摘要
以中国境内96个探空站2016~2018年1887313组数据为训练集、2019年635337组数据为测试集,建立3种基于BP神经网络的大气干、湿折射率模型,并与指数、ITU-R指数、双指数、Hopfield模型进行对比分析。结果表明,充分顾及折射率的各类可能影响因素、以地表气象信息及待定点空间位置为输入参数的BP模型效果最佳。与指数、ITU-R指数、双指数、Hopfield模型相比,最佳BP模型总折射率的RMSE分别降低69.8%、33.1%、31.9%和16.8%。BP模型在整体精度上优于传统模型,在地理空间和纵向剖面上的误差分布也更加均匀。
From the observation data of 96 sounding stations in China,we use 1887313 sets of data from 2016 to 2018 as the training set,and 635337 sets of data in 2019 as the test set.We conduct the comparison test with the exponential,ITU-R exponential,dual-exponential and Hopfield models.The results show that the BP model,which takes the surface meteorological information and the spatial location of the fixed point as input features,achieves the best effect by fully taking into account the various possible influencing factors of the refractivity.Compared with the exponential,ITU-R exponential,double exponential and Hopfield models,the RMSE of the best BP model is decreased by 69.8%,33.1%,31.9%and 16.8%,respectively.The BP model not only outperforms the traditional models in overall accuracy,but also has a more uniform distribution of errors in geospatial and longitudinal profiles.
作者
郑耀航
章迪
ZHENG Yaohang;ZHANG Di(School of Geodesy and Geomatics,Wuhan University,129 Luoyu Road,Wuhan 430079,China)
出处
《大地测量与地球动力学》
CSCD
北大核心
2023年第6期600-605,共6页
Journal of Geodesy and Geodynamics
基金
湖北省自然科学基金(2022CFB090)
武汉大学实验技术项目(WHU-2021-SYJS-15)
测绘遥感信息工程国家重点实验室专项科研经费(LIESMARS2022010)
国家自然科学基金(41604019)
湖北省大学生创新创业训练计划(S202110486161)。
关键词
大气折射率
BP神经网络
探空站
atmospheric refractivity
BP neural network
sounding station
