摘要
以最小二乘法、小波去噪、小波神经网络和BP神经网络为基础,构建9种地球自转参数预报模型,并进行30 d短周期预报。结果表明,对于极移预报,基于BP神经网络的地球自转参数预报模型效果不佳,RMSE均大于1.5 mas;最小二乘与小波神经网络组合模型的预报效果最好,RMSE小于1.3 mas。对于日长变化预报,最小二乘与小波神经网络组合模型的预报效果不佳,RMSE均大于0.18 ms;小波神经网络预报模型预报效果最好,RMSE为0.07 ms。
Based on least squares method,wavelet denoising,wavelet neural network and BP neural network,we construct nine kinds of prediction models of Earth rotation parameters.The results show that the prediction of Earth rotation parameters based on BP neural network is not effective,and the RMSE is greater than 1.5 mas.The least squares and wavelet neural network combined model has the best prediction effect,and the RMSE is less than 1.3 mas.For the prediction of length of day,the combined model of least squares and wavelet neural network is not good,and the RMSE is greater than 0.18 ms.The RMSE of wavelet neural network prediction model is the smallest,which is 0.07 ms.The results show that the wavelet neural network prediction model has the best prediction effect on the length of day.
作者
王帅民
赵亿奇
王振华
赵玉玲
徐玉静
章剑华
WANG Shuaimin;ZHAO Yiqi;WANG Zhenhua;ZHAO Yuling;XU Yujing;ZHANG Jianhua(School of Mining and Geomatics Engineering,Hebei University of Engineering,19 Taiji Road,Handan 056038,China;Land and Resources Exploration Center of Hebei Bureau of Geology and Mineral Resources Exploration,800 West-Zhongshan Road,Shijiazhuang 050081,China)
出处
《大地测量与地球动力学》
CSCD
北大核心
2024年第4期377-381,共5页
Journal of Geodesy and Geodynamics
基金
河北省自然科学基金(E2020402086)。
关键词
地球自转参数
小波神经网络
小波去噪
最小二乘法
Earth rotation parameters
wavelet neural network
wavelet denoising
least squares method