A Multiple Linear Regression and Artificial Neural Network Based Comparison of Air Quality Index

IJEP 46(4): 311-317 : Vol. 46 Issue. 4 (April 2026)

Full Text

Lokesh Kumar and Gaurav Kumar*

NAS College, Department of Mathematics, Meerut – 250 003, Uttar Pradesh, India

Abstract

These days, the main issue in cities that affects ecosystems, the environment and human health is air quality. Therefore, daily air pollution forecasts are usually needed by government officials, environmental groups and health agencies. These forecasts often rely on statistical relationships between different factors and air pollution. This work aims to evaluate how well the multi-layer perceptron (MLP) method performs. Radial basis function (RBF) and multiple linear regression (MLR) estimate the air quality index (AQI) for Meerut city. To predict AQI, many indicators, such as PM10, SO2 and NO2 were used. According to the results, the MLR model’s root mean square error (RMSE) is 2.538528, while the MLP’s training and testing values are 0.08165 and 0.053627, respectively. The RBF model’s values are 0.149603 and 0.177307. The MLP model proposed here could be used to improve, analyze and support air pollution prediction and air quality management. This study highlights the importance of designing and using artificial neural networks (ANN) to provide management options for reducing urban pollution.

Keywords

Artificial neural network, Multi-layer perceptron, Radial basis function, Air pollution, Air quality index

References

  1. Murray, C.J.L., et al. 2020. Global burden of 87 risk factors in 204 countries and territories, 1990–2019: a systematic analysis for the global burden of disease study 2019. Lancet., 396(10258): 1223–1249. DOI: 10.1016/S0140-6736(20)30752 -2.
  2. Lee, B.J., Kim, B. and Lee, K. 2014. Air pollution exposure and cardiovascular disease. Toxicol. Res., 30(2): 71–75. DOI: 10.5487/TR.2014.30.2.071.
  3. Apte, J.S., Brauer, M., Cohen, A.J., Ezzati, M. and Pope III, C.A. 2018. Ambient PM2.5reduces global and regional life expectancy. Env. Sci. Tech. Letters. 5(9): 546–551. DOI: 10.1021/acs.estlett.8b 00360.
  4. Wong, E.Y., Gohlke, J., Griffith, W.C., Farrow, S. and Faustman, E.M. 2004. Assessing the health benefits of air pollution reduction for children. Env. Health Perspectives. 112(2): 226–232. DOI: 10.12 89/ehp.6299.
  5. Cao, L., Zhai, D., Kuang, M. and Xia, Y. 2022. Indoor air pollution and frailty: A cross-sectional and follow-up study among older Chinese adults. Env. Res., 204A: 112006. DOI: 10.1016/j.envres.2021. 112006.
  6. Agarwal, N., Meena, C.S., Raj, B.P., Saini, L., Kumar, A., Gopalakrishnan, N., Kumar, A., Balam, N.B., Alam, T., Kapoor, N.R. and Aggarwal, V. 2021. Indoor air quality improvement in Covid-19 pandemic: Review. Sustain. Cities Soc., 70: 102942. DOI: 10.1016/j.scs.2021.102942.
  7. Pi, T., Wu, H. and Li, X. 2019. Does air pollution affect health and medical insurance cost in the elderly: An empirical evidence from China. Sustain., 11(6): 1526. DOI: 10.3390/su11061526.
  8. Power, A.L., Tennant, R.K., Jones, R.T., Tang, Y., Du, J., Worsley, A.T. and Love, J. 2018. Monitoring impacts of urbanisation and industrialisation on air quality in the Anthropocene using urban pond sediments. Frontiers Earth Sci., 6. DOI: 10.3389/feart.2018.00131.
  9. Mo, X., Zhang, L., Li, H. and Qu, Z. 2019. A novel air quality early-warning system based on artificial intelligence. Int. J. Env. Res. Public Health. 16(19): 3505. DOI: 10.3390/ijerph16193505.
  10. Bai, L., Wang, J., Ma, X. and Lu, H. 2018. Air pollution forecasts: An overview. Int. J. Env. Res. Public Health. 15(4): 780. DOI: 10.3390/ijerph15040 780.
  11. Jerrett, M., Arain, A., Kanaroglou, P., Beckerman, B., Potoglou, D., Sahsuvaroglu, T., Morrison, J. and Giovis, C. 2005. A review and evaluation of intra-urban air pollution exposure models. J. Exposure Sci. Env. Epidemiol., 15(2): 185–204. DOI: 10.1038 /sj.jea.7500388.
  12. Rahimi, A. 2017. Short-term prediction of NO2and NOx concentrations using multilayer perceptron neural network: a case study of Tabriz, Iran. Ecol. Processes. 6: 4. DOI: 10.1186/s13717-016-0069-x.
  13. Mishra, D., Goyal, P. and Upadhyay, A. 2015. Artificial intelligence-based approach to forecast PM2.5during haze episodes: A case study of Delhi, India. Atmos. Env., 102: 239–248. DOI: 10.1016/j.atmos env.2014. 11.050.
  14. Soh, P.W., Chang, J.W. and Huang, J.W. 2018. Adaptive deep learning-based air quality prediction model using the most relevant spatial-temporal relations. IEEE Access. 6: 38186–38199. DOI: 10.11 09/ACCESS. 2018.28-49820.
  15. Van, N.H., Thanh, P.V., Tran, D.N. and Tran, D.T. 2022. A new model of air quality prediction using lightweight machine learning. Int.J. Env. Sci. Tech., 20(3): 2983-2994. DOI: 10.1007/s13762-022-04185-w.