Because of the difficulty in deciding on the structure of BP neural network in operational meteorological application and the tendency for the network to transform to an issue of local solution, a hybrid Particle Swar...Because of the difficulty in deciding on the structure of BP neural network in operational meteorological application and the tendency for the network to transform to an issue of local solution, a hybrid Particle Swarm Optimization Algorithm based on Artificial Neural Network (PSO-BP) model is proposed for monthly mean rainfall of the whole area of Guangxi. It combines Particle Swarm Optimization (PSO) with BP, that is, the number of hidden nodes and connection weights are optimized by the implementation of PSO operation. The method produces a better network architecture and initial connection weights, trains the traditional backward propagation again by training samples. The ensemble strategy is carried out for the linear programming to calculate the best weights based on the "east sum of the error absolute value" as the optimal rule. The weighted coefficient of each ensemble individual is obtained. The results show that the method can effectively improve learning and generalization ability of the neural network.展开更多
The temporal variation of ventilation coefficient was estimated and a simple model for the prediction of urban ventilation coefficient in Changsha was developed. Firstly, Pearson correlation analysis was used to inves...The temporal variation of ventilation coefficient was estimated and a simple model for the prediction of urban ventilation coefficient in Changsha was developed. Firstly, Pearson correlation analysis was used to investigate the relationship between meteorological parameters and mixing layer height during 2005-2009 in Changsha, China. Secondly, the multi-linear regression model between daytime and nighttime was adopted to predict the temporal ventilation coefficient. Thirdly, the validation of the model between the predicted and observed ventilation coefficient in 2010 was conducted. The results showed that ventilation coefficient significantly varied and remained high during daytime, while it stayed relatively constant and low during nighttime. In addition, the diurnal ventilation coefficient was distinctly negatively correlated with PM10 (particle with the diameter less than 10 μm) concentration in Changsha, China. The predicted ventilation coefficient agreed well with the observed values based on the multi-linear regression models during daytime and nighttime. The urban temporal ventilation coefficient could be accurately predicted by some simple meteorological parameters during daytime and nighttime. The ventilation coefficient played an important role in the PM10 concentration level.展开更多
An international workshop on urban meteorology. observation and modeling, was jointly held by the Institute of Urban Meteorology （ China ） and the National Center for Atmospheric Research （US） in Beijing, October,...An international workshop on urban meteorology. observation and modeling, was jointly held by the Institute of Urban Meteorology （ China ） and the National Center for Atmospheric Research （US） in Beijing, October, 2004. The workshop was intended to share recent progress in urban meteorological research, discuss issues related to research and development priorities faced by diverse Chinese institutions, and explore collaboration opportunities between Chinese and US research institutions. This article summarizes the major issues discussed at the workshop, including observation on urban boundary layer, urban landuse modeling, socio-economic impacts of weather and climates, and air quality in urban environment. It includes recommendations for future urban meteorology observational and modeling research, and potential collaborative opportunities between China and US.展开更多
基金Natural Science Foundation of Guangxi (0832019Z)Natural Science Foundation of China (40675023)
文摘Because of the difficulty in deciding on the structure of BP neural network in operational meteorological application and the tendency for the network to transform to an issue of local solution, a hybrid Particle Swarm Optimization Algorithm based on Artificial Neural Network (PSO-BP) model is proposed for monthly mean rainfall of the whole area of Guangxi. It combines Particle Swarm Optimization (PSO) with BP, that is, the number of hidden nodes and connection weights are optimized by the implementation of PSO operation. The method produces a better network architecture and initial connection weights, trains the traditional backward propagation again by training samples. The ensemble strategy is carried out for the linear programming to calculate the best weights based on the "east sum of the error absolute value" as the optimal rule. The weighted coefficient of each ensemble individual is obtained. The results show that the method can effectively improve learning and generalization ability of the neural network.
基金Project(51178466) supported by the National Natural Science Foundation of ChinaProject(FANEDD200545) supported by Foundation for the Author of National Excellent Doctoral Dissertation of ChinaProject(2011JQ006) supported by Fundamental Research Funds of the Central Universities of China
文摘The temporal variation of ventilation coefficient was estimated and a simple model for the prediction of urban ventilation coefficient in Changsha was developed. Firstly, Pearson correlation analysis was used to investigate the relationship between meteorological parameters and mixing layer height during 2005-2009 in Changsha, China. Secondly, the multi-linear regression model between daytime and nighttime was adopted to predict the temporal ventilation coefficient. Thirdly, the validation of the model between the predicted and observed ventilation coefficient in 2010 was conducted. The results showed that ventilation coefficient significantly varied and remained high during daytime, while it stayed relatively constant and low during nighttime. In addition, the diurnal ventilation coefficient was distinctly negatively correlated with PM10 (particle with the diameter less than 10 μm) concentration in Changsha, China. The predicted ventilation coefficient agreed well with the observed values based on the multi-linear regression models during daytime and nighttime. The urban temporal ventilation coefficient could be accurately predicted by some simple meteorological parameters during daytime and nighttime. The ventilation coefficient played an important role in the PM10 concentration level.
文摘An international workshop on urban meteorology. observation and modeling, was jointly held by the Institute of Urban Meteorology （ China ） and the National Center for Atmospheric Research （US） in Beijing, October, 2004. The workshop was intended to share recent progress in urban meteorological research, discuss issues related to research and development priorities faced by diverse Chinese institutions, and explore collaboration opportunities between Chinese and US research institutions. This article summarizes the major issues discussed at the workshop, including observation on urban boundary layer, urban landuse modeling, socio-economic impacts of weather and climates, and air quality in urban environment. It includes recommendations for future urban meteorology observational and modeling research, and potential collaborative opportunities between China and US.
