Improving Air Quality Zoning Through Deep Learning and Hyperlocal Measurements
According to the Air Quality Directive 2008/50/EC, air quality zoning divides a territory into air quality zones where pollution and citizen exposure are similar and can be monitored using similar strategies. However, there is no standardized computational methodology to solve this problem, and only...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10460554/ |
_version_ | 1797243297084735488 |
---|---|
author | Eduardo Illueca Fernandez Antonio Jesus Jara Valera Jesualdo Tomas Fernandez Breis |
author_facet | Eduardo Illueca Fernandez Antonio Jesus Jara Valera Jesualdo Tomas Fernandez Breis |
author_sort | Eduardo Illueca Fernandez |
collection | DOAJ |
description | According to the Air Quality Directive 2008/50/EC, air quality zoning divides a territory into air quality zones where pollution and citizen exposure are similar and can be monitored using similar strategies. However, there is no standardized computational methodology to solve this problem, and only a few experiences in the Comunidad of Madrid based on chemistry transport models. In this study, we propose a methodological improvement based on the application of deep learning. Our method uses the CHIMERE-WRF air quality modelling system and adds a step that uses neural networks architectures to calibrate the simulations. We have validated our method in the Region of Murcia. The results obtained are promising given the values of the Pearson coefficient, obtaining <inline-formula> <tex-math notation="LaTeX">$r = 0.94$ </tex-math></inline-formula> for <inline-formula> <tex-math notation="LaTeX">$NO_{2}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$r = 0.95$ </tex-math></inline-formula> for <inline-formula> <tex-math notation="LaTeX">$O_{3}$ </tex-math></inline-formula>, improving 86 % and 29 % the performances reported in the state of the art. In addition, the cluster score improves after applying neural networks, demonstrating that neural networks improve the consistency of clusters compared to the current air quality zoning. This opened new research opportunities based on the use of neural networks for dimension reduction in spatial clustering problems, and we were able to provide recommendations for a new measurement point in the Region of Murcia Air Quality Network. |
first_indexed | 2024-04-24T18:52:52Z |
format | Article |
id | doaj.art-74c8fad3253e436d8c1b0e954c55844c |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-24T18:52:52Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-74c8fad3253e436d8c1b0e954c55844c2024-03-26T17:48:42ZengIEEEIEEE Access2169-35362024-01-0112387003871610.1109/ACCESS.2024.337420810460554Improving Air Quality Zoning Through Deep Learning and Hyperlocal MeasurementsEduardo Illueca Fernandez0https://orcid.org/0000-0002-1837-0355Antonio Jesus Jara Valera1https://orcid.org/0000-0002-2651-6684Jesualdo Tomas Fernandez Breis2https://orcid.org/0000-0002-7558-2880Department of Informatics and Systems, University of Murcia, Murcia, SpainResearch and Development Department, Libelium LAB, Ceutí, SpainDepartment of Informatics and Systems, University of Murcia, Murcia, SpainAccording to the Air Quality Directive 2008/50/EC, air quality zoning divides a territory into air quality zones where pollution and citizen exposure are similar and can be monitored using similar strategies. However, there is no standardized computational methodology to solve this problem, and only a few experiences in the Comunidad of Madrid based on chemistry transport models. In this study, we propose a methodological improvement based on the application of deep learning. Our method uses the CHIMERE-WRF air quality modelling system and adds a step that uses neural networks architectures to calibrate the simulations. We have validated our method in the Region of Murcia. The results obtained are promising given the values of the Pearson coefficient, obtaining <inline-formula> <tex-math notation="LaTeX">$r = 0.94$ </tex-math></inline-formula> for <inline-formula> <tex-math notation="LaTeX">$NO_{2}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$r = 0.95$ </tex-math></inline-formula> for <inline-formula> <tex-math notation="LaTeX">$O_{3}$ </tex-math></inline-formula>, improving 86 % and 29 % the performances reported in the state of the art. In addition, the cluster score improves after applying neural networks, demonstrating that neural networks improve the consistency of clusters compared to the current air quality zoning. This opened new research opportunities based on the use of neural networks for dimension reduction in spatial clustering problems, and we were able to provide recommendations for a new measurement point in the Region of Murcia Air Quality Network.https://ieeexplore.ieee.org/document/10460554/Air qualityartificial neural networksatmospheric modelingclustering algorithmsdeep learning |
spellingShingle | Eduardo Illueca Fernandez Antonio Jesus Jara Valera Jesualdo Tomas Fernandez Breis Improving Air Quality Zoning Through Deep Learning and Hyperlocal Measurements IEEE Access Air quality artificial neural networks atmospheric modeling clustering algorithms deep learning |
title | Improving Air Quality Zoning Through Deep Learning and Hyperlocal Measurements |
title_full | Improving Air Quality Zoning Through Deep Learning and Hyperlocal Measurements |
title_fullStr | Improving Air Quality Zoning Through Deep Learning and Hyperlocal Measurements |
title_full_unstemmed | Improving Air Quality Zoning Through Deep Learning and Hyperlocal Measurements |
title_short | Improving Air Quality Zoning Through Deep Learning and Hyperlocal Measurements |
title_sort | improving air quality zoning through deep learning and hyperlocal measurements |
topic | Air quality artificial neural networks atmospheric modeling clustering algorithms deep learning |
url | https://ieeexplore.ieee.org/document/10460554/ |
work_keys_str_mv | AT eduardoilluecafernandez improvingairqualityzoningthroughdeeplearningandhyperlocalmeasurements AT antoniojesusjaravalera improvingairqualityzoningthroughdeeplearningandhyperlocalmeasurements AT jesualdotomasfernandezbreis improvingairqualityzoningthroughdeeplearningandhyperlocalmeasurements |