Abstract
Three decades of rapid economic development is causing severe and widespread PM 25 pollution in China, which hindered China's sustainable development. Master the spatiotemporal change process of the PM 2 . 5 concentration is the foundation of controlling air pollutant emissions and improving the atmospheric environment and industrial restructuring. The lack of long-term historical monitoring data hinders PM 25 related research. Therefore, the following data as the base data, including the ground observations PM 2 . 5 concentration from 2013 to 2016 and MODIS Satellites observe atmospheric optical depth (AOD), boundary height, relative humidity, temperature, wind speed, wind direction from 2000 to 2016 in the four typical regions of Beijing-Tianjin-Hebei(BTH) region, The northeastern three provinces of China (NTPC), Yangtze River Delta and Pearl River Delta, China. A combined forecasting model was constructed by combining the two algorithms of backward artificial neural network (BPANN) and support vector regression (e-SVR) and realizes the scene reproduction of the historical changes of the PM 2 . 5 concentration from 2000 to 2012 using geospatial analysis technology. The results show that the combination model is better than the single model, with lower error and higher generalization ability. The results of spatial-temporal analysis show that the concentration of PM 2 . 5 in BTH and NTPC increased by 2.87μg/m3 and 0.104μg/m3 respectively, and the pollution range of PM 2 . 5 gradually expanded. In 2012, the concentration of PM 2 . 5 decreased, the pollution range narrowed compared with previous years. PM 2 . 5 concentration rose slightly after the decline, high pollution range has been reduced in BTH and NTPC during 2013–2016, which with the country to take PM 2 . 5 regional defense and other governance measures.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have