas—suffers from sparse sensor deployment and consequently limited modeling accuracy and spatial resolution. To address this, we propose GraPhy, a physics-informed graph neural network that uniquely embeds the atmospheric advection–diffusion equation into a graph structure. GraPhy integrates multi-scale spatial heterogeneity modeling with edge-feature-driven graph convolution, specifically designed for low-density, low-resolution monitoring data. Evaluated on PM₂.₅ monitoring in California’s San Joaquin Valley, GraPhy consistently outperforms baseline methods across all metrics: MSE, MAE, and R² improve by 9%–56%. Crucially, it maintains robust performance across diverse spatial heterogeneity regimes. This work establishes a generalizable paradigm for high-resolution, accurate PM₂.₅ mapping in data-scarce regions.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

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

Abstract

This work introduces GraPhy, a graph-based, physics-guided learning framework for high-resolution and accurate air quality modeling in urban areas with limited monitoring data. Fine-grained air quality monitoring information is essential for reducing public exposure to pollutants. However, monitoring networks are often sparse in socioeconomically disadvantaged regions, limiting the accuracy and resolution of air quality modeling. To address this, we propose a physics-guided graph neural network architecture called GraPhy with layers and edge features designed specifically for low-resolution monitoring data. Experiments using data from California’s socioeconomically disadvantaged San Joaquin Valley show that GraPhy achieves the overall best performance evaluated by mean squared error (MSE), mean absolute error (MAE), and R-square value (R2), improving the performance by 9%-56% compared to various baseline models. Moreover, GraPhy consistently outperforms baselines across different spatial heterogeneity levels, demonstrating the effectiveness of our model design.

Problem

• Imputing urban PM2.5 with sparse monitoring data
• Enhancing air quality modeling resolution in disadvantaged regions
• Combining physics and graph networks for accurate predictions

Innovation

• Graph neural network for air quality modeling
• Physics-guided learning with sparse data
• Improved accuracy in disadvantaged regions