Improved principal component analysis for 3D seismic data simultaneous reconstruction and denoising

Huang, Weilin; Wang, Runqiu; Zhou, Yanxin; Chen, Yangkang; Yang, Runfei

doi:10.1190/segam2016-13858769.1

Cited by 20 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first reconstruction approach (shown as 'Approach 1' in the results section (Section 4)) follows the commonly used statistical decomposition-based reconstruction, which often is implemented using the PCA approach to link two geophysical fields, for example see [73][74][75][76].…”

Section: Data Reconstruction-approachmentioning

confidence: 99%

An Iterative ICA-Based Reconstruction Method to Produce Consistent Time-Variable Total Water Storage Fields Using GRACE and Swarm Satellite Data

et al. 2020

View full text Add to dashboard Cite

Observing global terrestrial water storage changes (TWSCs) from (inter-)seasonal to (multi-)decade time-scales is very important to understand the Earth as a system under natural and anthropogenic climate change. The primary goal of the Gravity Recovery And Climate Experiment (GRACE) satellite mission (2002–2017) and its follow-on mission (GRACE-FO, 2018–onward) is to provide time-variable gravity fields, which can be converted to TWSCs with ∼ 300 km spatial resolution; however, the one year data gap between GRACE and GRACE-FO represents a critical discontinuity, which cannot be replaced by alternative data or model with the same quality. To fill this gap, we applied time-variable gravity fields (2013–onward) from the Swarm Earth explorer mission with low spatial resolution of ∼ 1500 km. A novel iterative reconstruction approach was formulated based on the independent component analysis (ICA) that combines the GRACE and Swarm fields. The reconstructed TWSC fields of 2003–2018 were compared with a commonly applied reconstruction technique and GRACE-FO TWSC fields, whose results indicate a considerable noise reduction and long-term consistency improvement of the iterative ICA reconstruction technique. They were applied to evaluate trends and seasonal mass changes (of 2003–2018) within the world’s 33 largest river basins.

show abstract

Section: Data Reconstruction-approachmentioning

confidence: 99%

An Iterative ICA-Based Reconstruction Method to Produce Consistent Time-Variable Total Water Storage Fields Using GRACE and Swarm Satellite Data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The microseismic data can also be denoised using multichannel methods, which are widely used in the activesource seismic community, such as predictive filtering methods (Liu et al, 2012;Liu and Chen 2013), singular spectrum analysis (Huang et al, 2015(Huang et al, , 2016aZhang et al, 2016a;Zhang et al, 2016b;Zhang et al, 2016c), low-rank approximation based methods (Huang et al, 2016b;Xie et al, 2016;Chen et al, 2017;Zhou and Zhang 2017;Bai et al, 2018), dictionary learning-based methods (Chen 2017;Siahsar et al, 2017;Wu and Bai 2018a, b), and morphological filtering based method (Huang et al, 2017). The multichannel denoising methods rely on a fairly dense spatial sampling of the data.…”

Section: Introductionmentioning

confidence: 99%

An Effective Denoising Method Based on Cumulative Distribution Function Thresholding and its Application in the Microseismic Signal of a Metal Mine With High Sampling Rate (6 kHz)

et al. 2022

View full text Add to dashboard Cite

Microseismic events can be used to analyze the risk of tunnel collapse, rock burst, and other mine hazards in space and time. In practice, the artificial activities and other signals at the mining site can seriously interfere with the microseismic waveforms, reducing the signal-to-noise ratio. In this study, we propose a denoising method based on the threshold of the cumulative distribution function (CDF) of the wavelet coefficients in the wavelet domain using synchrosqueezed continuous wavelet transform (SS-CWT). First, the ratio of microseismic signal variance between two adjacent time windows is used to determine the range of background noise. Then, the microseismic signal is transformed into a wavelet domain using SS-CWT, and the threshold of wavelet coefficients at each scale is estimated based on the cumulative distribution function (CDF) of background noise. At last, a post-processing step is applied by utilizing an amplitude smoothing function, to further suppress the noise. The proposed denoising method is tested by both synthetic and filed microseismic data recorded in a metal mine. The results show that the method is effective in denoising and can improve the SNR of mine microseismic data with a high sampling rate.

show abstract

“…The state-of-the-art denoising algorithms include transforming domain thresholding methods (Candes et al, 2006), singular spectrum analysis (Vautard et al, 1992), lowrank-approximation-based methods (Huang et al, 2016), dictionary-learning-based methods (Elad and Aharon, 2006), empirical-mode-decomposition and empirical-mode-decompositionlike methods (Huang et al, 1998), etc. Denoising microseismic data will inevitably cause useful small-amplitude signal damage, which degrades the fidelity of the processed data (Li et al, 2016;Huang et al, 2016;Zhang et al, 2019). Moreover, the damaged waveform amplitude will greatly affect the subsequent source localization and mechanism analysis (Maxwell et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

Automatic high-resolution microseismic event detection via supervised machine learning

Guan

Verschuur

et al. 2020

Geophysical Journal International

Self Cite

View full text Add to dashboard Cite

SUMMARY Microseismic methods are crucial for real-time monitoring of the hydraulic fracturing dynamic status during the development of unconventional reservoirs. However, unlike the active-source seismic events, the microseismic events usually have low signal-to-noise ratio (SNR), which makes its data processing challenging. To overcome the noise issue of the weak microseismic events, we propose a new workflow for high-resolution microseismic event detection. For the preprocessing, fix-sized segmentation with a length of 2*wavelength is used to divide the data into segments. Later on, 191 features have been extracted and used as the input data to train the support vector machine (SVM) model. These features include 63 1-D time/spectral-domain features, and 128 2-D texture features, which indicate the continuity, smoothness, and irregularity of the events/noise. The proposed feature extraction maximally exploits the limited information of each segment. Afterward, we use a combination of univariate feature selection and random-forest-based recursive feature elimination for feature selection to avoid overfitting. This feature selection strategy not only finds the best features, but also decides the optimal number of features that are needed for the best accuracy. Regarding the training process, SVM with a Gaussian kernel is used. In addition, a cross-validation (CV) process is implemented for automatic parameter setting. In the end, a group of synthetic and field microseismic data with different levels of complexity show that the proposed workflow is much more robust than the state-of-the-art short-term-average over long-term-average ratio (STA/LTA) method and also performs better than the convolutional-neural-networks (CNN), for this case where the amount of training data sets is limited. A demo for the synthetic example is available: https://github.com/shanqu91/ML_event_detection_microseismic.

show abstract

Improved principal component analysis for 3D seismic data simultaneous reconstruction and denoising

Cited by 20 publications

References 4 publications

An Iterative ICA-Based Reconstruction Method to Produce Consistent Time-Variable Total Water Storage Fields Using GRACE and Swarm Satellite Data

An Iterative ICA-Based Reconstruction Method to Produce Consistent Time-Variable Total Water Storage Fields Using GRACE and Swarm Satellite Data

An Effective Denoising Method Based on Cumulative Distribution Function Thresholding and its Application in the Microseismic Signal of a Metal Mine With High Sampling Rate (6 kHz)

Automatic high-resolution microseismic event detection via supervised machine learning

Contact Info

Product

Resources

About