Inferring air quality from a limited number of observations is an essential task for monitoring and controlling air pollution. Existing inference methods typically use low spatial resolution data collected by fixed monitoring stations and infer the concentration of air pollutants using additional types of data, e.g., meteorological and traffic information. In this work, we focus on street-level air quality inference by utilizing data collected by mobile stations. We formulate air quality inference in this setting as a graph-based matrix completion problem and propose a novel variational model based on graph convolutional autoencoders. Our model captures effectively the spatio-temporal correlation of the measurements and does not depend on the availability of additional information apart from the street-network topology. Experiments on a real air quality dataset, collected with mobile stations, shows that the proposed model outperforms state-of-the-art approaches.
Do Huu, T, Nguyen, MD, Tsiligianni, E, Lopez Aguirre, A, Panzica La Manna, V, Pasveer, F, Philips, W & Deligiannis, N 2019, Matrix Completion with Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8683787, IEEE, pp. 7535-7539, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, Brighton, United Kingdom, 12/05/19.
Do Huu, T., Nguyen, M. D., Tsiligianni, E., Lopez Aguirre, A., Panzica La Manna, V., Pasveer, F., Philips, W., & Deligiannis, N. (2019). Matrix Completion with Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 7535-7539). Article 8683787 IEEE.
@inproceedings{fc186d7e0ffa41e686c19cbdd7af2f7b,
title = "Matrix Completion with Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference",
abstract = "Inferring air quality from a limited number of observations is an essential task for monitoring and controlling air pollution. Existing inference methods typically use low spatial resolution data collected by fixed monitoring stations and infer the concentration of air pollutants using additional types of data, e.g., meteorological and traffic information. In this work, we focus on street-level air quality inference by utilizing data collected by mobile stations. We formulate air quality inference in this setting as a graph-based matrix completion problem and propose a novel variational model based on graph convolutional autoencoders. Our model captures effectively the spatio-temporal correlation of the measurements and does not depend on the availability of additional information apart from the street-network topology. Experiments on a real air quality dataset, collected with mobile stations, shows that the proposed model outperforms state-of-the-art approaches.",
keywords = "matrix completion, variational autoencoder, air quality inference, air quality inference, variational graph auto-encoder, graph-based matrix completion, deep learning",
author = "{Do Huu}, Tien and Nguyen, {Minh Duc} and Evangelia Tsiligianni and {Lopez Aguirre}, Angel and {Panzica La Manna}, Valerio and Frank Pasveer and Wilfried Philips and Nikolaos Deligiannis",
year = "2019",
month = apr,
day = "17",
language = "English",
pages = "7535--7539",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
publisher = "IEEE",
note = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",
url = "https://2019.ieeeicassp.org/",
}