Comparative Evaluation of Machine Learning Models for Urban Air Quality Forecasting in Emerging Economies

References

[1] Aryal, R., Shrestha, S., Niraula, S., & Paudel, B. (2023). XGBoost with Bayesian hyperparameter optimization for AQI forecasting in South Asian cities. Environ. Sci. Pollut. Res., 30(14), 41182–41197.

[2] Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). Wiley.

[3] Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

[4] Brokamp, C., Jandarov, R., Hossain, M., & Ryan, P. (2018). Predicting daily urban PM2.5 using a random forest model. Environ. Sci. Technol., 52(7), 4173–4179.

[5] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proc. 22nd ACM SIGKDD, 785–794.

[6] Grange, S. K., Carslaw, D. C., Lewis, A. C., Boleti, E., & Hueglin, C. (2018). Random forest meteorological normalisation models for Swiss PM10 trend analysis. Atmos. Chem. Phys., 18(9), 6223–6239.

[7] Gupta, P., & Gupta, S. (2023). Machine learning for AQI prediction in Indian cities during NCAP (2019–2023). Atmos. Environ., 296, 119571.

[8] Hu, X., et al. (2017). Estimating PM2.5 in the US using the random forest approach. Environ. Sci. Technol., 51(12), 6936–6944.

[9] Kumari, S., & Toshniwal, D. (2021). Deep learning models for air quality forecasting across diverse Indian cities. Sustain. Cities Soc., 71, 102970.

[10] Lelieveld, J., et al. (2020). Loss of life expectancy from air pollution: A worldwide perspective. Cardiovasc. Res., 116(11), 1910–1917.

[11] Liang, Y. C., et al. (2020). Machine learning-based prediction of air quality. Appl. Sci., 10(24), 9151.

[12] MoEF&CC (2014). National air quality index. Government of India.

[13] Mishra, D., & Goyal, P. (2015). AI-based NO₂ forecasting models at Taj Mahal, Agra. Atmos. Pollut. Res., 6(1), 99–106.

[14] Ni, X., Huang, H., & Du, W. (2018). Short-term prediction of PM2.5 in Beijing based on multi-source data. Atmos. Environ., 190, 168–178.

[15] Ong, B. T., Sugiura, K., & Zettsu, K. (2016). Dynamically pre-trained deep RNNs for predicting PM2.5. Neural Comput. Appl., 27(6), 1553–1566.

[16] Pandey, G., Zhang, B., & Jian, L. (2021). Predicting submicron air pollution indicators: A ML approach. Environ. Sci. Process. Impacts, 15(5), 996–1005.

[17] Qi, Z., et al. (2018). Deep air learning: Feature analysis of fine-grained air quality. IEEE Trans. Knowl. Data Eng., 30(12), 2285–2297.

[18] Rybarczyk, Y., & Zalakeviciute, R. (2021). Machine learning approaches for outdoor AQ modelling: A systematic review. Appl. Sci., 8(12), 2570.

[19] Shams, S. R., et al. (2021). AI accuracy assessment in NO₂ concentration forecasting of metropolises. Sci. Rep., 11(1), 1–10.

[20] Soh, P. W., Chang, J. W., & Huang, J. W. (2020). Adaptive deep learning-based AQ prediction model. IEEE Access, 6, 38186–38199.

[21] Srivastava, R. K., Sharma, A., & Pandey, S. K. (2022). LSTM vs. XGBoost for AQI prediction in Indian Tier-2 cities. J. Clean. Prod., 344, 130935.

[22] State of Global Air (2023). State of global air 2023: A special report on global exposure to air pollution and its health impacts. Health Effects Institute.

[23] Vapnik, V., & Chervonenkis, A. (1971). Uniform convergence of relative frequencies to probabilities. Theory Probab. Appl., 16(2), 264–280.

[24] Wang, Y., et al. (2019). Large-scale daily PM2.5 dataset using ML in China (2010–2019). Earth Syst. Sci. Data, 12(3), 1–37.

[25] World Health Organization (2021). WHO global air quality guidelines. WHO Press.

[26] Zareba, M., et al. (2023). Big-data-driven ML for spatiotemporal air pollution pattern analysis. Atmosphere, 14(4), 760.

[27] Zhang, Y., et al. (2019). Application of WRF/Chem over East Asia: Model evaluation. Tellus B, 62(5), 806–826.

@article{1717704,
      author = {Moksha Vora, Dr. Syed Shahid Raza},
      title = {Comparative Evaluation of Machine Learning Models for Urban Air Quality Forecasting in Emerging Economies},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {11},
      pages = {1190-1196},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1717704.pdf},
      abstract = {This study undertakes a comparative evaluation of Random Forest (RF) and XGBoost for daily Air Quality Index (AQI) forecasting across five major Indian metropolitan cities—Delhi, Mumbai, Kolkata, Chennai and Bangalore—spanning 2021 to 2025. The dataset comprises 7,605 city-day observations drawn from the CPCB monitoring archive, enriched with temporal lag features, rolling window statistics and cyclical calendar encodings. Both models were trained on an 80/20 temporal split and evaluated using RMSE, MAE and R². RF demonstrated superior predictive accuracy across all five cities, yielding an overall R²=0.6565 versus 0.6390 for XGBoost, with peak performance in Mumbai (R²=0.8627) and Delhi (R²=0.8516). Feature importance analysis confirmed the primacy of lagged AQI values (AQI_lag1: 86.34% of RF importance), underscoring the strongly autoregressive nature of urban air quality dynamics. Seasonal analysis identified Winter as the highest-pollution season (mean AQI=161.75) and the most challenging for accurate prediction. Findings provide actionable guidance for data-driven early-warning systems in emerging economy urban contexts.},
      keywords = {Air Quality Index; Random Forest; XGBoost; Urban Air Quality Forecasting; Machine Learning; India; Emerging Economies},
      month = {May},
      doi = {https://doi.org/10.64388/IREV9I11-1717704}
  }