The Research Of Environmental Pollution Characteristics, Variation Law, Environmental Meteorological Relationship And Forecasting Of Typical Urban In The Western Region Of Northern China

With the rapid development of economy, the environmental situation of the Western Region of Northern China has become more complex and more serious. The research of regional environment pollution characteristics, variation laws, environmental meteorological relationship and forecasting has important theoretical significance and practical significance in typical urban in western region of Northern China. The research and related work is mainly showed in the following aspects:(1) The air pollution index(API) date of the four major cities(TaiYuan, Da Tong, Hu HeHaoTe, BaoTou) in the western region of Northern China was collected for the research. The pollutants emission characteristic and the temporal-spatial distribution of API were analyzed. The air pollution conditions of four cities had been improved gradually in 2003-2012. The air pollution status varied seasonally, which was the most serious in the winter, and slightest in summer. The increasing sequence of the air pollution conditions in four cities was Hu HeHaoTe, BaoTou, Da Tong, TaiYuan. The air quality was influence by PM10 in the annual, and was influence by SO2 in the winter.(2) Based on the research of the pollutants emission characteristic and the temporal-spatial distribution of API in the western region of Northern China. The corresponding ground meteorological elements data was collected. The relationship between API and meteorological elements was statistical analyzed in variation scale. API and corresponding meteorological elements in four cities existed relationship in daily scale. API was significant negatively correlated with precipitation, temperature, sunshine time. API was significant positively correlated with air pressure. API had different correlated with wind and precipitation. The correlations of daily and monthly average disposal cases were consistent, and the correlation coefficient of monthly scale is obviously higher than daily scale. API was significant correlated with wind speed and relative humidity in summer and winter, respectively. Variation meteorological elements influence the API in different ways. The results were consistent with the correlation conclusions.(3) Based on the research of the relationship between API and meteorological elements. The BP neural network, Elman neural network, T-S fuzzy neural network and wav neural network were used to build the environmental meteorological forecasting models. The four ANN-based models with reliability, high prediction accuracy for API forecasting are successful established. The Elman neural network with dynamic feedback capability is better than the other three static models in high prediction accuracy and good generalization. Although the decision weights and their rank of four ANN-based models are different, it still had a similar regularity.Based on the research of environmental meteorological forecasting neural network models. The development environmental meteorological services were discussed. The develop of environmental meteorological forecasting service was required by the construction and reform of ecological civilization which were confirm in the 18 th National Congress of the CPC and the third plenary session of the 18 th CPC national congress. The environmental meteorological forecasting service was based on the construction of monitoring facilities. The focus of the forecasting service was the Cooperation in multivariate department sand multivariate districts. The rallying point of the forecasting service was to service and connect with the community effectively.(4) The water monitoring data of the Yellow River in the western region of Northern China was collected for the research. The water quality variation characteristics of the Yellow River in the region were studied. The multi-improved probabilistic fuzzy models calculate the weights by overweight method, information entropy and analytic hierarchy process. The new model was used to assess the water quality of the Yellow River in the region. The water quality monitoring date concentration of pH in six national monitoring site meet the standard of water quality. The ShanXi YunChengHeJinDaQiao was serious polluted in COD, DO, NH3-N which only meet the class E or E plus standard. Except it, the water quality monitoring date concentration of COD of five national monitoring site in the region meet the class A standard of water quality. The water quality monitoring date concentration of DO of five national monitoring site in the region meet the class A standard of water quality. The water quality monitoring date concentration of NH3-N of five national monitoring sites in the region meet the class B standard of water quality. The multi-improved probabilistic fuzzy models were successfully established. The evaluation results showed variation water quality in different monitoring site.