Granger-Causality Mining in Atmospheric Visibility Based on Deep Learning
- 8 Downloads
Causal relationship mining of multi-dimensional meteorological time series data can reveal the potential connection between visibility and other influencing factors, and it is meaningful in terms of environmental management, air pollution chasing, and haze control. However, because causality analysis based on statistical methods or traditional machine learning techniques cannot represent the complex relationship between visibility and its influencing factors, as an extension of traditional Granger-causality analysis, we propose a causality mining method based on the seq2seq-LSTM deep learning model. The method can profoundly reveal the hidden relationship between different features and visibility and the regular pattern of bad weather, which can provide theoretical support for air pollution control.
KeywordsGranger-causality Deep learning Multidimensional time series
This work is supported by National Natural Science Foundation of China (61702021), Beijing Natural Science Foundation (4174082), and General Program of Science and Technology Plans of Beijing Education Committee (SQKM201710005021).
- 1.Ma, Z., Li, H., Yu, P.: The impact of fog on Heyuan Expressway traffic. Guangdong Meteorol. 4, 61–62 (2006)Google Scholar
- 4.Lee, D.O.: Regional variations in long-term visibility trends in the UK 1962–1990. Geography 79, 108–121 (1994)Google Scholar
- 6.Sloane, C.S.: Visibility trends-I. Methods of analysis. Atmos. Environ. 16(1), 41–51 (1982)Google Scholar
- 18.Zhang, L., Zhang, C., Wang, B., et al.: Evolution characteristics and physical analysis ofatmospheric visibility in Beijing expressway. Chin. J. Atmos. Sci. 32(6), 1229–1240 (2008)Google Scholar
- 19.Wang, S., Zhang, X., Xu, X.: Statistical analysis of the change law of atmospheric visibility and its influencing factors in Beijing. Meteorol. Sci. Technol. 31(2), 109–114 (2003)Google Scholar
- 20.Ling, H., Junlin, A., Bin, Z.: Analysis of the change law and influence factors of atmospheric visibility in Nanjing. J. Atmos. Sci. 01(37), 91–98 (2014)Google Scholar
- 21.Fu, G., Zhang, Y., Zhang, Q., et al.: Analysis of characteristics of low visibility events in Hebei Province. Meteorology 39(08), 1042–1049 (2018)Google Scholar
- 22.Zhang, L., Zhang, C., Wang, B., et al.: Diagnosis and physical analysis of visibility and atmospheric dynamics and thermal factors of Beijing Airport Expressway. Clim. Environ. Res. 05(13), 260–272 (2008)Google Scholar