基于神经网络的区域电离层模型及其在单频PPP中的应用  

Regional ionospheric delay model based on neural network and its application in single frequency precise point positioning

作　　者：许承权[1] 花向红[2,3] 范千[2,3] 夏传义[4] 杨荣华[1] 

机构地区：[1]闽江学院地理科学系,福建福州350108 [2]武汉大学测绘学院,湖北武汉430079 [3]武汉大学灾害监测与防治研究中心,湖北武汉430079 [4]武汉市勘测设计研究院,湖北武汉430022

出　　处：《测绘工程》2009年第4期1-6,共6页Engineering of Surveying and Mapping

基　　金：国家自然科学基金资助项目(40474003)

摘　　要：基于武汉市CORS系统的双频非差载波相位观测数据,利用改进的神经网络方法建立区域电离层模型,并通过单频GPS精密单点定位的计算实例来分析该模型的精度。计算实例表明,当基准站间的距离小于100 km时,基于神经网络的区域电离层模型的平均外符合精度为0.03 m,对于时段长度为4 h的单频PPP静态时段解可以达到厘米级的定位精度。An improved neural network has been developed for estimating the total electron content（TEC） of the ionosphere using observations collected by a GPS network of double frequency GPS receivers. And a single frequency precise point positioning（PPP） software MPEPPP has been developed using neural network to mitigate the ionospheric delay. Numerical result shows that the external accordant accuracy of the regional ionospheric delay model using neural network is better than 0. 03 meters when the distances of base stations are between 50 and 100 km, and the single frequency PPP using the proposed model can achieve an accuracy of centimeter level.

关 键 词：电离层模型 神经网络 GPS 精密单点定位 

分 类 号：P228.4[天文地球—大地测量学与测量工程]