EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Forecasting air pollution with deep learning with a focus on impact of urban traffic on PM10 and noise pollution

Martin Kostadinov, Eftim Zdravevski, Petre Lameski iD, Paulo Jorge Coelho iD, Biljana Stojkoska, Michael A Herzog, Vladimir Trajkovik

PLOS ONE · 10.12.2024 · 19 (12) · e0313356

DOI: 10.1371/journal.pone.0313356 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 10.12.2024. Verfasst von Martin Kostadinov und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje, Skopje, N. Macedonia. Hauptthemen laut MEDLINE: Deep Learning, Air Pollution, Particulate Matter. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FCT/MEC, Ss. Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering, Bundesministerium für Bildung & Forschung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Air pollution constitutes a significant worldwide environmental challenge, presenting threats to both our well-being and the purity of our food supply. This study suggests employing Recurrent Neural Network (RNN) models featuring Long Short-Term Memory (LSTM) units for forecasting PM10 particle levels in multiple locations in Skopje simultaneously over a time span of 1, 6, 12, and 24 hours. Historical air quality measurement data were gathered from various local sensors positioned at different sites in Skopje, along with data on meteorological conditions from publicly available APIs. Various implementations and hyperparameters of several deep learning models were compared. Additionally, an analysis was conducted to assess the influence of urban traffic on air and noise pollution, leveraging the COVID-19 lockdown periods when traffic was virtually non-existent. The outcomes suggest that the proposed models can effectively predict air pollution. From the urban traffic perspective, the findings indicate that car traffic is not the major contributing factor to air pollution.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAir PollutionParticulate MatterHumansForecastingNoiseCOVID-19Vehicle EmissionsEnvironmental MonitoringNeural Networks, ComputerCitiesAir Pollutants

Substanzen

Particulate MatterVehicle EmissionsAir Pollutants

Autor:innen und Institutionen

  • Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje, Skopje, N. Macedonia.
  • School of Technology and Management, Polytechnic of Leiria, Leiria, Portugal.
  • Institute for Systems Engineering and Computers at Coimbra (INESC Coimbra), DEEC, Coimbra, Portugal.
  • Magdeburg-Stendal University, Magdeburg, Germany.

ORCID-Profile: Petre Lameski, Paulo Jorge Coelho

Förderung

  • FCT/MEC
  • Ss. Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering
  • Bundesministerium für Bildung & Forschung
  • NVIDIA

Zitieren

APA

Kostadinov, M., Zdravevski, E., Lameski, P., Coelho, P. J., Stojkoska, B., Herzog, M. A., & Trajkovik, V. (2024). Forecasting air pollution with deep learning with a focus on impact of urban traffic on PM10 and noise pollution. PLOS ONE, 19(12), e0313356. https://doi.org/10.1371/journal.pone.0313356

Vancouver

Kostadinov M, Zdravevski E, Lameski P, Coelho PJ, Stojkoska B, Herzog MA, et al. Forecasting air pollution with deep learning with a focus on impact of urban traffic on PM10 and noise pollution. PLOS ONE. 2024;19(12):e0313356. doi:10.1371/journal.pone.0313356

BibTeX
@article{Kostadinov2024,
  author = {Kostadinov, Martin and Zdravevski, Eftim and Lameski, Petre and Coelho, Paulo Jorge and Stojkoska, Biljana and Herzog, Michael A and Trajkovik, Vladimir},
  title = {Forecasting air pollution with deep learning with a focus on impact of urban traffic on PM10 and noise pollution},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {12},
  pages = {e0313356},
  doi = {10.1371/journal.pone.0313356}
}
Kostenlos starten →