Wyniki wyszukiwania - BazTech

1

Application of residual learning to microseismic random noise attenuation

Zheng Jing, Jiang Tianqi, Wu Zhixiang, Sun Yuan

Acta Geophysica

|

2021

|

Vol. 69, no. 4

1151--1161

EN

Microseismic data which are recorded by near-surface sensors are usually drawn in strong random noise. The reliability and accuracy of arrivals picking, source localization, microseismic imaging and source mechanism inversion are often afected by the random noise. Random noise attenuation is important for microseismic data processing. We introduce a novel deep convolutional neural network-based denoising approach to attenuate random noise from 1D microseismic data. The approach predicts the noise (the diference between the noisy microseismic data and clean microseismic data) as output instead of directly outputing the denoised data that is called residual learning. With the residual learning strategy, the approach removes the clean data in the hidden layers. In other words, the approach learns from the random noise prior instead of an explicit data prior. Then, the denoised data are reconstructed via subtracting noise from noisy data. Compared with other commonly used denoising methods, the proposed method performs its efectiveness and superiority by experimental tests on synthetic and real data. The model is trained with synthetic data and applied on real data. The results show that random noise in the synthetic and real data can been removed. However, some noise still remains in the real data case. The reason for that may be the approach can only remove random noise nor the correlated noise. Other methods are needed to be applied to remove the correlated noise to obtain higher performance after that approach when the real microseismic data which contain both correlated noise and random noise.

2

Microseismic event denoising via adaptive directional vector median filters

Zheng J., Lu J.-R., Jiang T.-Q., Liang Z.

Acta Geophysica

|

2017

|

Vol. 65, no. 1

47--54

EN

We present a novel denoising scheme via Radon transform-based adaptive vector directional median filters named adaptive directional vector median filter (AD-VMF) to suppress noise for microseismic downhole dataset. AD-VMF contains three major steps for microseismic downhole data processing: (i) applying Radon transform on the microseismic data to obtain the parameters of the waves, (ii) performing S-transform to determine the parameters for filters, and (iii) applying the parameters for vector median filter (VMF) to denoise the data. The steps (i) and (ii) can realize the automatic direction detection. The proposed algorithm is tested with synthetic and field datasets that were recorded with a vertical array of receivers. The P-wave and S-wave direct arrivals are properly denoised for poor signal-to-noise ratio (SNR) records. In the simulation case, we also evaluate the performance with mean square error (MSE) in terms of signal-to-noise ratio (SNR). The result shows that the distortion of the proposed method is very low; the SNR is even less than dB.

3

Modelowanie mikrosejsmiczne narzędziem wspomagania rozpoznawania i interpretacji geologicznej ośrodka oraz monitorowania efektów szczelinowania hydraulicznego

Jędrzejowska-Tyczkowska H.

Nafta-Gaz

|

2016

|

R. 72, nr 8

587--596

PL

W artykule przedstawiono wyniki obliczeń uzyskanych autorskim programem MICROMOD 3D, opracowanym w ramach realizacji programu Blue Gas – projekt GASLUPMIKROS. Otrzymane rezultaty należy traktować jako testowanie ogólności zaproponowanego rozwiązania, szczegółowo opisanego w publikacji [1]. Testowanie prowadzono na modelach teoretycznych, stworzonych na podstawie rzeczywistych danych pozyskanych na jednej z koncesji PGNiG. Komentarz dotyczący wyników dla kolejnych modeli odnosi się raczej do metodyki funkcjonalnej programu, która zapewnia możliwość zastosowania go dla 3 najczęściej realizowanych wersji monitoringu sejsmicznego (powierzchniowego, otworowego oraz odbiorników pogrążonych). Przedstawione rezultaty pozwalają pozytywnie ocenić opracowany program oraz rekomendować jego wykorzystanie w bieżących pracach przemysłowych, zarówno w projektowaniu akwizycji dla mikroszczelinowania hydraulicznego, jak też przy weryfikacji obliczanych parametrów geomechanicznych ośrodka geologicznego. Ponadto wyniki modelowań standardowo stanowią wsparcie dla prac interpretacyjnych sejsmiki.

EN

In the paper the results of calculations obtained by way of the Micromod 3D software, developed as part of the Blue Gas project – GASLUPMIKROS are presented. These results should be treated as general testing of the proposed solution, described in detail in the publication [1]. Testing was conducted on theoretical models, created on the basis of real data, obtained from one of the PGNiG concessions. Comments on the results for the following models refers rather to the methodology of the software functionality, which provides the ability to use the Micromod 3D for the three most frequently performed types of the seismic monitoring: surface sensor network, downhole sensors, and shallow buried array. The results allow to positively evaluate the developed software and recommend its use in the ongoing work in the industry, both in the design of acquisition for hydraulic fracturing as well as the verification of calculated geomechanical parameters of geological medium. Furthermore, the microseismic modeling results provides support for seismic interpretation.