AI-Based NO2 Concentration Prediction for Sustainable Environment Monitoring
Journal of Engineering and Applied Sciences · 2026 · 13 (1) · 1
DOI: 10.5455/jeas.2026060101 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Engineering and Applied Sciences, 2026. Verfasst von Hassan Jari.
Abstract (Originalsprache)
Nitrogen dioxide (NO₂) is a very critical atmospheric pollutant, which has greatly influenced environmental sustainability and public health. The measurements collected for NO₂ concentrations are valuable to improve air quality management and mitigation strategies. We propose an AI-oriented sustainable environment management system that predicts NO₂ in urban and industrial areas by implementing machine learning (ML) techniques. The model is developed to forecast the NO₂ concentrations based on the recorded past data on air quality and meteorological parameters (temperature, humidity, and wind speed) traffic flow data. For time-series forecasting and feature analysis advanced ML algorithms such as LSTM, Random Forest, and XGboost have been used. The results of this study indicate that these models are highly accurate by employing actual datasets in their evaluation. Further, the use of ML to predict provides early intervention for policymakers, enforces data-based environmental policies, has an overall favorable impact in decreasing pollution. Thus, the present study enhances the understanding of smart city applicability, air quality sentinel, as well as sustainable environmental management by applying AI for enhanced pollution detection.
Zitieren
APA
Jari, H. (2026). AI-Based NO2 Concentration Prediction for Sustainable Environment Monitoring. Journal of Engineering and Applied Sciences, 13(1), 1. https://doi.org/10.5455/jeas.2026060101
Vancouver
Jari H. AI-Based NO2 Concentration Prediction for Sustainable Environment Monitoring. Journal of Engineering and Applied Sciences. 2026;13(1):1. doi:10.5455/jeas.2026060101
BibTeX
@article{Jari2026,
author = {Jari, Hassan},
title = {AI-Based NO2 Concentration Prediction for Sustainable Environment Monitoring},
journal = {Journal of Engineering and Applied Sciences},
year = {2026},
volume = {13},
number = {1},
pages = {1},
doi = {10.5455/jeas.2026060101}
}
EUVIMED