Assessment of Machine Learning Algorithms in Short-term Forecasting of PM10 and PM2.5 Concentrations in Selected Polish Agglomerations

被引:35
作者
Czernecki, Bartosz [1 ]
Marosz, Michal [2 ,3 ]
Jedruszkiewicz, Joanna [4 ]
机构
[1] Adam Mickiewicz Univ, Dept Meteorol & Climatol, Poznan, Poland
[2] Natl Res Inst, Inst Meteorol & Water Management, Warsaw, Poland
[3] Univ Gdansk, Fac Oceanog & Geog, Gdansk, Poland
[4] Pedag Univ Cracow, Inst Geog, Krakow, Poland
关键词
PM10; PM2.5; Air quality; Machine learning; Short-term forecasting; PARTICULATE MATTER PM2.5; AMBIENT PM2.5; HUMAN HEALTH; MORTALITY; IMPACT; PERFORMANCE; POLLUTION; AIR;
D O I
10.4209/aaqr.200586
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Air pollution continues to have a significant impact on Europeans living in urban areas, and episodes of elevated PMx are responsible for a large number of premature deaths (mostly due to heart disease and stroke) each year. According to the annual EEA reports, Poland is one of the most polluted countries in Europe, experiencing high PMx concentrations during winter that mostly result from large emissions and unfavourable weather conditions in combination with environmental features. Thus, in addition to implementing municipal mitigation strategies, alerting residents to pollution episodes through accurate PMx forecasting is necessary. This research aimed to assess the feasibility of short-term PMx forecasting via machine learning (ML) and the subsequent identification of the primary meteorological covariates. The data comprised 10 years of hourly winter PM10 and PM2.5 concentrations measured at 11 urban air quality monitoring stations, including background, traffic, and industrial sites, in four large Polish agglomerations, viz., Poznan, Krakow, Lodz, and Gdansk, which cover areas with high population density and diverse environments that extend from the Baltic Sea coast (Tricity) through the lowlands (Poznan and Lodz) to the highlands (Krakow). We tested four ML models: AIC-based stepwise regression, two tree-based algorithms (random forests and XGBoost), and neural networks. Employing analysis and cross-validation, we found that XGBoost performed the best, followed by random forests and neural networks, and stepwise regression performed the worst. This ranking was apparent in the threshold exceedance values of the binary forecasts obtained via regression. Overall, our results confirm the high applicability of ML to short-term air quality prediction with the perfect prog approach.
引用
收藏
页数:18
相关论文
共 47 条
[31]   Feature Selection with the Boruta Package [J].
Kursa, Miron B. ;
Rudnicki, Witold R. .
JOURNAL OF STATISTICAL SOFTWARE, 2010, 36 (11) :1-13
[32]   A Forecast Evaluation of Planetary Boundary Layer Height Over the Ocean [J].
Lavers, David A. ;
Beljaars, Anton ;
Richardson, David S. ;
Rodwell, Mark J. ;
Pappenberger, Florian .
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, 2019, 124 (09) :4975-4984
[33]   Meteorological pattern analysis assisted daily PM2.5 grades prediction using SVM optimized by PSO algorithm [J].
Liu, Wei ;
Guo, Geng ;
Chen, Fuji ;
Chen, Yihui .
ATMOSPHERIC POLLUTION RESEARCH, 2019, 10 (05) :1482-1491
[34]   Systematic review and meta-analysis of the adverse health effects of ambient PM2.5 and PM10 pollution in the Chinese population [J].
Lu, Feng ;
Xu, Dongqun ;
Cheng, Yibin ;
Dong, Shaoxia ;
Guo, Chao ;
Jiang, Xue ;
Zheng, Xiaoying .
ENVIRONMENTAL RESEARCH, 2015, 136 :196-204
[35]   Bias Correction, Quantile Mapping, and Downscaling: Revisiting the Inflation Issue [J].
Maraun, Douglas .
JOURNAL OF CLIMATE, 2013, 26 (06) :2137-2143
[36]   Source attribution of urban smog episodes caused by coal combustion [J].
Mira-Salama, D. ;
Gruening, C. ;
Jensen, N. R. ;
Cavalli, P. ;
Putaud, J. -P. ;
Larsen, B. R. ;
Raes, F. ;
Coe, H. .
ATMOSPHERIC RESEARCH, 2008, 88 (3-4) :294-304
[37]   Distribution of particulate matter and tissue remodeling in the human lung [J].
Pinkerton, KE ;
Green, FHY ;
Saiki, C ;
Vallyathan, V ;
Plopper, CG ;
Gopal, V ;
Hung, D ;
Bahne, EB ;
Lin, SS ;
Ménache, MG ;
Schenker, MB .
ENVIRONMENTAL HEALTH PERSPECTIVES, 2000, 108 (11) :1063-1069
[38]   Effects of particulate matter (PM10, PM2.5 and PM1) on the cardiovascular system [J].
Polichetti, Giuliano ;
Cocco, Stefania ;
Spinali, Alessandra ;
Trimarco, Valentina ;
Nunziata, Alfredo .
TOXICOLOGY, 2009, 261 (1-2) :1-8
[39]  
RIEDMILLER M, 1993, 1993 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, P586, DOI 10.1109/ICNN.1993.298623
[40]  
Riedmiller M., 1994, A Implementation Details