GPS-ZTD data assimilation and its impact on wintertime haze prediction over North China Plain using WRF 3DVAR and CMAQ modeling system

Forecast of Fine Particles in Chengdu under Autumn-Winter Synoptic Conditions

We conducted an evaluation of the impact of meteorological factor forecasts on the prediction of fine particles in Chengdu, China, during autumn and winter, utilizing the European Cooperation in Science and Technology (COST)733 objective weather classification software and the Community Multiscale Air Quality model. This analysis was performed under four prevailing weather patterns. Fine particle pollution tended to occur under high-pressure rear, homogeneous-pressure, and low-pressure conditions; by contrast, fine particle concentrations were lower under high-pressure bottom conditions. The forecasts of fine particle concentrations were more accurate under high-pressure bottom conditions than under high-pressure rear and homogeneous-pressure conditions. Moreover, under all conditions, the 24 h forecast of fine particle concentrations were more accurate than the 48 and 72 h forecasts. Regarding meteorological factors, forecasts of 2 m relative humidity and 10 m wind speed were more accurate under high-pressure bottom conditions than high-pressure rear and homogeneous-pressure conditions. Moreover, 2 m relative humidity and 10 m wind speed were important factors for forecasting fine particles, whereas 2 m air temperature was not. Finally, the 24 h forecasts of meteorological factors were more accurate than the 48 and 72 h forecasts, consistent with the forecasting of fine particles.

Haze Prediction Model Using Deep Recurrent Neural Network

In recent years, haze pollution is frequent, which seriously affects daily life and production process. The main factors to measure the degree of smoke pollution are the concentrations of PM2.5 and PM10. Therefore, it is of great significance to study the prediction of PM2.5/PM10 concentration. Since PM2.5 and PM10 concentration data are time series, their time characteristics should be considered in their prediction. However, the traditional neural network is limited by its own structure and has some weakness in processing time related data. Recurrent neural network is a kind of network specially used for sequence data modeling, that is, the current output of the sequence is correlated with the historical output. In this paper, a haze prediction model is established based on a deep recurrent neural network. We obtained air pollution data in Chengdu from the China Air Quality Online Monitoring and Analysis Platform, and conducted experiments based on these data. The results show that the new method can predict smog more effectively and accurately, and can be used for social and economic purposes.