EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-time AIoT platform for monitoring and prediction of air quality in Southwestern Morocco

Abdellatif Bekkar iD, Badr Hssina, Najib Abekiri iD, Samira Douzi iD, Khadija Douzi

PLOS ONE · 22.08.2024 · 19 (8) · e0307214

DOI: 10.1371/journal.pone.0307214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 22.08.2024. Verfasst von Abdellatif Bekkar und 4 weiteren Autor:innen. Beteiligte Einrichtung: LIM Laboratory, Faculty of Sciences and Technics Hassan II University of Casablanca, Mohammedia, Morocco. Hauptthemen laut MEDLINE: Air Pollution, Environmental Monitoring, Particulate Matter, Bayes Theorem. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urbanization and industrialization have led to a significant increase in air pollution, posing a severe environmental and public health threat. Accurate forecasting of air quality is crucial for policymakers to implement effective interventions. This study presents a novel AIoT platform specifically designed for PM 2.5 monitoring in Southwestern Morocco. The platform utilizes low-cost sensors to collect air quality data, transmitted via WiFi/3G for analysis and prediction on a central server. We focused on identifying optimal features for PM 2.5 prediction using Minimum Redundancy Maximum Relevance (mRMR) and LightGBM Recursive Feature Elimination (LightGBM-RFE) techniques. Furthermore, Bayesian optimization was employed to fine-tune hyperparameters of popular machine learning models for the most accurate PM 2.5 concentration forecasts. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R 2 ). Our results demonstrate that the LightGBM model achieved superior performance in PM 2.5 prediction, with a significant reduction in RMSE compared to other evaluated models. This study highlights the potential of AIoT platforms coupled with advanced feature selection and hyperparameter optimization for effective air quality monitoring and forecasting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Air PollutionEnvironmental MonitoringParticulate MatterBayes TheoremMoroccoMachine LearningForecastingAir Pollutants

Substanzen

Particulate MatterAir Pollutants

Autor:innen und Institutionen

  • LIM Laboratory, Faculty of Sciences and Technics Hassan II University of Casablanca, Mohammedia, Morocco.
  • Higher School of Technology, University Ibn Zohr, Agadir, Morocco.
  • Faculty of Medicine and Pharmacy, Mohammed V University in Rabat, Rabat, Morocco.

ORCID-Profile: Abdellatif Bekkar, Najib Abekiri, Samira Douzi

Zitieren

APA

Bekkar, A., Hssina, B., Abekiri, N., Douzi, S., & Douzi, K. (2024). Real-time AIoT platform for monitoring and prediction of air quality in Southwestern Morocco. PLOS ONE, 19(8), e0307214. https://doi.org/10.1371/journal.pone.0307214

Vancouver

Bekkar A, Hssina B, Abekiri N, Douzi S, Douzi K. Real-time AIoT platform for monitoring and prediction of air quality in Southwestern Morocco. PLOS ONE. 2024;19(8):e0307214. doi:10.1371/journal.pone.0307214

BibTeX
@article{Bekkar2024,
  author = {Bekkar, Abdellatif and Hssina, Badr and Abekiri, Najib and Douzi, Samira and Douzi, Khadija},
  title = {Real-time AIoT platform for monitoring and prediction of air quality in Southwestern Morocco},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {8},
  pages = {e0307214},
  doi = {10.1371/journal.pone.0307214}
}
Kostenlos starten →