頁籤選單縮合
題名 | Regional Air Quality Forecast Using a Machine Learning Method and the WRF Model over the Yangtze River Delta, East China |
---|---|
作 者 | Jia, Mengwei; Cheng, Xinghong; Zhao, Tianliang; Yin, Chongzhi; Zhang, Xiangzhi; Wu, Xianghua; Wang, Liming; Zhang, Renjian; | 書刊名 | Aerosol and Air Quality Research |
卷期 | 19:7 2019.07[民108.07] |
頁次 | 頁1602-1613 |
分類號 | 445.63 |
關鍵詞 | Regional air quality forecast; BP network; WRF model; Heavy haze; Yangtze River Delta; |
語文 | 英文(English) |
英文摘要 | A statistical forecasting method of air quality based on meteorological elements with high spatiotemporal resolution simulated by the Weather Research and Forecasting (WRF) model and a back-propagation (BP) neural network was established to predict 72 h PM_(2.5) mass concentrations over the Yangtze River Delta (YRD) region of eastern China. Short-term statistical forecasting of air quality in 25 major cities in the YRD region was conducted and the PM_(2.5) forecast was validated using the corresponding surface PM_(2.5) observational data in this study. Results indicate that the short-term air quality forecasting system has a ability to accurately forecast PM_(2.5) concentration in the major cities in the YRD region. The average index of agreement (IA) between PM_(2.5) forecasts and observations in the four seasons ranges from 74% to 77%, and the root mean square error (RMSE) fall between 15.2 μg m^(-3) and 33.0 μg m^(-3). The data with PM_(2.5) concentration greater than 115 μg m^(-3) are selected to establish the EXP-Polluted model and then used to predict PM_(2.5) concentration during heavy haze periods in 2017. The RMSEs of PM_(2.5) forecasts during severe haze periods are improved by 44.1%, which compared to predictions using the EXP-All Time model constructed by the full-year data. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。