Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data
Open Access
- 25 April 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 22 (4) , 1-23
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 ( R 2 ), 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. 1Keywords
All Related Versions
This publication has 50 references indexed in Scilit:
- Tool learning with large language models: a surveyFrontiers of Computer Science, 2025
- Statistical Modeling for Spatio-Temporal Data From Stochastic Convection-Diffusion ProcessesJournal of the American Statistical Association, 2021
- Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modelingEngineering Structures, 2020
- Step-Level Occupant Detection across Different Structures through Footstep-Induced Floor Vibration Using Model TransferJournal of Engineering Mechanics, 2020
- A temporal-spatial interpolation and extrapolation method based on geographic Long Short-Term Memory neural network for PM2.5Journal of Cleaner Production, 2019
- Spatial interpolation of air pollution measurements using CORINE land cover dataAtmospheric Environment, 2008
- A new model for learning in graph domains2006
- Recommendations on the Use of Satellite Remote-Sensing Data for Urban Air QualityJournal of the Air & Waste Management Association, 2004
- A Comparison of Four Gravimetric Fine Particle Sampling MethodsJournal of the Air & Waste Management Association, 2001
- A desicion-theoretic generalization of on-line learning and an application to boosting1995