ABSTRACT
The main air pollutant all around the world is particulate matter PM10. This is particulate matter smaller than 10 microns. In the human body, harmful particles lead to serious health problems, causing chronic lung disease, asthma, bronchitis, and heart failure. Statistics for Bulgaria show that an average of 66-68% of mortality is due to exactly such cardiovascular disease. This paper applies the powerful Classification and Regression Tree (CART) method to analyze data about PM10 air pollution for the city of Smolyan. The modeling procedure found that depending on the number of observations, the obtained models approximate the actual data to a different degree. The study uses mean daily measurements for the period from 1 January 2010 to 27 April 2018. The obtained results show that the best model approximates the actual measured values of PM10 up to 87%. The selected best CART model is applied to forecast future pollution 3 days ahead.
- Pao-Wen and G., L. 2009. Simulation of the daily average PM10 concentrations at Ta-Liao with Box-Jenkins time series models and multivariate analysis. Atmospheric Environment 43, (Apr. 2009), 2104--2113. DOI= https://doi.org/10.1016/j.atmosenv.2009.01.055.Google Scholar
- Zheleva, I., Veleva, E., and Filipova, M. 2017. Analysis and modeling of daily air pollutants in the city of Ruse, Bulgaria. In International conference AMITANS (Albena, Bulgaria, June 21-26, 2017). AIP Conference Proceedings 1895, 030007--1-03000-10. DOI= https://doi.org/10.1063/1.5007366.Google Scholar
- Stoimenova, M. 2016. Stochastic modeling of problematic air pollution with particulate matter in the city of Pernik, Bulgaria. Ecologia Balkanica. 8, 2 (Dec. 2016), 33--41.Google Scholar
- Jaiswal, A., Samuel, C., and Kadabgaon, V. M. 2018. Statistical trend analysis and forecast modeling of air pollutants. Global Journal of Environmental Science and Management. 4, 4 (Nov. 2018), 427--438. DOI= https://www.doi.org/10.22034/gjesm.2018.04.004.Google Scholar
- Hung, C., Hung, C. N., and Lin, S. Y. 2014. Predicting time series using integration of moving Average and support vector regression. International Journal of Machine Learning and Computing. 4, 6 (Dec. 2014), 492--495. DOI= http://doi.org/10.7763/IJMLC.2014.V6.460Google ScholarCross Ref
- Parashar, H. J., Vijendra, S., and Vasudeva, N. 2012. An efficient classification approach for data Mining. International Journal of Machine Learning and Computing. 2, 4 (Aug. 2012), 446--448. DOI= http://doi.org/10.7763/IJMILC.2012.V2.164Google Scholar
- Ahani, I. K., Salari, M., and Shadman, A. 2019. Statistical models for multi-step-ahead forecasting of fine particulate matter in urban areas. Atmospheric Pollution Research. 10, 3 (May. 2019), 689--700. DOI= https://doi.org/10.1016/j.apr.2018.11.006.Google Scholar
- Biancofiore, F., Busilacchio, M., Verdecchia, M., Tomassetti, B., Aruffo, E., Bianco, S., Tommaso, S. Di., Colangeli, C., Rosatelli, G., and Carlo, P. Di. 2017. Recursive neural network model for analysis and forecast of PM10 and PM2.5. Atmospheric Pollution Research. 8, 4 (Jan. 2017), 652--659. DOI= https://doi.org/10.1016/j.apr.2016.12.014.Google ScholarCross Ref
- Aladag, C. H., Egrioglu, E., and Kadilar, C. 2009. Forecasting nonlinear time series with a hybrid methodology. Applied Mathematics Letters. 22, 9 (Sep. 2009), 1467--1470. DOI= https://doi.org/10.1016/j.aml.2009.02.006.Google ScholarCross Ref
- Bougoudis, I., Demertzis, K., and Iliadis, L. 2016. HISYCOL a hybrid computational intelligence system for combined machine learning: the case of air pollution modelling in Athens. Neural Computing and Applications. 27, 5 (Jul. 2016), 1191--1206. DOI= https://doi.org/10.1007/s00521-015-1927-7.Google ScholarDigital Library
- Zhang, H., Zhang, S., Wang, P., Qin, Y., and Wang, H. 2017. Forecasting of particulate matter time series using wavelet analysis and wavelet-ARMA/ARIMA model in Taiyuan, China. Journal of the Air & Waste Management Association. 67, 7 (Feb. 2017), 776--788. DOI= https://doi.org/10.1080/10962247.2017.1292968.Google ScholarCross Ref
- Choi, W., Paulson, S. E., Casmassi, J., and Winer, A. M. 2013. Evaluating meteorological comparability in air quality studies: Classification and regression trees for primary pollutants in California's South Coast Air Basin. Atmospheric Environment. 64 (Jan. 2013), 150--159. DOI= https://doi.org/10.1016/j.atmosenv.2012.09.049.Google Scholar
- Gocheva-Ilieva, S., Voynikova, D., Stoimenova, M., Ivanov, A., and Iliev, I. 2019. Regression trees modeling of time series for air pollution analysis and forecasting. Neural Computing and Applications. 31, 12 (Aug. 2019), 9023--9039. DOI= https://doi.org/10.1007/s00521-019-04432-1.Google ScholarCross Ref
- Roy, S. S., Pratyush, C., and Barna, C. 2018. Predicting ozone layer concentration using multivariate adaptive regression splines, random forest and classification and regression tree. Soft Computing Applications. SOFA 2016. Advances in Intelligent Systems and Computing 634, (Oct. 2017), 140--152. DOI= https://doi.org/10.1007/978-3-319-62524-9_11.Google Scholar
- Choubin, B., Abdolshahnejad, M., Moradi, E., Querol, X., Mosavi, A., Shamshirband, S., and Ghamisi, P. 2019. Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain. Science of the Total Environment. 701, 134474 (Jan. 2020). DOI= https://doi.org/10.1016/j.scitotenv.2019.134474.Google ScholarCross Ref
- Cohen, J. C. 1988. Statistical Power Analysis for the Behavioral Sciences. Routledge, New York.Google Scholar
- Directive 2008/50/EC of the European Parliament and of the Council of 21 May 2008 on ambient air quality and cleaner air for Europe. 2008. Official Journal of the European Union, L 152/1.Google Scholar
- Morgan, J. N., and Sonquist, J. A. 1963. Problems in an analysis of survey data and a proposal. Journal of the American Statistical Association. 58, 302 (Jun. 1963), 415--434. DOI= https://www.doi.org/10.2307/2283276Google ScholarCross Ref
- Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. 1984. Classification and regression trees. Wadsworth Advanced Books and Software, Belmont, Canada.Google Scholar
- Wu, X., and Kumar, V. 2009. The Top Ten Algorithms in Data Mining. Chapman & Hall / CRC, Boca Raton.Google Scholar
- Steinberg, D., and Golovnya, M. 2007. CART 6.0 User's Guide. Salford Systems, San Diego, CA.Google Scholar
Index Terms
- PM10 Prediction Using CART Method Depending on the Number of Observations
Recommendations
The Application of Machine Learning Models in the Prediction of PM2.5/PM10 Concentration
ICCMB '21: Proceedings of the 2021 4th International Conference on Computers in Management and BusinessThe current world economy and science are in an era of rapid development, and Beijing is experiencing chronic air pollution. The air quality is important to the travel of people, development of enterprise and normal operation of traffic. PM2.5 and PM10 ...
Modeling of PM10 Air Pollution in Urban Environment Using MARS
Large-Scale Scientific ComputingAbstractIn the modern world, attention is increasingly drawn to the pressing problem of atmospheric air pollution, which is a serious threat to human health. Worldwide, China, India, Indonesia and some of the countries in Europe, including Bulgaria, are ...
Identification of regional atmospheric PM10 transport pathways using HYSPLIT, MM5-CMAQ and synoptic pressure pattern analysis
Air pollution in urban cites is caused not only by local emission sources but also significantly by regional atmospheric pollutant transport from surrounding areas. This study is to identify regional atmospheric PM"1"0 transport pathways through an ...
Comments