Page 644 - NGTU_paper_withoutVideo

Modern Geomatics Technologies and Applications

5. Conclusion
In this research, by entering meteorological parameters, topographic status and intensity of air inversion in a time series,
the class or class of air pollution from particulate pollutants less than 2.5 microns using models created by base tree methods
(CART and C4.5). Then, using the tree-to-law conversion and the repetition rate of each parameter, the effective parameters and
factors were identified. In the next step, classification maps of particulate pollution less than 2.5 microns were produced, the
purpose of which is to prepare a classification, control and management map of this hazard. The use of C4.5 algorithms is
recommended due to its intuition, comprehensibility and low computational load. The results showed that the overall accuracy
and Kappa index in the decision tree model C4.5 show the highest numbers, which indicates that this model gives an accurate
estimate of the real model and can be used to classify the pollution class. The high accuracy of this method is due to the fact that
C4.5 goes back through the tree once it's been created and attempts to remove branches that do not help by replacing them with
leaf nodes. With these interpretations, the use of method C4.5 is recommended to classify the pollution of suspended particles
less than 2.5 microns.

6. Acknowledgments

The authors would like to acknowledge Iranian Meteorological Organization for providing meteorological data.

7. Reference

[1] Chang, Y.-S., et al., An LSTM-based aggregated model for air pollution forecasting. Atmospheric Pollution Research,
2020. 11, (8): pp. 1451-1463.
[2] Harishkumar, K., K. Yogesh, and I. Gad, Forecasting Air Pollution Particulate Matter (PM2.5) Using Machine Learning
Regression Models. Procedia Computer Science, 2020. 171: pp. 2057-2066.
[3] Vallero, D.A., Fundamentals of air pollution. (Academic press, Fifth edition, 2014).
[4] Duan, Y., et al., Effect of changes in season and temperature on cardiovascular mortality associated with nitrogen
dioxide air pollution in Shenzhen, China. Science of The Total Environment, 2019. 697: pp. 134051.
[5] Elangasinghe, M.A., et al., Development of an ANN–based air pollution forecasting system with explicit knowledge
through sensitivity analysis. Atmospheric pollution research, 2014. 5, (4): pp. 696-708.
[6] Kleine Deters, J., et al., Modeling PM2.5 urban pollution using machine learning and selected meteorological
parameters. Journal of Electrical and Computer Engineering, 2017.
[7] Wei, D., Predicting air pollution level in a specific city. (Stanford Publication, First edition, 2014).
[8] Corani, G. and M. Scanagatta, Air pollution prediction via multi-label classification. Environmental modelling &
software, 2016. 80: pp. 259-264.
[9] http://weather.uwyo.edu/upperair/sounding.html.
[10] Chilès, J.-P. and N. Desassis, Fifty years of kriging, in Handbook of mathematical geosciences. 2018, Springer, Cham.
pp. 589-612.
[11] Feng, X., S. Wei, and S. Wang, Temperature inversions in the atmospheric boundary layer and lower troposphere over
the Sichuan Basin, China: Climatology and impacts on air pollution. Science of The Total Environment, 2020: pp.
138579.
[12] Bahari, R., R. Abaspour, and P. Pahlavani, Zoning of Particulate Matters (PM) pollution using local statistical models
in GIS (Case Study: tehran Metropolisies). Journal of Geomatics Science and Technology, 2016. 5, (3): pp. 165-174.
[13] Bourne, S.M., A climate perspective of observed and modeled surface-based temperature inversions in Alaska. 2008,
University of Alaska Fairbanks.
[14] EPA, Validation of Inversion Strength Estimation Method. Technical Report, Environment Protection Authority,
Sydney., 2014.
[15] Delavar, M.R., et al., A novel method for improving air pollution prediction based on machine learning approaches: a
case study applied to the capital city of Tehran. ISPRS International Journal of Geo-Information, 2019. 8, (2): pp. 99.
[16] Acharya, D., et al., Application of adaptive Savitzky–Golay filter for EEG signal processing. Perspectives in science,
2016. 8: pp. 677-679.
[17] Babu, K.M., Beulah, J.R., Air Quality Prediction based on Supervised Machine Learning Methods. International Journal
of Innovative Technology and Exploring Engineering (IJITEE), 2019. 8, (9): pp. 206-212.
[18] Carletta, J., Assessing agreement on classification tasks: the kappa statistic. arXiv preprint cmp-lg/9602004, 1996.
[19] Breiman, L., et al., Classification and regression trees. Belmont, CA: Wadsworth. International Group, 1984. 432: pp.
151-166.

8