WRF-Chem Simulation of Winter Visibility in Jiangsu, China, and the Application of a Neural Network Algorithm
Abstract
:1. Introduction
2. Experimental Design, Data and Method
2.1. WRF-Chem Numerical Experiment Design
2.2. Visibility Inversion Scheme
2.3. Visibility Correction Scheme
- (1)
- Layer: it is the core component of neural network. It is a data processing module that extracts representation from input data. Thus, simple layers are linked to realize progressive data distillation.
- (2)
- Input data and corresponding targets: in this paper, the input training data are 2-m humidity, 2-m air temperature, 10-m meridional and zonal wind speed, sulfate, nitrate, ammonia, OM, black carbon, PM (PM2.5–10), and aerosol factors in the winter of 2013 simulated by WRF-Chem. The target data are the visibility diurnal series in the Yangtze River Delta in winter of 2013.
- (3)
- Loss function: it is used to measure the performance of the neural network on training data to ensure the network progresses correctly. In this paper, the mean square error between the prediction and observation data are used as the loss function.
- (4)
- Optimizer: it is a mechanism for updating the network based on training data and loss function. The smaller the loss function value, the better the performance of the neural network model.
2.4. Error Analysis Method
2.5. Observation Data
3. Simulation Result Analysis
3.1. Simulation of Meteorological Elements in Jiangsu Province
3.2. WRF-Chem Simulation of Air Pollutants in Jiangsu Province
3.3. Test for Modified Visibility Based on the Neural Network Scheme
4. Conclusions and Discussions
Author Contributions
Funding
Conflicts of Interest
References
- Guo, Y.; Li, S.; Zhou, Y.; Chen, L.; Chen, S.; Yao, T.; Wu, S. The effect of air pollution on human physiological function in China: A longitudinal study. Lancet 2015, S31, 386. [Google Scholar] [CrossRef]
- Zanobetti, A.; Schwartz, J. The Effect of Fine and Coarse Particulate Air Pollution on Mortality: A National Analysis. Environ. Health Perspect. 2009, 117, 898–903. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Zhang, A.; Zhong, L.; Xu, Y.; Wang, H.; Dang, L. Tourists’ Perception of Haze Pollution and the Potential Impacts on Travel: Resha** the Features of Tourism Seasonality in Bei**g, China. Sustainability 2015, 7, 2397–2414. [Google Scholar] [CrossRef] [Green Version]
- Stevens, C.J.; Dise, N.B.; Mountford, J.O.; Gowing, D.J. Impact of nitrogen deposition on the species richness of grasslands. Science 2004, 303, 1876–1879. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Zhang, R.H.; Li, Q.; Zhang, R.N. Meteorological conditions for the persistent severe fog and haze event over eastern China in January 2013. Sci. China Earth Sci. 2014, 57, 26–35. [Google Scholar]
- Chen, H.P.; Wang, H.J. Haze days in North China and the associated atmospheric circulations based on daily visibility data from 1960 to 2012. J. Geophys. Res. Atmos. 2015, 120, 5895–5909. [Google Scholar] [CrossRef]
- Wang, H.J.; Chen, H.P.; Liu, J.P. Arctic sea ice decline intensified haze pollution in eastern China. Atmos. Oceanic Sci. Lett. 2015, 8, 1–9. [Google Scholar]
- Li, S.L.; Han, Z.; Chen, H.P. A comparison of the effects of interannual Arctic sea ice loss and ENSO on winter haze days: Observational analyses and AGCM simulations. J. Meteorol. Res. 2017, 31, 820–833. [Google Scholar] [CrossRef]
- Liu, D.; Wei, J.; Kang, Z.; Yan, W.; Cao, L.; Chen, H. Urbanization and Industrialization Effects on Haze in China: Take **agsu for Example. In Proceedings of the 19th EGU General Assembly, EGU2017, Vienna, Austria, 23–28 April 2017; 2017; p. 18493. [Google Scholar]
- Gao, X.; Xu, Y.; Zhao, Z. Jeremy Impacts of horizontal resolution and topography on the numerical simulation of East Asian precipitation (in Chinese). Chin. J. Atmos. Sci. 2006, 30, 185–192. [Google Scholar]
- Yu, E.T.; Sun, J.Q.; Chen, H.P.; ** Asian anthropogenic emissions of non-methane volatile organic compounds to multiple chemical mechanisms. Atmos. Chem. Phys. 2014, 14, 5617–5638. [Google Scholar] [CrossRef] [Green Version]
- Zheng, B.; Huo, H.; Zhang, Q.; Yao, Z.L.; Wang, X.T.; Yang, X.F.; Liu, X.; He, K.B. High-resolution map** of vehicle emissions in China in 2008. Atmos. Chem. Phys. 2014, 14, 9787–9805. [Google Scholar] [CrossRef] [Green Version]
- Sisler, J.F.; Malm, W.C. Interpretation of trends of PM2.5 and reconstructed visibility from the IMPROVE network. J. Air Waste Manag. Assoc. 2000, 50, 775–789. [Google Scholar] [CrossRef] [PubMed]
- Chow, J.C.; Bachmann, J.D.; Wierman, S.S.G.; Chow, J.C.; Bachmann, J.D.; Wierman, S.S.G.; Mathai, C.V.; Malm, W.C.; &White, W.H. Vsibility: Science and regulation. J. Air Waste Manag. Assoc. 2002, 52, 973–999. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Pitchford, M.; Main, W.; Schichtel, B. Revised algorithm for estimating light extinction from IMPROVE particle speciation data. J. Air Waste Manag. Assoc. 2007, 57, 1326–1336. [Google Scholar] [CrossRef]
- Qiu, Y.; Ma, Z.; Li, K. A modeling study of the peroxyacetyl nitrate (PAN) during a wintertime haze event in Bei**g, China. Sci. Total Environ. 2019, 650, 1944–1953. [Google Scholar] [CrossRef]
- Zhang, Z.; Gong, D.; Mao, R.; Kim S., J.; Xu, J.; Zhao, X. Cause and predictability for the severe haze pollution in downtown Bei**g in November–December 2015. Sci. Total Environ. 2017, 592, 627–638. [Google Scholar] [CrossRef]
- Chollet, F. Deep Learning with Python; Manning Publications: Westampton, NJ, USA, 2018. [Google Scholar]
- Boylan, J.W.; Russell, A.G. PM and light extinction model performance metrics, goals, and criteria for three-dimensional air quality models. Atmos. Environ. 2006, 40, 4946–4959. [Google Scholar] [CrossRef]
Weather Element | R | RMSE | MFE | MFB |
---|---|---|---|---|
T2(°C) | 0.95 | 0.97 | 0.04 | 0.11 |
RH2(%) | 0.90 | 5.95 | −0.02 | 0.04 |
WS10(m/s) | 0.43 | 0.75 | −0.02 | 0.19 |
Visibility(km) | 0.76 | 3.70 | −0.32 | 0.33 |
Weather Element | City | R | RMSE | MFE | MFB |
---|---|---|---|---|---|
T2(°C) | XZ | 0.90 | 1.51 | −0.22 | 0.45 |
YC | 0.91 | 1.38 | 0.24 | 0.40 | |
NJ | 0.90 | 1.36 | −0.16 | 0.14 | |
SZ | 0.87 | 1.30 | 0.014 | 0.10 | |
RH2(%) | XZ | 0.78 | 10.50 | −0.06 | 0.10 |
YC | 0.84 | 11.26 | −0.08 | 0.09 | |
NJ | 0.83 | 7.88 | −0.01 | 0.07 | |
SZ | 0.78 | 9.25 | −0.04 | 0.07 | |
WS10(m/s) | XZ | 0.36 | 1.01 | −0.02 | 0.34 |
YC | 0.44 | 1.07 | −0.08 | 0.27 | |
NJ | 0.38 | 1.07 | −0.08 | 0.25 | |
SZ | 0.28 | 1.14 | 0.00 | 0.26 | |
Visibility (VIS, km) | XZ | 0.59 | 3.16 | −0.03 | 0.26 |
YC | 0.53 | 6.52 | 0.16 | 0.33 | |
NJ | 0.54 | 3.26 | −0.24 | 0.34 | |
SZ | 0.48 | 4.49 | −0.30 | 0.42 |
Scheme | R | RMSE | MFE | MFB |
---|---|---|---|---|
IMPROVE | 0.17 | 2.62 | −0.26 | 0.33 |
Neural Network | 0.42 | 1.76 | −0.05 | 0.12 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zong, P.; Zhu, Y.; Wang, H.; Liu, D. WRF-Chem Simulation of Winter Visibility in Jiangsu, China, and the Application of a Neural Network Algorithm. Atmosphere 2020, 11, 520. https://doi.org/10.3390/atmos11050520
Zong P, Zhu Y, Wang H, Liu D. WRF-Chem Simulation of Winter Visibility in Jiangsu, China, and the Application of a Neural Network Algorithm. Atmosphere. 2020; 11(5):520. https://doi.org/10.3390/atmos11050520
Chicago/Turabian StyleZong, Peishu, Yali Zhu, Huijun Wang, and Duanyang Liu. 2020. "WRF-Chem Simulation of Winter Visibility in Jiangsu, China, and the Application of a Neural Network Algorithm" Atmosphere 11, no. 5: 520. https://doi.org/10.3390/atmos11050520