Journal of Advances in Environmental Health Research

Journal of Advances in Environmental Health Research

Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF

Document Type : Original Article

Authors
Ali Mohammadi Bardshahi 1
Nematollah Jaafarzadeh 2
Tayebeh Tayebeh 1
Fazel Amiri 1
1 Department of Environment, Bushehr Branch, Islamic Azad University, Bushehr, Iran
2 Environmental Technologies Research Center, Medical Basic Sciences Research Institute, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
10.34172/jaehr.1387
Abstract
Background: Exposure to air pollutants, such as PM2.5 is recognized as a significant health risk, contributing to the development of various diseases, and increased risk of premature mortality.
Methods: Multilayer perceptron (MLP) and radial basis function (RBF) neural networks, were used to predict the hourly concentration of PM2.5 in Isfahan, Iran. The MLP model was designed with five input variables, including PM2.5 concentration and weather characteristics, ten hidden layers, and a single output layer. The dataset was divided into three subsets: 70% for training, 15% for testing, and 15% for validation.
Results: The results showed that the average concentration of PM2.5 was 26.5 μg/m3. The root mean square error (RMSE) was estimated as 6.49 μg/m3. Increasing the input data resulted in a slight reduction in network error, with the RBF model, utilizing 1450 inputs and an RMSE of 6.47, achieving the same accuracy as the MLP model with 10 inputs.
Conclusion: Given that the PM2.5 concentration estimates from the RBF and MLP models deviated by less than 23 and 25%, respectively, compared to the observed concentrations, both MLP and RBF can be regarded as reliable tools for predicting PM2.5 levels.
Keywords
Artificial neural network
RBF
MLP
Particulate matter
Isfahan

Subjects

  1. Zeng J, Liu T, Feiock R, Li F. The impacts of China’s provincial energy policies on major air pollutants: a spatial econometric analysis. Energy Policy. 2019;132:392-403. doi: 1016/j.enpol.2019.05.052.
  2. Li P, Lin Z, Du H, Feng T, Zuo J. Do environmental taxes reduce air pollution? Evidence from fossil-fuel power plants in China. J Environ Manage. 2021;295:113112. doi: 1016/j.jenvman.2021.113112.
  3. Hopke PK, Croft DP, Zhang W, Lin S, Masiol M, Squizzato S, et al. Changes in the hospitalization and ED visit rates for respiratory diseases associated with source-specific PM5 in New York State from 2005 to 2016. Environ Res. 2020;181:108912. doi: 10.1016/j.envres.2019.108912.
  4. Wang W, Sun X, Zhang M. Does the central environmental inspection effectively improve air pollution?-An empirical study of 290 prefecture-level cities in China. J Environ Manage. 2021;286:112274. doi: 1016/j.jenvman.2021.112274.
  5. Chen B, Song Z, Pan F, Huang Y. Obtaining vertical distribution of PM2.5 from CALIOP data and machine learning algorithms. Sci Total Environ. 2022;805:150338. doi: 1016/j.scitotenv.2021.150338.
  6. Hajizadeh Y, Jafari N, Fanaei F, Ghanbari R, Mohammadi A, Behnami A, et al. Spatial patterns and temporal variations of traffic-related air pollutants and estimating its health effects in Isfahan city, Iran. J Environ Health Sci Eng. 2021;19(1):781-91. doi: 1007/s40201-021-00645-6.
  7. Mainka A, Fantke P. Preschool children health impacts from indoor exposure to PM2.5 and metals. Environ Int. 2022;160:107062. doi: 1016/j.envint.2021.107062.
  8. Herman DA, Wingen LM, Johnson RM, Keebaugh AJ, Renusch SR, Hasen I, et al. Seasonal effects of ambient PM2.5 on the cardiovascular system of hyperlipidemic mice. J Air Waste Manag Assoc. 2020;70(3):307-23. doi: 1080/10962247.2020.1717674.
  9. Olaniyan T, Pinault L, Li C, van Donkelaar A, Meng J, Martin RV, et al. Ambient air pollution and the risk of acute myocardial infarction and stroke: a national cohort study. Environ Res. 2022;204(Pt A):111975. doi: 1016/j.envres.2021.111975.
  10. Samal KK, Babu KS, Das SK. Multi-directional temporal convolutional artificial neural network for PM2.5 forecasting with missing values: a deep learning approach. Urban Clim. 2021;36:100800. doi: 1016/j.uclim.2021.100800.
  11. Liu H, Dong S. A novel hybrid ensemble model for hourly PM2.5 forecasting using multiple neural networks: a case study in China. Air Qual Atmos Health. 2020;13(12):1411-20. doi: 1007/s11869-020-00895-7.
  12. Yin PY, Yen AY, Chao SE, Day RF, Bhanu B. A machine learning-based ensemble framework for forecasting PM2.5 concentrations in Puli, Taiwan. Appl Sci. 2022;12(5):2484. doi: 3390/app12052484.
  13. Chen YC, Li DC. Selection of key features for PM2.5 prediction using a wavelet model and RBF-LSTM. Appl Intell (Dordr). 2021;51(4):2534-55. doi: 1007/s10489-020-02031-5.
  14. Menares C, Perez P, Parraguez S, Fleming ZL. Forecasting PM2.5 levels in Santiago de Chile using deep learning neural networks. Urban Clim. 2021;38:100906. doi: 1016/j.uclim.2021.100906.
  15. Bai Y, Zeng B, Li C, Zhang J. An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting. Chemosphere. 2019;222:286-94. doi: 1016/j.chemosphere.2019.01.121.
  16. Champati BB, Padhiari BM, Ray A, Jena S, Sahoo A, Mohanty S, et al. Implementation of multilayer perceptron (MLP) and radial basis function (RBF) neural networks for predicting shatavarin IV content in Asparagus racemosus Ind Crops Prod. 2023;191:115968. doi: 10.1016/j.indcrop.2022.115968.
  17. Alimissis A, Philippopoulos K, Tzanis CG, Deligiorgi D. Spatial estimation of urban air pollution with the use of artificial neural network models. Atmos Environ. 2018;191:205-13. doi: 1016/j.atmosenv.2018.07.058.
  18. Ismail A, Kumar N. AI in global health: the view from the front lines. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. New York, NY: Association for Computing Machinery; 2021. p. 1-21. doi: 1145/3411764.3445130.
  19. Khoshand A, Shahbazi Sehrani M, Kamalan H, Bodaghpour S. Prediction of ground-level air pollution using artificial neural network in Tehran. Anthropog Pollut. 2017;1(1):61-7.
  20. Feng R, Gao H, Luo K, Fan JR. Analysis and accurate prediction of ambient PM2.5 in China using multi-layer perceptron. Atmos Environ. 2020;232:117534. doi: 1016/j.atmosenv.2020.117534.
  21. Wang H, Wang P, Zhang Y. PM2.5 prediction based on feature extraction with LASSO and multilayer perceptron. In: Second International Conference on Sensors and Information Technology (ICSI 2022). Vol 12248. SPIE; 2022. p. 166-74. doi: 1117/12.2637473.
  22. de Mattos Neto PS, Firmino PR, Siqueira H, de Souza Tadano Y, Alves TA, de Oliveira JF, et al. Neural-based ensembles for particulate matter forecasting. IEEE Access. 2021;9:14470-90. doi: 1109/access.2021.3050437.
  23. Asadollahfardi G, Madinejad M, Homayoun Aria SH, Motamadi V. Predicting particulate matter (PM2.5) concentrations in the air of Shahr-e Ray city, Iran, by using an artificial neural network. Environ Qual Manag. 2016;25(4):71-83. doi: 1002/tqem.21464.
  24. Pham BT, Nguyen MD, Bui K-TT, Prakash I, Chapi K, Bui DT. A novel artificial intelligence approach based on multi-layer perceptron neural network and biogeography-based optimization for predicting coefficient of consolidation of soil. Catena (Amst). 2019;173:302-11. doi: 1016/j.catena.2018.10.004.
  25. Ismailov VE. On the approximation by neural networks with bounded number of neurons in hidden layers. J Math Anal Appl. 2014;417(2):963-9. doi: 1016/j.jmaa.2014.03.092.
  26. Amanollahi J, Ausati S. PM2.5 concentration forecasting using ANFIS, EEMD-GRNN, MLP, and MLR models: a case study of Tehran, Iran. Air Qual Atmos Health. 2020;13(2):161-71. doi: 1007/s11869-019-00779-5.
  27. Phaisangittisagul E. An analysis of the regularization between L2 and dropout in single hidden layer neural network. In: 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS). Bangkok, Thailand: IEEE; 2016. p. 174-9. doi: 1109/isms.2016.14.
  28. Rodríguez-Rajo FJ, Astray G, Ferreiro-Lage JA, Aira MJ, Jato-Rodriguez MV, Mejuto JC. Evaluation of atmospheric Poaceae pollen concentration using a neural network applied to a coastal Atlantic climate region. Neural Netw. 2010;23(3):419-25. doi: 1016/j.neunet.2009.06.006.
  29. Rezaei F, Jafari S, Hemmati-Sarapardeh A, Mohammadi AH. Modeling of gas viscosity at high pressure-high temperature conditions: integrating radial basis function neural network with evolutionary algorithms. J Pet Sci Eng. 2022;208(Pt A):109328. doi: 1016/j.petrol.2021.109328.
  30. Hashemi Fath A, Madanifar F, Abbasi M. Implementation of multilayer perceptron (MLP) and radial basis function (RBF) neural networks to predict solution gas-oil ratio of crude oil systems. Petroleum. 2020;6(1):80-91. doi: 1016/j.petlm.2018.12.002.
  31. Haiming Z, Xiaoxiao S. Study on prediction of atmospheric PM2.5 based on RBF neural network. In: 2013 Fourth International Conference on Digital Manufacturing & Automation. Shinan, China: IEEE; 2013. p. 1287-9. doi: 1109/icdma.2013.306.
  32. Sudheer KP, Jain SK. Radial basis function neural network for modeling rating curves. J Hydrol Eng. 2003;8(3):161-4. doi: 1061/(asce)1084-0699(2003)8:3(161).
  33. Madhiarasan M. Accurate prediction of different forecast horizons wind speed using a recursive radial basis function neural network. Prot Control Mod Power Syst. 2020;5(3):1-9. doi: 1186/s41601-020-00166-8.
  34. Bai Y, Li Y, Zeng B, Li C, Zhang J. Hourly PM2.5 concentration forecast using stacked autoencoder model with emphasis on seasonality. J Clean Prod. 2019;224:739-50. doi: 1016/j.jclepro.2019.03.253.
  35. Zhou G, Liu R, Zhang Z, Yang C, Ding H. Optimization of diesel engine dual-variable geometry turbocharger regulated two-stage turbocharging system based on radial basis function neural network-quantum genetic algorithm. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects. 2025;47(1):1910-26. doi: 1080/15567036.2020.1837299.
  36. Vafaei A, Ghaedi AM, Avazzadeh Z, Kiarostami V, Agarwal S, Gupta VK. Removal of hydrochlorothiazide from molecular liquids using carbon nanotubes: radial basis function neural network modeling and culture algorithm optimization. J Mol Liq. 2021;324:114766. doi: 1016/j.molliq.2020.114766.
  37. Vakili M, Sabbagh-Yazdi SR, Kalhor K, Khosrojerdi S. Using artificial neural networks for prediction of global solar radiation in Tehran considering particulate matter air pollution. Energy Procedia. 2015;74:1205-12. doi: 1016/j.egypro.2015.07.764.
  38. Park S, Kim M, Kim M, Namgung HG, Kim KT, Cho KH, et al. Predicting PM10 concentration in Seoul metropolitan subway stations using artificial neural network (ANN). J Hazard Mater. 2018;341:75-82. doi: 1016/j.jhazmat.2017.07.050.
  39. Ren M, Sun W, Chen S. Combining machine learning models through multiple data division methods for PM2.5 forecasting in Northern Xinjiang, China. Environ Monit Assess. 2021;193(8):476. doi: 1007/s10661-021-09233-5.
  40. Shanmugaprakash M, Sivakumar V. Development of experimental design approach and ANN-based models for determination of Cr(VI) ions uptake rate from aqueous solution onto the solid biodiesel waste residue. Bioresour Technol. 2013;148:550-9. doi: 1016/j.biortech.2013.08.149.
  41. Cheng Y, He KB, Du ZY, Zheng M, Duan FK, Ma YL. Humidity plays an important role in the PM2.5 pollution in Beijing. Environ Pollut. 2015;197:68-75. doi: 1016/j.envpol.2014.11.028.
  42. Kleine Deters J, Zalakeviciute R, Gonzalez M, Rybarczyk Y. Modeling PM2.5 urban pollution using machine learning and selected meteorological parameters. J Electr Comput Eng. 2017;2017(1):5106045. doi: 1155/2017/5106045.
  43. Trinh TT, Trinh TT, Le TT, Nguyen TDH, Tu BM. Temperature inversion and air pollution relationship, and its effects on human health in Hanoi city, Vietnam. Environ Geochem Health. 2019;41(2):929-37. doi: 1007/s10653-018-0190-0.
  44. Shao M, Xu X, Lu Y, Dai Q. Spatio-temporally differentiated impacts of temperature inversion on surface PM2.5 in eastern China. Sci Total Environ. 2023;855:158785. doi: 1016/j.scitotenv.2022.158785.
  45. Torkashvand J, Jonidi Jafari A, Hopke PK, Shahsavani A, Hadei M, Kermani M. Airborne particulate matter in Tehran’s ambient air. J Environ Health Sci Eng. 2021;19(1):1179-91. doi: 1007/s40201-020-00573-x.
  46. Li F, Yan J, Wei Y, Zeng J, Wang X, Chen X, et al. PM2.5-bound heavy metals from the major cities in China: Spatiotemporal distribution, fuzzy exposure assessment and health risk management. J Clean Prod. 2021;286:124967. doi: 1016/j.jclepro.2020.124967.
  47. Bandowe BA, Meusel H, Huang RJ, Ho K, Cao J, Hoffmann T, et al. PM2.5-bound oxygenated PAHs, nitro-PAHs and parent-PAHs from the atmosphere of a Chinese megacity: seasonal variation, sources and cancer risk assessment. Sci Total Environ. 2014;473-474:77-87. doi: 1016/j.scitotenv.2013.11.108.
  48. Shahbazi H, Hassani A, Hosseini V. Evaluation of Tehran clean air action plan using emission inventory approach. Urban Clim. 2019;27:446-56. doi: 1016/j.uclim.2019.01.002.
Journal of Advances in Environmental Health Research
Volume 13, Issue 2
Winter 2025
Pages 129-134