基于RBF神经网络的空间插值法在空气质量监测中的应用  

Application of spatial interpolation method in air quality monitoring based on RBF neural network

作　　者：花晓蕾[1] 唐慧强[1,2] 张红燕[1] 张丽萍[1] 

机构地区：[1]南京信息工程大学信息与控制学院,江苏南京210044 [2]南京信息工程大学气象灾害预报预警与评估协同创新中心,江苏南京210044

出　　处：《传感器与微系统》2015年第1期157-160,共4页Transducer and Microsystem Technologies

基　　金：国家重大科学仪器设备开发专项任务项目(2012YQ170003-5)

摘　　要：针对我国现有大气监测站点数量有限且离散,采集的数据不能代表整个区域的空气质量等问题,提出基于RBF神经网络的空间插值法应用于空气质量的监测,以经纬度和邻近点污染物浓度为输入,建立插值点与地理坐标和邻近点之间的对应关系。实验结果表明:该方法具有较高的插值精度,为预测未知空间数据值提供了有效的处理方法,同时为大气污染治理和控制提供理论依据。Aiming at problem of quantity of atmospheric monitoring sites in our country is limited and positions are discrete, collecting data can not represent air quality of the entire area, interpolation model is established based on RBF netural network for air quality monitoring, longitude, latitude and pollutant concentrations of the vicinity stations are designed as the input of net, then build corresponding relation between interpolating point and geographic coordinate and neighborhood points. Experimental results show that the method has high interpolation precision and provide an effective processing method of predicting data for the place with unknown, therefore, treatment of air polution and control provide theory basic.

关 键 词：空气质量 径向基函数 神经网络 插值 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP391.9[自动化与计算机技术—计算机科学与技术]