Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

PM2.5 concentration forecasting using ANFIS, EEMD-GRNN, MLP, and MLR models: a case study of Tehran, Iran

Abstract

Tehran, the capital city of Iran, is among the world’s most polluted cities. Tehran is exposed to different types of pollutants, one of which is the suspended particles of PM2.5. One of the steps that should be taken to reduce hazardous effects of this pollution on the health of society is timely prediction and announcement of its increased levels. Different methods can be used for predicting PM2.5 concentration. This study used a variety of models for predicting PM2.5 concentrations, including linear, nonlinear, and hybrid models. More specifically, the models which were used consisted of multiple linear regression, multi-layer perceptron (nonlinear model), and a combination of ensemble empirical mode decomposition and general regression neural network (EEMD-GRNN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) (hybrid of nonlinear models). The independent variables in the current study were air quality parameters, which were measured in reference to PM2.5, PM10, SO2, NO2, CO, and O3 and meteorological data which included average atmospheric pressure (AP), average maximum temperature (Max T), average minimum temperature (Min T), daily relative humidity level of the air (RH), daily total precipitation (TP), and daily wind speed (WS) in 2016 in Tehran. The results indicated that the ANFIS model exhibited the most accurate prediction in the training phase (R2 = 0.99, RMSE (root mean square error) = 0.4794 and MAE (mean absolute error) = 0.1305) and in the testing phase (R2 = 0.82, RMSE = 3.2979 and MAE = 2.1668). As it can be concluded, in comparison with a linear model, hybrid models are of higher precision in predicting PM2.5 concentration.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

References

  1. Alimissis A, Philippopoulos K, Tzanis CG, Deligiorgi D (2018) Spatial estimation of urban air pollution with the use of artificial neural network models. Atmos Environ 191:205–213

  2. Alizadeh-Choobari O, Ghafarian P, Adibi P (2016) Inter-annual variations and trends of the urban warming in Tehran. Atmos Res 170:176–185

  3. Amirkhani S, Nasirivatan S, Kasaeian AB, Hajinezhad A (2015) ANN and ANFIS models to predict the performance of solar chimney power plants. Renew Energy 83:597–607

  4. Ausati S, Amanollahi J (2016) Assessing the accuracy of ANFIS, EEMD-GRNN, PCR, and MLR models in predicting PM2.5. Atmos Environ 142:465–474

  5. Baker KR, Foley KM (2011) A nonlinear regression model estimating single source concentrations of primary and secondarily formed PM2.5. Atmos Environ 45:3758–3767

  6. Bench G (2004) Measurement of contemporary and fossil carbon contents of PM2.5 aerosols: results from turtleback dome, Yosemite National Park. Environ Sci Technol 38(8):2424–2427

  7. De Menezes Neto OL, Coutinho MM, Marengo JA, Capistrano VB (2017) The impact of a plume-rise scheme on earth system modeling: climatological effects of biomass aerosols on the surface temperature and energy budget of South America. Theor Appl Climatol 129(3–4):1035–1044

  8. Ding W, Zhang J, Leung Y (2016) Prediction of air pollutant concentration based on sparse response back-propagation training feedforward neural networks. Environ Sci Pollut Res 23:19481–19494

  9. Ghasemi A, Amanollahi J (2019) Integration of ANFIS model and forward selection method for air quality forecasting. Air Qual Atmos Health 12(1):59–72

  10. Gheyas I, Smith L (2009) A neural network approach to time series forecasting. Proceedings of the World Congress on Engineering Vol II

  11. Golchoubian H, Moayyedi G, Fazilati H (2012) Spectroscopic studies on Solvatochromism of mixed-chelate copper(II) complexes using MLR technique. Spectrochim Acta A Mol Biomol Spectrosc 85(1):25–30

  12. Guneri AF, Ertay T, Yücel A (2011) An approach based on ANFIS input selection and modeling for supplier selection problem. Expert Syst Appl 38(12):14907–14917

  13. Haywood J, Boucher O (2000) Estimates of the direct and indirect radiative forcing due to tropospheric aerosols: a review. Rev Geophys 38(4):513–543

  14. Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Royal Soc Math Phys Eng Sci 454:903–995

  15. Jang JSR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing: a computational, approach to learning and machine intelligence. IEEE Trans Autom Control 42(10), 1482-1484

  16. Jian S, Khare M (2010) Adaptive neuro-fuzzy modeling for prediction of ambient CO concentration at urban intersections and roadways. Air Quality, Atmosphere & Health. 3(4): 203-212.

  17. Kaboodvandpour S, Amanollahi J, Qhavami S, Mohammadi B (2015) Assessing the accuracy of multiple regressions, ANFIS, and ANN models in predicting dust storm occurrences in Sanandaj, Iran. Nat Hazards 78(2):879–893

  18. Kim SG, Yoon S (2019) Measuring the value of airborne particulate matter reduction in Seoul. Air Qual Atmos Health 12(5):549–560

  19. Legates DR, McCabe GJ (1999) Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water Resour Res 35(1):233–241

  20. Lelieveld J, Evans JS, Fnais M, Giannadaki D, Pozzer A (2015) The contribution of outdoor air pollution sources to pre-mature mortality on a global scale. Nature 525:367–371

  21. Leung MT, Daock H, Chen A (2000) Forecasting stock indices: a comparison of classification and level estimation models. Int J Forecast 16(2):173–190

  22. Liu X, Nie D, Zhang K, Wang Z, Li X, Shi Z, Wang Y, Huag L, Chen M, Ge X, Ying Q, Yu X, Liu X, Hu J (2019) Evaluation of particulate matter deposition in the human respiratory tract during winter in Nanjing using size and chemically resolved ambient measurements. Air Qual Atmos Health 12(5):529–538

  23. Lu CJ, Shao YE (2012) Forecasting computer products sales by integrating ensemble empirical mode decomposition and extreme learning machine. Math Probl Eng 15p

  24. Mashaly AF, Alazba AA (2016) MLP and MLR models for instantaneous thermal efficiency prediction of solar still under hyper-arid environment. Comput Electron Agric 122:146–155

  25. Matlab (2018) Anfis and the ANFIS Editor, Available at: http://www.mathworks.com/help/fuzzy/anfis-and-the-anfis-editor-gui.html

  26. McCulloch W, Pitts W (1943) Alogical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133

  27. Messikh N, Bousba S, Bougdah N (2017) The use of a multilayer perceptron (MLP) for modelling the phenol removal by emulsion liquid membrane. J Environ Chem Eng 5(4):3483–3489

  28. Ministry of Health and Medical Education 2012. Available online at http://www.behdasht.gov.ir/

  29. Mirzaei M, Amanollahi J, Tzanis CG (2019) Evaluation of linear , nonlinear, and hybrid models for predicting PM2.5 based on a GTWR model and MODIS AOD data. Air Qual Atmos Health 12(10):1215–1224

  30. Noori R, Hoshyaripour G, Ashrafi K, NadjarArrabi B (2010) Uncertainty analysis of developed ANN and ANFIS model in prediction of carbon monoxide daily concentration. Atmos Environ 44(4):476–482

  31. Nørgaard M, Ravn O, Poulsen NK, Hansen LK (2000) Neural networks for modelling and control of dynamic systems. Springer, United Kingdom

  32. Oh H-J, Kim J, Sohn J-R, Kim J (2019) Exposure to indoor-outdoor particulate matter and associated trace elements within childcare facilities. Air Qual Atmos Health 12(8):993–1001

  33. Pope CA, Burnett RT, Thurston GD, Thun MJ, Calle EE, Krewski D, Godleski JJ (2004) Cardiovascular mortality and long-term exposure to particulate air pollution: epidemiological evidence of general pathophysiological pathways of disease. Circulation 109(1):71–77

  34. Pouretedal HR, Damirri S, Shahsavan A (2018) Modification of RDX and HMX crystals in procedure of solvent/anti-solvent by statistical methods of Taguchi analysis design and MLR technique. Def Technol 14(1):59–63

  35. Sahu SK, Zhang H, Guo H, Hu J, Ying Q, Kota SK (2019) Helath risk associated with potential source regions of PM2.5 in Indian cities. Air Qual Atmos Health 12(3):327–340

  36. Shahbazi B, Rezazi B, Chehreh Chelgani S, Javad Koleini SM, Noaparast M (2013) Estimation of diameter and surface area flux of bubbles based on operational gas dispersion parameters by using regression and ANFIS. Int J Min Sci Technol 23(3):343–348

  37. Sun W, Zhang H, Palazoglu A, Singh A, Zhang W, Liu S (2013) Prediction of 24-hour-average PM2.5 concentrations using a hidden Markov model with different emission istributions in northern California. Sci Total Environ 443:93–103

  38. Thorkashvand AM, Ahmadi A, Layegh Nikravesh N (2017) Prediction of kiwifruit firmness using fruit mineral nutrient concentration by artificial neural network (ANN) and multiple linear regressions (MLR). J Integr Agric 16(7):1634–1644

  39. Tzanis C, Varotsos CA (2008) Tropospheric aerosol forcing of climate: a case study for the greater area of Greece. Int J Remote Sens 29(9):2507–2517

  40. Tzanis CG, Alimissis A, Philippopoulos K, Deligiorgi D (2019) Applying linear and nonlinear models for the estimation of particulate matter variability. Environ Pollut 246:89–98

  41. Ventura LMB, Pinto FO, Soares LM, Luna AS, Gioda A (2019) Forecast of daily PM2.5 concentrations applying artificial neural networks and Holt-Winters models. Air Qual Atmos Health 12(3):317–325

  42. Vlachogianni A, Kassomenos P, Karppinen A, Karakitsios S, Kukkonen J (2011) Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki. Sci Total Environ 409(8):1559–1571

  43. Wang J, Pan Y, Tian S, Chen X, Wang L, Wang Y (2016) Size distributions and health risks of particulate trace elements in rural areas in northeastern China. Atmos Res 168:191–204

  44. Wang Y, Wang J, Zhao G, Dong Y (2012) Application of residual modification approach in seasonal ARIMA for electricity demand forecasting: a case study of China. Energy Policy 48:284–294

  45. Wei M, Bai B, Sung AH, Liu Q, Wang J, Cather ME (2007) Predicting injection profiles using ANFIS. Inf Sci 177(20):4445–4461

  46. Willmott CJ, Matsuura K (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res 30:79–82

  47. Wu J, Xu Y, Yang Q, Han Z, Zhao D, Tang J (2013) Anumerical simulation of aerosols direct effects on trpopause height. Theor Appl Climatol 112(3–4):659–671

  48. Wu Z, Huang NE (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal 1:1–41

  49. Yadav AK, Sahoo SK, Dubey JS, Kumar AV, Pandey G, Tripathi RM (2019) Assessment of particulate matter, metals of toxicological concentration, and health risk around a mining area, Odisha, India. Air Qual Atmos Health 12(7):775–783

  50. Zendehboudi A, Li X, Wang B (2017) Utilization of ANN and ANFIS models to predict variable speed scroll compressor with vapor injection. Int J Refrig 74:475–487

  51. Zhou Q, Jiang H, Wang J, Zhou J (2014) A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network. Sci Total Environ 496:264–274

  52. Zhu J, Wu P, Chen H, Zhou L, Tao Z (2018) A hybrid forecasting approach to air quality time series based on endpoint condition and combined forecasting model. Int J Environ Res Public Health 15:1941–1960

Download references

Funding

The work was supported by the Iran National Science Foundation: INSF through grant agreement 95850153.

Author information

Correspondence to Jamil Amanollahi.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

ESM 1

(DOCX 305 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

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 13, 161–171 (2020). https://doi.org/10.1007/s11869-019-00779-5

Download citation

Keywords

  • Air quality
  • Meteorological data
  • Validation
  • Hybrid models
  • Linear model