Urban air quality modelling aims at inferring unknown pollution concentrations at specific urban locations. Physical methods derive the partial differential equations (PDEs) that mathematically define the laws of motion, albeit using computationally intense algorithms. In contrast, deep (generative) models, such as variational autoencoders, provide high performance by addressing the task as a data generation problem. Yet, physics knowledge and the spatio-temporal data correlations are not exploited by these deep learning models. In this work, we propose a physics-guided variational graph autoencoder whose graph convolutional operator is derived from the PDE defining the convection-diffusion physical process. We compare against statistical and deep learning approaches on two air quality datasets and report superior performance.
Rodrigo Bonet, E & Deligiannis, N 2024, Physics-guided variational graph autoencoder for air quality inference. in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, IEEE, pp. 6940-6945. https://doi.org/10.1109/ICASSP48485.2024.10448194
Rodrigo Bonet, E., & Deligiannis, N. (2024). Physics-guided variational graph autoencoder for air quality inference. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 6940-6945). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). IEEE. https://doi.org/10.1109/ICASSP48485.2024.10448194
@inproceedings{e357924a16e442b3a40006c1d5eb545f,
title = "Physics-guided variational graph autoencoder for air quality inference",
abstract = "Urban air quality modelling aims at inferring unknown pollution concentrations at specific urban locations. Physical methods derive the partial differential equations (PDEs) that mathematically define the laws of motion, albeit using computationally intense algorithms. In contrast, deep (generative) models, such as variational autoencoders, provide high performance by addressing the task as a data generation problem. Yet, physics knowledge and the spatio-temporal data correlations are not exploited by these deep learning models. In this work, we propose a physics-guided variational graph autoencoder whose graph convolutional operator is derived from the PDE defining the convection-diffusion physical process. We compare against statistical and deep learning approaches on two air quality datasets and report superior performance.",
author = "{Rodrigo Bonet}, Esther and Nikos Deligiannis",
note = "Funding Information: This work was supported in part by the Research Foundation - Flanders (FWO) through the Ph.D. Fellowship Strategic Basic Research under Project 1SC4521N, in part by IMEC under the AAA Project AI-based Air Quality Map and Analytics and in part by the Flemish Government, under the Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen programme. Publisher Copyright: {\textcopyright} 2024 IEEE.",
year = "2024",
doi = "10.1109/ICASSP48485.2024.10448194",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",
pages = "6940--6945",
booktitle = "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
}