A Traffic-Based Method to Predict and Map Urban Air Quality

被引:33
作者
Zalakeviciute, Rasa [1 ]
Bastidas, Marco [2 ]
Buenano, Adrian [2 ]
Rybarczyk, Yves [3 ]
机构
[1] Univ Las Amer, Grp Biodiversidad Medio Ambiente & Salud BIOMAS, Quito 170125, Ecuador
[2] Univ Las Amer, Fac Ingn & Ciencias Aplicadas, Quito 170125, Ecuador
[3] Dalarna Univ, Fac Data & Informat Sci, S-79188 Falun, Sweden
来源
APPLIED SCIENCES-BASEL | 2020年 / 10卷 / 06期
关键词
urban air quality; machine-learning-based models; pollution mapping; LAND-USE REGRESSION; LOW-COST; POLLUTION; EXPOSURE;
D O I
10.3390/app10062035
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
As global urbanization, industrialization, and motorization keep worsening air quality, a continuous rise in health problems is projected. Limited spatial resolution of the information on air quality inhibits full comprehension of urban population exposure. Therefore, we propose a method to predict urban air pollution from traffic by extracting data from Web-based applications (Google Traffic). We apply a machine learning approach by training a decision tree algorithm (C4.8) to predict the concentration of PM2.5 during the morning pollution peak from: (i) an interpolation (inverse distance weighting) of the value registered at the monitoring stations, (ii) traffic flow, and (iii) traffic flow + time of the day. The results show that the prediction from traffic outperforms the one provided by the monitoring network (average of 65.5% for the former vs. 57% for the latter). Adding the time of day increases the accuracy by an average of 6.5%. Considering the good accuracy on different days, the proposed method seems to be robust enough to create general models able to predict air pollution from traffic conditions. This affordable method, although beneficial for any city, is particularly relevant for low-income countries, because it offers an economically sustainable technique to address air quality issues faced by the developing world.
引用
收藏
页数:18
相关论文
共 40 条
[1]  
[Anonymous], 2014, 7 million premature deaths annually linked to air pollution, DOI [11/44679/index.htm, DOI 11/44679/INDEX.HTM]
[2]  
[Anonymous], CHEM TRANSPORT MODEL
[3]  
[Anonymous], PART MATT PM 2 5
[4]  
[Anonymous], MICR PRO REAL TIM DU
[5]  
[Anonymous], ETREX OWN MAN
[6]  
[Anonymous], AIR QUAL EUR 2017 RE
[7]  
[Anonymous], 2018, AIR POLLUTION MONITO, DOI DOI 10.5772/57353
[8]  
[Anonymous], P IEEE ETCM GUAYAQ E
[9]   High-Resolution Air Pollution Mapping with Google Street View Cars: Exploiting Big Data [J].
Apte, Joshua S. ;
Messier, Kyle P. ;
Gani, Shahzad ;
Brauer, Michael ;
Kirchstetter, Thomas W. ;
Lunden, Melissa M. ;
Marshall, Julian D. ;
Portier, Christopher J. ;
Vermeulen, Roel C. H. ;
Hamburg, Steven P. .
ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2017, 51 (12) :6999-7008
[10]   A cost-effective approach to the evaluation of traffic noise exposure in the city of Quito, Ecuador [J].
Bravo-Moncayo, Luis ;
Chavez, Miguel ;
Puyana, Virginia ;
Lucio-Naranjo, Jose ;
Garzon, Christiam ;
Pavon-Garcia, Ignacio .
CASE STUDIES ON TRANSPORT POLICY, 2019, 7 (01) :128-137