Advancing air quality forecasting in Abu Dhabi, UAE using time series models

Mona S. Ramadan, Abdelgadir Abuelgasim, Naeema Al Hosani

Research output: Contribution to journalArticlepeer-review

Abstract

This research enhances air quality predictions in Abu Dhabi by employing Autoregressive Integrated Moving Average (ARIMA) models on comprehensive air quality data collected from 2015 to 2023. We collected hourly data on nitrogen dioxide (NO2), particulate matter (PM10), and fine particulate matter (PM2.5) from 19 well-placed ground monitoring stations. Our approach utilized ARIMA models to forecast future pollutant levels, with extensive data preparation and exploratory analysis conducted in R. Our results found a significant drop in NO2 levels after 2020 and the highest levels of particulate matter observed in 2022. The findings of our research confirm the effectiveness of the models, indicated by Mean Absolute Percentage Error (MAPE) values ranging from 7.71 to 8.59. Additionally, our study provides valuable spatiotemporal insights into air pollution historical evolution, identifying key times and areas of heightened pollution, which can help in devising focused air quality management strategies. This research demonstrates the potential of ARIMA models in precise air quality forecasting, aiding in proactive public health initiatives and environmental policy development, consistent with Abu Dhabi’s Vision 2030.

Original languageEnglish
Article number1393878
JournalFrontiers in Environmental Science
Volume12
DOIs
Publication statusPublished - 2024

Keywords

  • ARIMA model
  • Abu Dhabi
  • R studio
  • air quality
  • environmental management
  • forecasting
  • pollution historical evolution

ASJC Scopus subject areas

  • General Environmental Science

Fingerprint

Dive into the research topics of 'Advancing air quality forecasting in Abu Dhabi, UAE using time series models'. Together they form a unique fingerprint.

Cite this