ASSESSING THE IMPACT OF URBAN INTERSECTION TRAFFIC CONGESTION ON AIR QUALITY IN TASHKENT USING ADVANCED MODELING TECHNIQUES

Boltayev Jahongir Erkin oglu

Authors

Boltayev Jahongir Erkin oglu Termez State University

Abstract

Traffic congestion at urban intersections can significantly degrade air quality, especially through increased vehicle emissions. In Tashkent, a growing vehicle fleet and frequent traffic jams have contributed to worsening pollution levels. For instance, during a peak rush-hour in 2022, Tashkent’s Air Quality Index (AQI) spiked to 262 (considered “very unhealthy”), far exceeding typical levels. Vehicles are identified as the main culprits, accounting for nearly 60% of the 1.3 million tons of pollutants emitted in Uzbekistan during the first nine months of 2022. These emissions include greenhouse gases and harmful pollutants such as carbon dioxide (CO₂), nitrogen dioxide (NO₂), and fine particulate matter (PM₂.₅), all of which pose serious environmental and health risks. Given that most air pollution-related health impacts (e.g., respiratory and cardiovascular diseases) are linked to PM₂.₅, understanding and mitigating traffic-related emissions at intersections is critical. This research focuses on quantifying pollutant concentrations during traffic congestion in Tashkent and applying advanced analytical methods (LSTM neural networks, Kalman filtering, and data segmentation via logistic regression) to model and forecast these pollution levels. The goal is to provide scientifically grounded findings on how congestion elevates pollution and how modern data-driven techniques can improve air quality assessment and management.

Downloads

Download data is not yet available.

References

1. World Health Organization (2021). WHO Global Air Quality Guidelines: Particulate Matter (PM₂.₅ and PM₁₀), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide. Geneva: WHO, 2021.

2. Zhang, R., Zhang, Y., Lin, H., Feng, X., Fu, T.-M., & Wang, Y. (2021). NO₂ and PM₂.₅ pollution reductions in urban traffic due to COVID-19 lockdowns. Environmental Pollution, 268, 115901. (Scopus indexed)

3. Masseran, N., Safari, Y., & Mohd Nasir, A. (2024). Logistic regression analysis for classification of air pollution episodes. Atmospheric Pollution Research, 15(3), 105–115. DOI:10.1016/j.apr.2024.01.015.

4. Goh, K. C., Chong, S. H., & Masrom, M. A. (2022). Air Quality Prediction Model Using LSTM Neural Network. Environmental Engineering Research, 28(4), 342–355. DOI:10.3390/aqpm.2022.08.014.

5. Jahon Banki (World Bank). (2024). Urban Air Quality in Uzbekistan: Trends, Causes and Policy Recommendations. World Bank Group Report, Washington D.C., 2024.

6. Isakov, V., Venkatram, A., & Snyder, M. G. (2020). Using Kalman filter data assimilation to improve near-road air quality modeling. Atmospheric Environment, 234, 117622. DOI:10.1016/j.atmosenv.2020.117622.

7. Song, W., Wang, D., Zhang, Z., & Huang, Y. (2022). A hybrid LSTM–Kalman filtering method for urban air quality forecasting. Atmospheric Pollution Research, 13(1), 78–88. DOI:10.1016/j.apr.2022.05.009.

8. Masseran, N., Mamat, M., Ahmad, M. A., & Zakaria, M. (2024). Modeling extreme pollution events using logistic regression. Environmental Science and Pollution Research, 31(1), 1–11. DOI:10.1007/s11356-024-21199-3.

9. Chen, Y., & Zhang, J. (2023). Integration of Kalman filtering with deep learning models for urban air pollution prediction. Environmental Informatics, 8(2), 25–33. DOI:10.3390/envi8020033.

10. Li, H., Fan, J., & Zhang, X. (2023). Deep learning-based air pollution prediction using LSTM networks. Science of the Total Environment, 898, 165425. DOI:10.1016/j.scitotenv.2023.165165.

11. Fu, L., Zhai, L., & Yang, Y. (2024). Hybrid deep neural networks combining CNN and LSTM for air quality forecasting. Environmental Modelling & Software, 169, 104402. DOI:10.1016/j.envsoft.2024.03.012.

12. Mahajan, S., & Goyal, P. (2021). Air quality forecasting using hybrid LSTM-Kalman filter modeling. Environmental Modeling & Software, 143, 105105. DOI:10.1016/j.envsoft.2021.05.018.

13. Uzbekistan Ministry of Ecology and Environmental Protection. (2022). National environmental report of Uzbekistan. Tashkent, Ministry of Ecology, Environmental Protection and Climate Change, 2022.

14. Ўзбекистон Республикаси Давлат статистика қўмитаси. (2023). 2022 йилда транспорт воситалари ва ҳаво ифлосланиши бўйича статистик маълумотлар. Тошкент: Статистика ахборотномаси.

15. Тошкент шаҳар Экология ва атроф-муҳитни муҳофаза қилиш бошқармаси. (2023). Тошкент шаҳридаги чорраҳаларда ҳаво ифлосланишининг мониторинг ҳисоботлари, 2023 йил учун ҳисобот.

16. UzNews.uz (2023). "Тошкент ҳавосининг ифлосланиш даражаси 2022 йилда 262 баллга етди." URL: https://www.uznews.uz/articles/Tashkent-Air-Pollution-2022-report

17. Дунё Банки. (2024). Ўзбекистон: шаҳар ҳаво сифати таҳлили ва иқтисодий таъсирлар ҳисоботи. Тошкент ва Вашингтон: Жаҳон банки ҳисоботи.

18. US Environmental Protection Agency (EPA). (2021). Idle Reduction and Emissions. EPA Publication, Washington D.C., USA.

19. Luo, Z., Huang, X., & Guo, J. (2022). Assessment of Urban Intersection Traffic Emissions Using Neural Networks. Environmental Monitoring and Assessment, 194(7), 485. DOI:10.1007/s10661-022-10257-4.