Prediction of daily PM2.5 concentration using support vector training combination (SVM)  - adaptive and principal component analysis (PCA)

Zarei, Amir; Zarei, Sirvan; Kakapor, Vahid; Vazeri, Mohamad  Hossein; Mohammadi, Eqbal; Aghighi, Hossein

doi:10.22038/jreh.2023.65531.1516

Document Type : Research article

Authors

¹ Water Engineering, Isfahan University of Technology

² Department of Health, Safety and Environment (HSE), School of Public Health and Safety, Workplace Health Promotion Research Center (WHPRC),Shahid Beheshti University of Medical Scienses,Tehran,Iran

³ MSc,Department of Natural Resources Engineering, Faculty of Natural Resources, Isfahan University of Technology, Isfahan, Iran

⁴ PhD,Assistant Professor, Department of Health, Safety and Environment (HSE), Workplace Health Promotion Research Center,School of Public Health and Safety,Shahid Beheshti University of Medical Scienses,Tehran,Iran

⁵ Ph.D Student, Department of GIS &amp; RS, Facuity of Earth sciences, Shahid Beheshti University,Tehran,Iran

⁶ Assistant Prof., Research Center of Remote Sensing and GIS, Shahid Beheshti University, Tehran

https://doi.org/10.22038/jreh.2023.65531.1516

Abstract

Background and Purpose: Air quality control is an inevitable issue at the forefront of national concerns. The aim of this study was to predict the daily concentration of PM2.5.
Materials and methods: According to the objective, the type of research can be considered practical, and the statistical population of the research includes meteorological and pollution measuring stations within the 22 districts of Tehran. However, the statistical sample (synoptic geophysical station and Tarbiat Modares measuring station) was selected using a non-random sampling method. The desired statistical year for the study included the daily data from the selected stations for one year. Eleven input variables were used, which included meteorological data from the geophysical synoptic station (maximum and minimum temperature, minimum and maximum relative humidity, rainfall, maximum wind speed, and wind direction) and pollution data of PM2.5 concentration from the Tarbiat Modares station (daily concentrations of PM2.5 and the previous day). The support vector machine (SVM) model was used for prediction in this step.
Results: The model was able to predict the daily concentration values of the PM2.5 pollutant for the upcoming days with a detection coefficient R² = 0.611 and RMSE = 10.87. In the second method, the support vector machine (SVM) model was combined with principal component analysis (PCA) to reduce the number of variables and perform modeling.
Conclusion: The results of this study show that the performance of the combined model is superior to the previous model, as the coefficient of determination R² increased to 0.65 and the error value decreased to 10.37 RMSE (root mean square error). This hybrid model (PCA-SVM) can assist city managers and decision-makers in controlling and reducing the amount of PM2.5 pollutants.

Keywords

References

1.Adams, K.J.Exercise Physiology: ACSM Resourse Manual for Guidelines for Exercise testing and prescription.6th ed": In:Ehrman JK,editor. Philadelphia.Lippincott Williams and Wilkin.2010; 73-4.

2. Arnesano M, Revel G M, Seri, F A. Tool for the optimal sensor placement to temperature monitoring in large sports spaces.Journal of Automation in Construction.2016; 68:223–234.

3. Bono R, Raffaella D, Marco P, Valeria R, Renato R. Benzene and formaldehyde in air of two winter Olympic venues of Torino.Journal of Environment International. 2010;36(3):269-275.

4. Boznar M, Lesjak M, Mlakar, P. 1993, A Neural Network-Based Method for ShortTerm Predictions of Ambient SO2 Concentrations in Highly Polluted Industrial Areas of Complex Terrain, Atmospheric Environment, Part B. Journal of Urban Atmosphere.1993; 27(2): 221- 230.

5. Chen ST, Yu PS. Pruning of support vector networks on flood forecasting. Journal of Hydrology. 2007;347(1-2):67-78.

6. Dimitris V, Kostas K, Jaakko K, Teemu R, Ari K, Mikko K.Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki. Journal of Science of The Total Environment.2011; 409(7):1266-1276.

7. Fernando H.J, Mammarella M, Grandoni, G, Fedele P, Di Marco R, Dimitrova R, Hyde P. Forecasting PM 10 in Metropolitan Areas: Efficacy of Neural Networks.Journal of Environmental Pollution. 2012; 163: 62- 67.

8. Gardner MW, Dorling SR. Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London.Journal of Atmospheric Environment. 1999;33(5):709–719.

9.Ghaemi, Z, Farnaghi M, Alimohammadi A. An Online Approach for SpatioTemporal Prediction of Air Pollution in Tehran Using Support Vector Machine. Journal of Geospatial Information Technology.2016; 3(4): 43- 63.

10. Gorai AK, Tuluri F, Tchounwou PB. A GIS based approach for assessing the association between air pollution and asthma in New York State, USA. Int J Environ Res Public Health. 2014;11(5):4845-69.

11. Kolehmainen M, Martikainen H, Hiltunen T, Ruuskanen, J. Forecasting Air Quality Parameters Using Hybrid Neural Network Modelling, Urban Air Quality: Measurement, Modelling and Management.2000; 277- 286.

12. Kumar A,Goyal P.Forecasting of Air Quality in Delhi Using Principal Component Regression Technique, Atmospheric Pollution Research.2011;2(4): 436- 444.

13. Lu WZ, Wang WJ. Potential assessment of the support vector machine method in forecasting ambient air pollutant trends. Journal of Chemosphere. 2005;59:693-701.

14. Mostafaeipour A, Zarezade M, Goudarzi H, Rezaei-Shouroki M, Qolipour M. Investigating the Factors on Using the Solar Water Heaters for Dry Arid Regions: A Case Study.Journal of Renewable and Sustainable Energy Reviews. 2017; 78: 157-166.

15. Moussiopoulos N, Sahm P, Kessler C. Numerical Simulation of Photochemical Smog Formation in Athens, Greece a Case Study.Journal of Atmospheric Environment.1995;29(24): 3619- 3632.

16. Niska H, Hiltunen T, Karppinen A, Ruuskanen J, Kolehmainen M. Evolving the Neural Network Model for Forecasting Air Pollution Time Series.Journal of Engineering Applications of Artificial Intelligence.2004; 17(2): 159 -167.

17. Noori R, Abdoli MA, Ameri- Ghasrodashti A, JaliliGhazizade M. Prediction of municipal solid waste generation with combination of support vector machine and principal component analysis: a case study of Mashhad. Journal of Environmental Progress & Sustainable Energy. 2009;28(2):249-58.

18. Noori R, Ashrafi K, Azhdarpour A. Comparison of ANN and PCA based multivariate linear regression applied to predict the daily average concentration of CO: a case study of Tehran. Journal of the Earth Space Physics. 2008;34(1):135-52.

19. Noori R, Hoshyaripour G, Ashrafi K, NadjarAraabi B. Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration. Journal of Atmosphric Environment. 2010;44(4):476,82.

20. Noori R, Karbassi A, Farokhnia A, Dehghani M. Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques. Environmental Engineering Science. 2009;26(10):1503-10.

21. Nunnari G, Dorling S, Schlink U, Cawley G, Foxall R, Chatterton T. Modelling SO2 concentration at a point with statistical approaches, Environmental Modelling & Software. 2004;19(10):887–905.

22. Nunnari G. Simplified Fuzzy Modelling of Pollutant Time Series, Neural Network World. 2000; 10(6): 983- 1000.

23. Osowski S. Forecasting of the daily meteorological pollution using wavelets and support vector machine.Journal of Engineering Applications of Artificial Intelligence. 2001;15(3):208-16.

24. Pelliccioni A, Tirabassi T. Air dispersion model and neural network: a new perspective for integrated models in the simulation of complex situations. Journal of Environmental Modelling & Software. 2006;21(4):539-46

25. Pérez P, Trier A, Reyes J. Prediction of PM 2.5 Concentrations Several Hours in Advance Using Neural Networks in Santiago, Chile.Journal of Atmospheric Environment. 2000; 34(8): 1189- 1196.

26. Qu Y, Liu Y, Nayak R, Li, M.Sustainable development of eco-industrial parks in China: effects of managers' environmental awareness on the relationships between practice and performance. Journal of Cleaner Production. 2015; 87:328-338

27. Sahoo M M, Patra K, Khatua K.Inference of Water Quality Index Using ANFIA and PCA.Journal of Aquatic Procedia. 2015; 4:1099 -1106.

28. Salazar-Ruiz E, Ordieres JB, Vergara EP, CapuzRizo SF. Development and comparative analysis of tropospheric ozone prediction models using linear and artificial intelligence-based models in Mexicali, Baja California (Mexico) and Calexico, California (US). Journal of Environmental Modelling & Software. 2008;23:1056- 69.

29. Schlkopf C, Smola A. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MA, USA, MIT Press Cambridge. 2018.

30. Singh K P, Gupta S, Rai P. Identifying Pollution Sources and Predicting Urban Air Quality Using Ensemble Learning Methods, Journal of Atmospheric Environment. 2013; 80: 426 437.

31. Statheropoulos M, Vassiliadis N, Pappa, A.Principal Component and Canonical Correlation Analysis for Examining Air Pollution and Meteorological Data.Journal of Atmospheric Environment. 1998; 32(6):1087-1095.

32. Suleiman A, Tight M R, Quinn A D. Assessment and prediction of the impact of road transport on ambient concentrations of particulate matter PM10. Journal of Transportation Research Part D. 2016; 49:301-312.

33. Williamsn B, Onsman A, Brown T. Exploratory Factor Analysis: A Five-Step Guide for Novices, Australasian Journal of Paramedicine. 2010;8(3):1-13.

34 Wei L, Geng G, Fuji C, Yihui C.Meteorological pattern analysis assisted daily PM 2.5 grades prediction using SVM optimized by PSO algorithm,Journal of Atmospheric Pollution Research, 2019;10(5): 1482-1491,

35. Wei-Zhen Lu, Wen-Jian Wang.Potential assessment of the â€œsupport vector machineâ€‌ method in forecasting ambient air pollutant trends.Journal of Chemosphere.2005;59(5):693-701.

36. Yu PS, Chen ST, Chang IF. Support vector regression for real-time flood stage forecasting. Journal of Hydrology. 2006;328(3-4):704-16.

37. Zhang J, Wang C, Liu L, Guo H, Liu G, Li Y, Deng S.Investigation of Carbon Dioxide Emission in China by Primary Component Analysis.Journal of Science of The Total Environment. 2014; 472:239- 247.

Journal of Research in Environmental Health

Prediction of daily PM2.5 concentration using support vector training combination (SVM) - adaptive and principal component analysis (PCA)

References

References

Volume 9, Issue 1 - Serial Number 33
June 2023
Pages 108-121

Prediction of daily PM2.5 concentration using support vector training combination (SVM) - adaptive and principal component analysis (PCA)

References

References

Volume 9, Issue 1 - Serial Number 33June 2023Pages 108-121

Volume 9, Issue 1 - Serial Number 33
June 2023
Pages 108-121