Stochastic Multi-Dimensional Deconvolution

Ravasi, Matteo; Selvan, Tamil; Luiken, Nick

doi:10.1109/tgrs.2022.3179626

Cited by 15 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, the solution improves when chained preconditioners are enforced across iterations (Table 1). Nevertheless, in all scenarios we observe a semi-convergence behavior (i.e., the solution starts to degrade after a certain number of iterations), highlighting the reliance of our method on a good stopping criterion (Ravasi et al, 2021).…”

Section: Numerical Examplesmentioning

confidence: 80%

Physics-based preconditioned multidimensional deconvolution in the time domain

Vargas

Vasconcelos

Ravasi

et al. 2022

Second International Meeting for Applied Geoscience &Amp; Energy

Self Cite

View full text Add to dashboard Cite

Multi-Dimensional Deconvolution is a data-driven method that is at the center of key seismic processing applications -from suppressing multiples to inversion-based imaging. When posed in an interferometric context, it can grant access to overburdenfree seismic virtual surveys at a given datum in the subsurface. As such, it constitutes an essential processing operation that achieves multiple imaging objectives simultaneously in redatuming or target-oriented imaging: e.g., suppressing multiples, removing complex overburden effects, and retrieving amplitude consistent image gathers for impedance inversion. Despite its potential, the deconvolution process relies on the solution of an ill-conditioned linear inverse problem sensitive to noise artifacts due to incomplete acquisition, limited sources, and band-limited data. Typically, this inversion is performed in the Fourier domain where the estimation of optimal regularization parameters hinders accurate waveform reconstruction. We reformulate the problem in the time domain -long believed to be computationally intractable -and introduce several physical constraints that naturally drive the inversion towards a reduced set of reliable, stable solutions. This allows to successfully reconstruct the overburden-free reflection response beneath a complex salt body from noise-contaminated data.

show abstract

Section: Numerical Examplesmentioning

confidence: 80%

Physics-based preconditioned multidimensional deconvolution in the time domain

Vargas

Vasconcelos

Ravasi

et al. 2022

Second International Meeting for Applied Geoscience &Amp; Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…To validate our proposed procedure, the approach is first tested on a realistic synthetic data set contaminated by different types of noise. The data set has been modelled using a realistic synthetic velocity model that mimics the subsurface structure of the Volve field and an ocean‐bottom configuration (see Ravasi et al., 2022, for details). The noise types under investigation include white Gaussian noise (WGN), time‐correlated noise, both isotropic and anisotropic coloured Gaussian noise (CGN) and pseudo‐rig noise.…”

Section: Numerical Analysismentioning

confidence: 99%

Explainable artificial intelligence‐driven mask design for self‐supervised seismic denoising

Birnie,

Ravasi

2024

Geophysical Prospecting

Self Cite

View full text Add to dashboard Cite

The presence of coherent noise in seismic data leads to errors and uncertainties, and as such it is paramount to suppress noise as early and efficiently as possible. Self‐supervised denoising circumvents the common requirement of deep learning procedures of having noisy‐clean training pairs. However, self‐supervised coherent noise suppression methods require extensive knowledge of the noise statistics. We propose the use of explainable artificial intelligence approaches to ‘see inside the black box’ that is the denoising network and use the gained knowledge to replace the need for any prior knowledge of the noise itself. This is achieved in practice by leveraging bias‐free networks and the direct linear link between input and output provided by the associated Jacobian matrix; we show that a simple averaging of the Jacobian contributions over a number of randomly selected input pixels provides an indication of the most effective mask to suppress noise present in the data. The proposed method, therefore, becomes a fully automated denoising procedure requiring no clean training labels or prior knowledge. Realistic synthetic examples with noise signals of varying complexities, ranging from simple time‐correlated noise to complex pseudo‐rig noise propagating at the velocity of the ocean, are used to validate the proposed approach. Its automated nature is highlighted further by an application to two field data sets. Without any substantial pre‐processing or any knowledge of the acquisition environment, the automatically identified blind masks are shown to perform well in suppressing both trace‐wise noise in common shot gathers from the Volve marine data set and coloured noise in post‐stack seismic images from a land seismic survey.

show abstract

“…It should be noted that the original signal we are dealing with is the convolution of artificial pulse signals and real earthquake signals, which is why we need to perform wavelet decomposition. The process is similar to deconvolution, which can reverse the convolution process and extract the real earthquake pulse signals from the mixed seismic records and artificial pulse signals [33][34][35][36]. To understand the randomness in the signal, we use the median absolute deviation (MAD) value to determine the minimum threshold of the wavelet coefficients in the time series [37,38].…”

Section: Removing Noisementioning

confidence: 99%

Predicting the Remaining Time before Earthquake Occurrence Based on Mel Spectrogram Features Extraction and Ensemble Learning

Zhang,

Xu,

Chen

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Predicting the remaining time before the next earthquake based on seismic signals generated in a laboratory setting is a challenging research task that is of significant importance for earthquake hazard assessment. In this study, we employed a mel spectrogram and the mel frequency cepstral coefficient (MFCC) to extract relevant features from seismic signals. Furthermore, we proposed a deep learning model with a hierarchical structure. This model combines the characteristics of long short-term memory (LSTM), one-dimensional convolutional neural networks (1D-CNN), and two-dimensional convolutional neural networks (2D-CNN). Additionally, we applied a stacking model fusion strategy, combining gradient boosting trees with deep learning models to achieve optimal performance. We compared the performance of the aforementioned feature extraction methods and related models for earthquake prediction. The results revealed a significant improvement in predictive performance when the mel spectrogram and stacking were introduced. Additionally, we found that the combination of 1D-CNN and 2D-CNN has unique advantages in handling time-series problems.

show abstract

Stochastic Multi-Dimensional Deconvolution

Cited by 15 publications

References 43 publications

Physics-based preconditioned multidimensional deconvolution in the time domain

Physics-based preconditioned multidimensional deconvolution in the time domain

Explainable artificial intelligence‐driven mask design for self‐supervised seismic denoising

Predicting the Remaining Time before Earthquake Occurrence Based on Mel Spectrogram Features Extraction and Ensemble Learning

Contact Info

Product

Resources

About