Abstract—Challenges in air pollution control and
environmental management continue to evolve, significantly
impacting public health and ecosystems. This study estimates
surface Nitrogen Dioxide (NO₂) concentrations in Lithuania
using an integrated framework. It combines Sentinel-5
Precursor satellite (5P) TROPOspheric Monitoring Instrument
(TROPOMI) observations of total NO₂ Vertical Column
Densities (VCDs) with various meteorological parameters, such
as air temperature, wind speed, and direction. Data were
collected across thirteen in situ monitoring stations throughout
Lithuania, spanning from January 2020 to December 2023. The
analysis involved two modelling approaches: Bagged Trees (BT)
and Coarse Tree (CT) algorithms. The BT model outperformed
the CT, achieving lower Root Mean Square Error (RMSE)
values of 5.12 μg/m³ during validation and 4.90 μg/m³ during
testing, compared to 5.73 μg/m³ and 5.58 μg/m³ for the CT model,
respectively. The integration of VCDs data and predictive
modeling provides valuable indicators for NO₂ concentration
trends, stressing the necessity of continuous monitoring efforts,
essential for effective air pollution management.
Keywords—satellite monitoring, Nitrogen Dioxide (NO₂), air
pollution control, environmental management, atmospheric
monitoring, geospatial analysis, air quality assessment,
predictive modelling
Cite: Mina Adel Shokry Fahim and Jūratė Sužiedelytė Visockienė, "Satellite-Driven Monitoring and Prediction of Atmospheric Nitrogen Dioxide in Lithuania," International Journal of Environmental Science and Development vol. 16, no. 4, pp. 265-271, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).