Microseismic denoising assessment by polarization histograms

Abstract

We have performed a comparison of microseismic data denoising methods based on their effect on the polarization attributes of 3C microseismic signals. The compared denoising methods include the classic band-pass filtering, and three recently proposed denoising techniques: restricted-domain hyperbolic Radon transform denoising, singular value decomposition (SVD)-based reduced-rank filtering, and empirical mode decomposition denoising. In order to draw the comparison, we denoised 3C synthetic data contaminated with noise extracted from field data records; calculated their rectilinearity, azimuth, and dip polarization attributes; and arranged them into histograms. The comparison has been drawn by measuring the distances between the polarization histograms of the clean and denoised data, assuming that one method outperforms another if the aforementioned distance is smaller. This strategy allows us to quantify the improvement in the calculated polarization attributes due to the different denoising processes. In addition, we also calculated the quality factor (QF) of the denoised signals, which adds value and robustness to the comparison. Our results indicated that the method based on SVD preserves the original polarization attributes better than the other techniques tested in this work. Moreover, it also retrieved the denoised signal with the highest QF. Finally, we tested the methods with field data and assessed their performance qualitatively on the basis of the insight gained from numerical tests with synthetic data.