Improved Wavelet Threshold De-noising Method Based on GNSS Deformation Monitoring Data

In the process of GNSS deformation monitoring, it is inevitable that the monitoring data are contaminated by noise. Effectively mitigating the impact of noise on the measurements and thus improving the quality of the deformation data is the objective of GNSS data processing. Wavelet analysis can analyse the signal according to different frequencies of the signal. Simulation data can be used to determine the best wavelet basis function and select the appropriate decomposition level. In this paper, an improved threshold de-noising method is proposed, based on an analysis of conventional hard threshold de-noising, soft threshold de-noising and compulsory de-noising methods. The improved method was examined through a simulation analysis and applied in an engineering case. The results show that it effectively removed the noise at high frequencies while retaining data details and mutation. The de-noising ability of the proposed technique was better than that of the conventional methods. Moreover, this method significantly improved the quality of the deformation data.