WP6 – Stage 1 – AQI modeling and prediction

Planned activities during stage 1

Results achieved during stage 1

• Under this work package, empirical research has been conducted on modeling, analysis and forecasting of air pollution by applying appropriate statistical methods, according to data collected from publicly available databases. Comparisons of many methods for predicting air pollution in different types of input data groups have been made and a selection of adequate methods has been made. A family of new hybrid methods for creating statistical models with increased predictive properties for air purity has been created (and tested), applicable for short-term future predicts (in real time) for the different classification groups of settlements, with simulations and tests with real data. Evaluation, validation and comparison of the results of the conducted empirical research were performed, and appropriate groups of statistical methods were determined depending on the classifications of the settlements.
• The results achieved in this work package are presented in accepted or sent for publication scientific publications, as follows:
• In magazines with impact factor/rank – 1 publication.

  [6.1]

  S. Gocheva-Ilieva, A. Ivanov, M. Stoimenova-Minova. Prediction of Daily Mean PM10 Concentrations Using Random Forest, CART Ensemble and Bagging Stacked by MARS. Sustainability, 2022, 14, 798. еISSN: 2071-1050. https://www.mdpi.com/2071-1050/14/2/798/pdf ; https://www.scopus.com/record/display.uri?eid=2-s2.0-85122754869&origin=resultslist&sort=plf-f&src=s&st1=%22Prediction+of+Daily+Mean+PM10+Concentrations+Using+Random+Forest%2cCART+Ensemble+and+Bagging+Stacked+by+MARS%22&sid=8960c12b59da5c001d45e58deff20751&sot=b&sdt=b&sl=124&s=TITLE-ABS-KEY%28%22Prediction+of+Daily+Mean+PM10+Concentrations+Using+Random+Forest%2c+CART+Ensemble+and+Bagging+Stacked+by+MARS%22%29&relpos=0&citeCnt=0&searchTerm= ; https://www.webofscience.com/wos/woscc/full-record/WOS:000750563400001 ; https://jcr.clarivate.com/jcr-jp/journal-profile?journal=SUSTAINABILITY-BASEL&year=2020&fromPage=%2Fjcr%2Fhome ; https://www.scimagojr.com/journalsearch.php?q=21100240100&tip=sid&clean=0

• In papers of conferences, refereed in WoS/Scopus – 5 publications.

  [6.2]	M. P. Stoimenova-Minova, S. G. Gocheva-Ilieva, A. V. Ivanov. 2020. “PM10 Prediction Using CART Method Depending on the Number of Observations”. Proc. of the International Conference on Mathematics and Statistics (ICoMS 2020), ACM International Conference Proceeding Series (ICPS), pp. 65-70. 21-23 June, Paris, France. (virtual event). ISBN: 978-1-4503-7541-2. Scopus, SJR2020=0,182. https://doi.org/10.1145/3409915.3409919 ; https://dl.acm.org/doi/abs/10.1145/3409915.3409919 ; https://www.scimagojr.com/journalsearch.php?q=11600154611&tip=sid&clean=0
  [6.3]	А. Ivanov, S. Gocheva-Ilieva, M. Stoimenova-Minova. 2021. “Random forest regression for statistical modeling and forecasting of PM10”. Proc. of the 13th International Conference on Application of Mathematics in Technical and Natural Sciences (AMiTaNS’21), АIP Conference Proceedings. 24–29 June 2021, Albena, Bulgaria. (hybrid event). (accepted and sent for printing; to be referenced and indexed in WoS; Scopus, SJR2020=0,177) http://2021.eac4amitans.eu/resources/amitansabsbook.pdf ; https://www.webofscience.com/wos/woscc/summary/f63ea692-77c0-499f-84f1-7583399ceacb-1ffebefa/relevance/1 ; https://www.scopus.com/results/results.uri?sort=plf-f&src=s&st1=AMiTaNS&sid=b9c4bb73c362d676794f8a2b44ee7eab&sot=b&sdt=b&sl=13&s=CONF%28AMiTaNS%29&origin=searchbasic&editSaveSearch=&yearFrom=Before+1960&yearTo=Present
  [6.4]	S. Gocheva-Ilieva, A. Ivanov, M. Stoimenova-Minova. 2020. “Prediction of PM10 air pollution using random forests with ARIMA error correction models”. Proc. of the 19th International Conference on Applied Mathematics (APLIMAT 2020), pp. 537–544. 4-6 February 2020, Bratislava, Slovakia. code 158284. POD Publ: Curran Associates, Inc. ISBN: 9781713807964. Scopus https://www.proceedings.com/content/053/053722webtoc.pdf ; https://www.researchgate.net/publication/357702606_PREDICTION_OF_PM10_AIR_POLLUTION_USING_RANDOM_FORESTS_AND_ARIMA_ERROR_CORRECTION_MODELS_APLIMAT_2020 ; https://www.scopus.com/record/display.uri?eid=2-s2.0-85082395600&origin=resultslist&sort=plf-f
  [6.5]	A. Ivanov, S. Gocheva-Ilieva, M. Stoimenova. 2020. “Hybrid boosted trees and regularized regression for studying ground ozone and PM10 concentrations”. Proc. of the 12th International Conference on Application of Mathematics in Technical and Natural Sciences (AMiTaNS’20), AIP Conference Proceedings. 24–29 June 2020, Albena, Bulgaria. (virtual event) https://aip.scitation.org/toc/apc/2302/1 ; https://www.webofscience.com/wos/woscc/full-record/WOS:000636887700026 ; https://www.scopus.com/record/display.uri?eid=2-s2.0-85097818806&origin=resultslist&sort=plf-f&src=s&st1=Hybrid+boosted+trees+and+regularized+regression+for+studying+ground+ozone+and+PM10+concentrations&sid=0a4db146eb98bcec944a307fb2046908&sot=b&sdt=b&sl=104&s=TITLE%28Hybrid+boosted+trees+and+regularized+regression+for+studying+ground+ozone+and+PM10+concentrations%29&relpos=0&citeCnt=0&searchTerm=
  [6.6]	J. Zhao, F. He, Z. Ji, I. Ganchev. 2021. “PM2.5 Prediction Based on the Combined EMD-LSTM Model”. Proc. of the 2021 International Conference on Computational Science and Computational Intelligence (CSCI'21), Pp. x1-x3, 15-17 December, Las Vegas, USA. (hybrid event). (accepted and sent for printing; to be referenced and indexed in Scopus, SJR2020=0,112) https://american-cse.org/static/Book-of-abstracts_CSCI21.pdf ; https://www.scopus.com/results/results.uri?sort=plf-f&src=s&st1=%22International+Conference+on+Computational+Science+and+Computational+Intelligence%22&sid=9a754bc368934cc62761255a88514324&sot=b&sdt=b&sl=88&s=CONF%28%22International+Conference+on+Computational+Science+and+Computational+Intelligence%22%29&origin=searchbasic&editSaveSearch=&yearFrom=Before+1960&yearTo=Present ; https://www.scimagojr.com/journalsearch.php?q=21100958064&tip=sid&clean=0