地球时变重力场模型反演陆地水储量变化已为全球气候变化研究作出巨大贡献,考虑到时变重力场模型球谐系数中存在相关性,其高阶次项具有较大的误差,需采用最优的滤波方法进行空间平滑。本文提出一种新的各向异性组合滤波方法,其基本思想是将改进的高斯滤波法与均方根(root mean square,RMS)滤波法组合,即对球谐系数的低阶次采用改进的高斯滤波法,而高阶次采用RMS滤波法。首先分析了最新的GRACE RL05系列时变重力场模型系数误差特性,基于全球水储量变化反演结果,分析比较了高斯滤波、改进的高斯滤波、RMS滤波和DDK滤波与本文提出的组合滤波法的有效性及精度,并利用模型结果进行了验证,计算结果表明,组合滤波法的中误差最小。研究结果表明,本文提出的组合法相比于先前的滤波方法,可有效地过滤高阶次的噪声,消除南北条带误差,同时减少信号泄漏,提高信噪比,保留更多有效的地球物理信号,进而提高反演精度。
英文摘要:
The inversion of variations of terrestrial water storage by the earth time-variable gravity filed model makes a great contribution to global climate change, however, the spherical harmonics of time-variable gravity field have correlation problem and significant errors in high orders and degrees, and so optimal filtering method is needed to solve this problem. In this article, a new filter, named 'non-isotropic combination filter' was devised, and showed a better performance. The basic idea of the new filter is to apply the Gaussian filter and the RMS filter to low-degree and high-degree harmonic coefficients separately. In this paper, we first analyze the error characteristics of the latest GRACE RL05 series variable gravity field model, compare the validity and precision with Gaussian filter, improved Gaussian filter, RMS filter, DDK filter, the non-isotropic combination filter and verified them with the model. It shows that the mean square error of the non-isotropic combination filter and model is the least. Based on above analysis, we find that the non-isotropic combination filter can suppress the noises in high-degrees and high-orders, eliminate the N-S striping errors, lower signal leakage errors, improve the ratio of signal-to-noise more effectively compared with the previous filters.