« Previous AbstractStructure and predictive functional profiling of microbial communities in two biotrickling filters treated with continuous/discontinuous waste gases    Next AbstractTwo-dimensional analytical solution for VOC vapor migration through layered soil laterally away from the edge of contaminant source »

Environ Pollut

Title:		"Unveiling tropospheric ozone by the traditional atmospheric model and machine learning, and their comparison:A case study in hangzhou, China"
Author(s):		Feng R; Zheng HJ; Zhang AR; Huang C; Gao H; Ma YC;
Address:		"State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou, 310027, PR China. Electronic address: 11727081@zju.edu.cn. Department of Intensive Care Unit, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310020, PR China. Electronic address: huijunzheng@zju.edu.cn. Zhejiang Tongji Vocational College of Science and Technology, Hangzhou, 311215, PR China. Hangzhou Netease Zaigu Technology Co., Ltd., Hangzhou, 310052, PR China. Zhejiang Construction Investment Environment Engineering Co, Ltd., Hangzhou, 310013, PR China. School of Electronics & Control Engineering, Chang'an University, Xi'an, 710064, PR China. Electronic address: mayucheng@chd.edu.cn"
Journal Title:		Environ Pollut
Year:		2019
Volume:		20190527
Issue:		Pt A
Page Number:		366 - 378
DOI:		10.1016/j.envpol.2019.05.101
ISSN/ISBN:		1873-6424 (Electronic) 0269-7491 (Linking)
Abstract:		"Tropospheric ozone in the surface air has become the primary atmospheric pollutant in Hangzhou, China, in recent years. Previous analysis is not enough to decode it for better regulation. Therefore, we use the traditional atmospheric model, Weather Research and Forecasting coupled with Community Multi-scale Air Quality (WRF-CMAQ), and machine learning models, Extreme Learning Machine (ELM), Multi-layer Perceptron (MLP), Random Forest (RF) and Recurrent Neural Network (RNN) to analyze and predict the ozone in the surface air in Hangzhou, China, using meteorology and air pollutants as input. We firstly quantitatively demonstrate that the dew-point deficit, instead of temperature and relative humidity, is the predominant meteorological factor in shaping tropospheric ozone. Urban heat island, daily direct solar radiation time, wind speed and wind direction play trivial role in impacting tropospheric ozone. NO(2) is the primary influential factors both for hourly ozone and daily O(3)-8?ª+h due to the titration effect. The most environmental-friendly way to mitigate the ozone pollution is to lower the volatile organic compounds (VOCs) with the highest ozone formation potentials. We deduce that the tropospheric ozone formation process tends to be not only non-linear but also non-smooth. Compared with the traditional atmospheric models, machine learning, whose characteristics are rapid convergence, short calculating time, adaptation of forecasting episodes, small program memory, higher accuracy and less cost, is able to predict tropospheric ozone more accurately"
Keywords:		"Air Pollutants/*analysis Air Pollution/*analysis China Environmental Monitoring/*methods Forecasting *Machine Learning Meteorological Concepts Meteorology Neural Networks, Computer Ozone/*analysis Volatile Organic Compounds/analysis Weather Wind Feature i;"
Notes:		"MedlineFeng, Rui Zheng, Hui-Jun Zhang, An-Ran Huang, Chong Gao, Han Ma, Yu-Cheng eng England 2019/06/04 Environ Pollut. 2019 Sep; 252(Pt A):366-378. doi: 10.1016/j.envpol.2019.05.101. Epub 2019 May 27"