基于遥感和BP人工神经网络的城乡气象站点划分分析

Discrimination of Urban and Rural Meteorological Stations Based on Remote Sensing and BP Artificial Neural Network

城市热岛是城市环境和全球变化研究的重要组成部分,利用气象观测资料研究城市热岛的影响一般采用城市和乡村气象站的同步实测气温,并计算其平均气温差,因此,城乡气象站点划分的准确性,将直接影响城市热岛研究的科学性。鉴于以行政单元统计人口为依据的划分方式未考虑人口在行政单元内的实际空间分布,本文以安徽省为例,利用从遥感影像上提取的土地利用信息,采用BP人工神经网络方法,建立站点缓冲区内土地利用类型比例的城乡站点划分模型,并利用空间化后的人口格网数据对该模型的精度进行了验证。结果表明,该模型有效地建立了气象站点周边缓冲区内的土地利用类型比例与城乡站点类型之间的定量关系,避免直接采用行政单元统计人口数据的不足,客观地模拟了缓冲区内土地利用对气象站点的综合作用,科学地划分出城市和乡村气象站点,为城市热岛研究提供科学、可靠的数据保障,并可用于大区域研究。另外,本文利用划分出的乡村站点建立背景温度场,得出2000年安徽省各城市站点平均热岛强度为0.4℃。

Urban heat island has close relationship with urban environment and global climate change.Using meteorological observation data to study urban heat island is usually to calculate the difference of the mean temperature between rural meteorological stations and urban ones.Therefore,it is important to distinguish the urban stations from the rural ones correctly,which directly affects the accuracy of urban heat island research.Previous classification methods,usually based on population census data of administrative regions,did not consider the spatial distribution of population.The city＇s large population cannot reflect the situation around the station,which may lead to wrong results.In addition,it is subjective to designate rural and urban stations by manual interpretation based on remote sensing and land use,which cannot reflect the combined action of land use to meteorological stations.In this paper,BP artificial neural network was employed to build a nonlinear model between the land-use types within 5 km around the meteorological stations by remote sensing and their rural/urban property.And the model was tested by population grid data obtained from remote sensing and statistical data.The simulated result fitted the stations＇ rural/urban property well.This model avoids the limitation from administrative regions＇ population census data and reflects the combined action of land use to meteorological stations.Furthermore,this model can combine the strengths both of the density of population and land-use types by a further analysis.In order to test the temperature difference between city and rural stations,we make a temperature comparison between some city stations and the surrounding rural stations.The difference is obvious.At the same time,we build the background temperature of Anhui Province in 2000 by rural stations classified by the model.Compared with the background temperature,city temperature is averagely approximately 0.4℃ higher.This model can be adopted in lager areas and even for the whole country,where has the characters of larger coverage and shorter time of remote sensing images.