Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 15.85 MB
Add to list
  1. Search results
  2. Spatiotemporal air quality inference ...

Spatiotemporal air quality inference of low-cost sensor data : evidence from multiple sensor testbeds

Jelle Hofman, Tien Huu Do, Xuening Qin (UGent) , Esther Rodrigo Bonet, Wilfried Philips (UGent) , Nikos Deligiannis and Valerio Panzica La Manna
(2022) ENVIRONMENTAL MODELLING & SOFTWARE. 149.
Author
Organization
Project
Abstract
Recent advances in sensor and IoT technologies allow for denser and mobile air quality measurements. These measurements are still spatiotemporally sparse at city-level, but can be interpolated using data-driven techniques. This work presents validation results of two machine-learning models to infer air quality sensor data in both space and time. Temporal validation exercises are performed at available regulatory monitoring stations following the FAIRMODE protocol. Both models show scalable to different mobile datasets with comparable prediction performance for PM2.5 (R-2 = 0.68-0.75, MAE = 2.99-2.82 mu g m(- 3)) and NO2 (R-2 = 0.8-0.82, MAE = 8.81-9.83 mu gm(- 3)) in Utrecht and Antwerp. In Oakland (Atlanta), we observed a lower performance for NO2 (R-2 = 0.46-0.41, MAE = 4.06-5.07) and BC (R-2 = 0.31-0.28, MAE = 0.48-0.27), likely caused by the less representative monitoring coverage. Although comparable in terms of prediction performance, the Geographical Random Forest (GRF) model seems to achieve slightly better accuracies, while the correlations are typically higher for the Air Variational Graph Autoencoder (AVGAE) model. This work demonstrates the potential of data driven techniques for spatiotemporal air quality inference of complementary sensor data. The observed performance metrics approach current state-of-the-art chemical transport models in terms of performance while needing much lower resources, computational power, infrastructure and processing time.& nbsp;& nbsp;
Keywords
Ecological Modeling, Environmental Engineering, Software, IoT, Urban, Air quality, Mobile, Sensors, Machine learning, BLACK CARBON, ULTRAFINE PARTICLES, CYCLIST EXPOSURE, URBAN ROUTES, POLLUTION, ANTWERP, PM2.5, PM10, UFP

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 15.85 MB

Citation

Please use this url to cite or link to this publication:

MLA
Hofman, Jelle, et al. “Spatiotemporal Air Quality Inference of Low-Cost Sensor Data : Evidence from Multiple Sensor Testbeds.” ENVIRONMENTAL MODELLING & SOFTWARE, vol. 149, 2022, doi:10.1016/j.envsoft.2022.105306.
APA
Hofman, J., Do, T. H., Qin, X., Bonet, E. R., Philips, W., Deligiannis, N., & La Manna, V. P. (2022). Spatiotemporal air quality inference of low-cost sensor data : evidence from multiple sensor testbeds. ENVIRONMENTAL MODELLING & SOFTWARE, 149. https://doi.org/10.1016/j.envsoft.2022.105306
Chicago author-date
Hofman, Jelle, Tien Huu Do, Xuening Qin, Esther Rodrigo Bonet, Wilfried Philips, Nikos Deligiannis, and Valerio Panzica La Manna. 2022. “Spatiotemporal Air Quality Inference of Low-Cost Sensor Data : Evidence from Multiple Sensor Testbeds.” ENVIRONMENTAL MODELLING & SOFTWARE 149. https://doi.org/10.1016/j.envsoft.2022.105306.
Chicago author-date (all authors)
Hofman, Jelle, Tien Huu Do, Xuening Qin, Esther Rodrigo Bonet, Wilfried Philips, Nikos Deligiannis, and Valerio Panzica La Manna. 2022. “Spatiotemporal Air Quality Inference of Low-Cost Sensor Data : Evidence from Multiple Sensor Testbeds.” ENVIRONMENTAL MODELLING & SOFTWARE 149. doi:10.1016/j.envsoft.2022.105306.
Vancouver
1.
Hofman J, Do TH, Qin X, Bonet ER, Philips W, Deligiannis N, et al. Spatiotemporal air quality inference of low-cost sensor data : evidence from multiple sensor testbeds. ENVIRONMENTAL MODELLING & SOFTWARE. 2022;149.
IEEE
[1]
J. Hofman et al., “Spatiotemporal air quality inference of low-cost sensor data : evidence from multiple sensor testbeds,” ENVIRONMENTAL MODELLING & SOFTWARE, vol. 149, 2022.
@article{8738419,
  abstract     = {{Recent advances in sensor and IoT technologies allow for denser and mobile air quality measurements. These measurements are still spatiotemporally sparse at city-level, but can be interpolated using data-driven techniques. This work presents validation results of two machine-learning models to infer air quality sensor data in both space and time. Temporal validation exercises are performed at available regulatory monitoring stations following the FAIRMODE protocol. Both models show scalable to different mobile datasets with comparable prediction performance for PM2.5 (R-2 = 0.68-0.75, MAE = 2.99-2.82 mu g m(- 3)) and NO2 (R-2 = 0.8-0.82, MAE = 8.81-9.83 mu gm(- 3)) in Utrecht and Antwerp. In Oakland (Atlanta), we observed a lower performance for NO2 (R-2 = 0.46-0.41, MAE = 4.06-5.07) and BC (R-2 = 0.31-0.28, MAE = 0.48-0.27), likely caused by the less representative monitoring coverage. Although comparable in terms of prediction performance, the Geographical Random Forest (GRF) model seems to achieve slightly better accuracies, while the correlations are typically higher for the Air Variational Graph Autoencoder (AVGAE) model. This work demonstrates the potential of data driven techniques for spatiotemporal air quality inference of complementary sensor data. The observed performance metrics approach current state-of-the-art chemical transport models in terms of performance while needing much lower resources, computational power, infrastructure and processing time.& nbsp;& nbsp;}},
  articleno    = {{105306}},
  author       = {{Hofman, Jelle and Do, Tien Huu and Qin, Xuening and Bonet, Esther Rodrigo and Philips, Wilfried and Deligiannis, Nikos and La Manna, Valerio Panzica}},
  issn         = {{1364-8152}},
  journal      = {{ENVIRONMENTAL MODELLING & SOFTWARE}},
  keywords     = {{Ecological Modeling,Environmental Engineering,Software,IoT,Urban,Air quality,Mobile,Sensors,Machine learning,BLACK CARBON,ULTRAFINE PARTICLES,CYCLIST EXPOSURE,URBAN ROUTES,POLLUTION,ANTWERP,PM2.5,PM10,UFP}},
  language     = {{eng}},
  pages        = {{12}},
  title        = {{Spatiotemporal air quality inference of low-cost sensor data : evidence from multiple sensor testbeds}},
  url          = {{http://doi.org/10.1016/j.envsoft.2022.105306}},
  volume       = {{149}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: