Searcharxiv⌕ Search

arXiv subjects

Tariq Alkhalifah

Publications and source records attributed to Tariq Alkhalifah.

At least 73 records · Page 4Linked to original sources
arXiv2023

A self-supervised scheme for ground roll suppression

In recent years, self-supervised procedures have advanced the field of seismic noise attenuation, due to not requiring a massive amount of clean labeled data in the training stage, an unobtainable requirement for seismic data. However, current self-supervised methods usually suppress simple noise types, such as random and trace-wise noise, instead of the complicated, aliased ground roll. Here, we propose an adaptation of a self-supervised procedure, namely, blind-fan networks, to remove aliased ground roll within seismic shot gathers without any requirement for clean data. The self-supervised denoising procedure is implemented by designing a noise mask with a predefined direction to avoid the coherency of the ground roll being learned by the network while predicting one pixel's value. Numerical experiments on synthetic and field seismic data demonstrate that our method can effectively attenuate aliased ground roll.

physics.geo-ph↗
arXiv2023

Micro-seismic Elastic Reflection Full Waveform Inversion with An Equivalent Source

In micro-seismic event measurements, pinpointing the passive source's exact spatial and temporal location is paramount. This research advocates for the combined use of both P- and S-wave data, captured by geophone monitoring systems, to improve source inversion accuracy. Drawing inspiration from the secondary source concept in Elastic Reflection Full Waveform Inversion (ERFWI), we introduce an equivalent source term. This term combines source functions and source images. Our optimization strategy iteratively refines the spatial locations of the source, its temporal functions, and associated velocities using a full waveform inversion framework. Under the premise of an isotropic medium with consistent density, the source is defined by two spatial and three temporal components. This offers a nuanced source representation in contrast to the conventional seismic moment tensor. To address gradient computation, we employ the adjoint-state method. However, we encountered pronounced non-linearity in waveform inversion of micro-seismic events, primarily due to the unknown source origin time, resulting in cycle skipping challenges. To counteract this, we devised an objective function that is decoupled from the source origin time. This function is formulated by convolving reference traces with both observed and predicted data. Through the concurrent inversion of the source image, source time function, and velocity model, our method offers precise estimations of these parameters, as validated by a synthetic 2D example based on a modified Marmousi model. This nested inversion approach promises enhanced accuracy in determining the source image, time function, and velocity model.

physics.geo-ph↗
arXiv2023

Physics-informed neural wavefields with Gabor basis functions

Recently, Physics-Informed Neural Networks (PINNs) have gained significant attention for their versatile interpolation capabilities in solving partial differential equations (PDEs). Despite their potential, the training can be computationally demanding, especially for intricate functions like wavefields. This is primarily due to the neural-based (learned) basis functions, biased toward low frequencies, as they are dominated by polynomial calculations, which are not inherently wavefield-friendly. In response, we propose an approach to enhance the efficiency and accuracy of neural network wavefield solutions by modeling them as linear combinations of Gabor basis functions that satisfy the wave equation. Specifically, for the Helmholtz equation, we augment the fully connected neural network model with an adaptable Gabor layer constituting the final hidden layer, employing a weighted summation of these Gabor neurons to compute the predictions (output). These weights/coefficients of the Gabor functions are learned from the previous hidden layers that include nonlinear activation functions. To ensure the Gabor layer's utilization across the model space, we incorporate a smaller auxiliary network to forecast the center of each Gabor function based on input coordinates. Realistic assessments showcase the efficacy of this novel implementation compared to the vanilla PINN, particularly in scenarios involving high-frequencies and realistic models that are often challenging for PINNs.

physics.geo-ph↗
arXiv2023

Robust data driven discovery of a seismic wave equation

Despite the fact that our physical observations can often be described by derived physical laws, such as the wave equation, in many cases, we observe data that do not match the laws or have not been described physically yet. Therefore recently, a branch of machine learning has been devoted to the discovery of physical laws from data. We test such discovery algorithms, with our own flavor of implementation D-WE, in discovering the wave equation from the observed spatial-temporal wavefields. D-WE first pretrains a neural network (NN) in a supervised fashion to establish the mapping between the spatial-temporal locations (x,y,z,t) and the observation displacement wavefield function u(x,y,z,t). The trained NN serves to generate meta-data and provide the time and spatial derivatives of the wavefield (e.g., u_tt and u_xx) by automatic differentiation. Then, a preliminary library of potential terms for the wave equation is optimized from an overcomplete library by using a genetic algorithm. We, then, use a physics-informed information criterion to evaluate the precision and parsimony of potential equations in the preliminary library and determine the best structure of the wave equation. Finally, we train the "physics-informed" neural network to identify the corresponding coefficients of each functional term. Examples in discovering the 2D acoustic wave equation validate the feasibility and effectiveness of D-WE. We also verify the robustness of this method by testing it on noisy and sparsely acquired wavefield data.

physics.geo-ph↗
arXiv2023

Meta-Processing: A robust framework for multi-tasks seismic processing

Machine learning-based seismic processing models are typically trained separately to perform specific seismic processing tasks (SPTs), and as a result, require plenty of training data. However, preparing training data sets is not trivial, especially for supervised learning (SL). Nevertheless, seismic data of different types and from different regions share generally common features, such as their sinusoidal nature and geometric texture. To learn the shared features, and thus, quickly adapt to various SPTs, we develop a unified paradigm for neural network-based seismic processing, called Meta-Processing, that uses limited training data for meta learning a common network initialization, which offers universal adaptability features. The proposed Meta-Processing framework consists of two stages: meta-training and meta-testing. In the meta-training stage, each SPT is treated as a separate task and the training dataset is divided into support and query sets. Unlike conventional SL methods, here, the neural network (NN) parameters are updated by a bilevel gradient descent from the support set to the query set, iterating through all tasks. In the meta-testing stage, we also utilize limited data to fine-tune the optimized NN parameters in an SL fashion to conduct various SPTs, such as denoising, interpolation, ground-roll attenuation, image enhancement, and velocity estimation, aiming to converge quickly to ideal performance. Comprehensive numerical examples are performed to evaluate the performance of Meta-Processing on both synthetic and field data. The results demonstrate that our method significantly improves the convergence speed and prediction accuracy of the NN.

physics.geo-ph↗
arXiv2023

Semi-blind-trace algorithm for self-supervised attenuation of trace-wise coherent noise

Trace-wise noise is a type of noise often seen in seismic data, which is characterized by vertical coherency and horizontal incoherency. Using self-supervised deep learning to attenuate this type of noise, the conventional blind-trace deep learning trains a network to blindly reconstruct each trace in the data from its surrounding traces; it attenuates isolated trace-wise noise but causes signal leakage in clean and noisy traces and reconstruction errors next to each noisy trace. To reduce signal leakage and improve denoising, we propose a new loss function and masking procedure in semi-blind-trace deep learning. Our hybrid loss function has weighted active zones that cover masked and non-masked traces. Therefore, the network is not blinded to clean traces during their reconstruction. During training, we dynamically change the masks' characteristics. The goal is to train the network to learn the characteristics of the signal instead of noise. The proposed algorithm enables the designed U-net to detect and attenuate trace-wise noise without having prior information about the noise. A new hyperparameter of our method is the relative weight between the masked and non-masked traces' contribution to the loss function. Numerical experiments show that selecting a small value for this parameter is enough to significantly decrease signal leakage. The proposed algorithm is tested on synthetic and real off-shore and land datasets with different noises. The results show the superb ability of the method to attenuate trace-wise noise while preserving other events. An implementation of the proposed algorithm as a Python code is also made available.

physics.geo-ph↗
arXiv2023

GaborPINN: Efficient physics informed neural networks using multiplicative filtered networks

The computation of the seismic wavefield by solving the Helmholtz equation is crucial to many practical applications, e.g., full waveform inversion. Physics-informed neural networks (PINNs) provide functional wavefield solutions represented by neural networks (NNs), but their convergence is slow. To address this problem, we propose a modified PINN using multiplicative filtered networks, which embeds some of the known characteristics of the wavefield in training, e.g., frequency, to achieve much faster convergence. Specifically, we use the Gabor basis function due to its proven ability to represent wavefields accurately and refer to the implementation as GaborPINN. Meanwhile, we incorporate prior information on the frequency of the wavefield into the design of the method to mitigate the influence of the discontinuity of the represented wavefield by GaborPINN. The proposed method achieves up to a two-magnitude increase in the speed of convergence as compared with conventional PINNs.

physics.geo-ph↗
arXiv2023

Optimizing a Transformer-based network for a deep learning seismic processing workflow

StorSeismic is a recently introduced model based on the Transformer to adapt to various seismic processing tasks through its pretraining and fine-tuning training strategy. In the original implementation, StorSeismic utilized a sinusoidal positional encoding and a conventional self-attention mechanism, both borrowed from the natural language processing (NLP) applications. For seismic processing they admitted good results, but also hinted to limitations in efficiency and expressiveness. We propose modifications to these two key components, by utilizing relative positional encoding and low-rank attention matrices as replacements to the vanilla ones. The proposed changes are tested on processing tasks applied to a realistic Marmousi and offshore field data as a sequential strategy, starting from denoising, direct arrival removal, multiple attenuation, and finally root-mean-squared velocity ($V_{RMS}$) prediction for normal moveout (NMO) correction. We observe faster pretraining and competitive results on the fine-tuning tasks and, additionally, fewer parameters to train compared to the vanilla model.

physics.geo-ph↗
arXiv2023

Learnable Gabor kernels in convolutional neural networks for seismic interpretation tasks

The use of convolutional neural networks (CNNs) in seismic interpretation tasks, like facies classification, has garnered a lot of attention for its high accuracy. However, its drawback is usually poor generalization when trained with limited training data pairs, especially for noisy data. Seismic images are dominated by diverse wavelet textures corresponding to seismic facies with various petrophysical parameters, which can be suitably represented by Gabor functions. Inspired by this fact, we propose using learnable Gabor convolutional kernels in the first layer of a CNN network to improve its generalization. The modified network combines the interpretability features of Gabor filters and the reliable learning ability of original CNN. More importantly, it replaces the pixel nature of conventional CNN filters with a constrained function form that depends on 5 parameters that are more in line with seismic signatures. Further, we constrain the angle and wavelength of the Gabor kernels to certain ranges in the training process based on what we expect in the seismic images. The experiments on the Netherland F3 dataset show the effectiveness of the proposed method in a seismic facies classification task, especially when applied to testing data with lower signal-to-noise ratios. Besides, we also test this modified CNN using different kernels on salt$\&$pepper and speckle noise. The results show that we obtain the best generalization and robustness of the CNN to noise when Gabor kernels are used in the first layer.

physics.geo-ph↗
arXiv2023

Gabor-based learnable sparse representation for self-supervised denoising

Traditional supervised denoising networks learn network weights through "black box" (pixel-oriented) training, which requires clean training labels. The uninterpretability nature of such denoising networks in addition to the requirement for clean data as labels limits their applicability in real case scenarios. Deep unfolding methods unroll an optimization process into Deep Neural Networks (DNNs), improving the interpretability of networks. Also, modifiable filters in DNNs allow us to embed the physics information of the desired signals to be extracted, in order to remove noise in a self-supervised manner. Thus, we propose a Gabor-based learnable sparse representation network to suppress different noise types in a self-supervised fashion through constraints/bounds applied to the parameters of the Gabor filters of the network during the training stage. The effectiveness of the proposed method was demonstrated on two noise type examples, pseudo-random noise and ground roll, on synthetic and real data.

physics.geo-ph↗
arXiv2023

A prior regularized full waveform inversion using generative diffusion models

Full waveform inversion (FWI) has the potential to provide high-resolution subsurface model estimations. However, due to limitations in observation, e.g., regional noise, limited shots or receivers, and band-limited data, it is hard to obtain the desired high-resolution model with FWI. To address this challenge, we propose a new paradigm for FWI regularized by generative diffusion models. Specifically, we pre-train a diffusion model in a fully unsupervised manner on a prior velocity model distribution that represents our expectations of the subsurface and then adapt it to the seismic observations by incorporating the FWI into the sampling process of the generative diffusion models. What makes diffusion models uniquely appropriate for such an implementation is that the generative process retains the form and dimensions of the velocity model. Numerical examples demonstrate that our method can outperform the conventional FWI with only negligible additional computational cost. Even in cases of very sparse observations or observations with strong noise, the proposed method could still reconstruct a high-quality subsurface model. Thus, we can incorporate our prior expectations of the solutions in an efficient manner. We further test this approach on field data, which demonstrates the effectiveness of the proposed method.

physics.geo-ph↗
arXiv2023

Physics reliable frugal uncertainty analysis for full waveform inversion

Full waveform inversion (FWI) enables us to obtain high-resolution velocity models of the subsurface. However, estimating the associated uncertainties in the process is not trivial. Commonly, uncertainty estimation is performed within the Bayesian framework through sampling algorithms to estimate the posterior distribution and identify the associated uncertainty. Nevertheless, such an approach has to deal with complex posterior structures (e.g., multimodality), high-dimensional model parameters, and large-scale datasets, which lead to high computational demands and time-consuming procedures. As a result, uncertainty analysis is rarely performed, especially at the industrial scale, and thus, it drives practitioners away from utilizing it for decision-making. This work proposes a frugal approach to estimate uncertainty in FWI through the Stein Variational Gradient Descent (SVGD) algorithm by utilizing a relatively small number of velocity model particles. We warm-start the SVGD algorithm by perturbing the optimized velocity model obtained from a deterministic FWI procedure with random field-based perturbations. Such perturbations cover the scattering (i.e., high wavenumber) and the transmission (i.e., low wavenumber) components of FWI and, thus, represent the uncertainty of the FWI holistically. We demonstrate the proposed approach on the Marmousi model; we have learned that by utilizing a relatively small number of particles, the uncertainty map presents qualitatively reliable information that honours the physics of wave propagation at a reasonable cost, allowing for the potential for industrial-scale applications. Nevertheless, given that uncertainties are underestimated, we must be careful when incorporating them into downstream tasks of seismic-driven geological and reservoir modelling.

physics.geo-ph↗
arXiv2023

LatentPINNs: Generative physics-informed neural networks via a latent representation learning

Physics-informed neural networks (PINNs) are promising to replace conventional partial differential equation (PDE) solvers by offering more accurate and flexible PDE solutions. However, they are hampered by the relatively slow convergence and the need to perform additional, potentially expensive, training for different PDE parameters. To solve this limitation, we introduce latentPINN, a framework that utilizes latent representations of the PDE parameters as additional (to the coordinates) inputs into PINNs and allows for training over the distribution of these parameters. Motivated by the recent progress on generative models, we promote the use of latent diffusion models to learn compressed latent representations of the PDE parameters distribution and act as input parameters to NN functional solutions. We use a two-stage training scheme in which the first stage, we learn the latent representations for the distribution of PDE parameters. In the second stage, we train a physics-informed neural network over inputs given by randomly drawn samples from the coordinate space within the solution domain and samples from the learned latent representation of the PDE parameters. We test the approach on a class of level set equations given by the nonlinear Eikonal equation. We specifically share results corresponding to three different sets of Eikonal parameters (velocity models). The proposed method performs well on new phase velocity models without the need for any additional training.

cs.LG↗
arXiv2023

Integrating U-nets into a Multi-scale Waveform Inversion for Salt Body Building

In salt provinces, full-waveform inversion (FWI) is most likely to fail when starting with a poor initial model that lacks the salt information. Conventionally, salt bodies are included in the FWI starting model by interpreting the salt boundaries from seismic images, which is time-consuming and prone to error. Studies show that FWI can improve the interpreted salt provided that the data are recorded using long offsets, and contain low frequencies, which are not always available. Thus, we develop an approach to invert for the salt body starting from a poor initial model, limited data offsets, and the absence of low frequencies. We leverage deep learning to apply multi-stage flooding and unflooding of the velocity model. Specifically, we apply a multi-scale FWI using three frequency bandwidths. We apply a network after each frequency scale. After the first two bandwidths, the networks are trained to flood the salt, while the network after the last frequency bandwidth is trained to unflood it. We verify the method on the synthetic BP 2004 salt model benchmark. We only use the synthetic data of short offsets up to 6 km and remove frequencies below 3 Hz. We also apply the method to real vintage data acquired in the Gulf of Mexico region. The real data lack frequencies below 6 Hz and the streamer length is only 4.8 km. With these limitations, we manage to recover the salt body and verify the result by using them to image the data and analyze the resulting angle gathers.

physics.geo-ph↗
arXiv2023

Efficient physics-informed neural networks using hash encoding

Physics-informed neural networks (PINNs) have attracted a lot of attention in scientific computing as their functional representation of partial differential equation (PDE) solutions offers flexibility and accuracy features. However, their training cost has limited their practical use as a real alternative to classic numerical methods. Thus, we propose to incorporate multi-resolution hash encoding into PINNs to improve the training efficiency, as such encoding offers a locally-aware (at multi resolution) coordinate inputs to the neural network. Borrowed from the neural representation field community (NeRF), we investigate the robustness of calculating the derivatives of such hash encoded neural networks with respect to the input coordinates, which is often needed by the PINN loss terms. We propose to replace the automatic differentiation with finite-difference calculations of the derivatives to address the discontinuous nature of such derivatives. We also share the appropriate ranges for the hash encoding hyperparameters to obtain robust derivatives. We test the proposed method on three problems, including Burgers equation, Helmholtz equation, and Navier-Stokes equation. The proposed method admits about a 10-fold improvement in efficiency over the vanilla PINN implementation.

cs.LG↗
arXiv2022

Posterior sampling with CNN-based, Plug-and-Play regularization with applications to Post-Stack Seismic Inversion

Uncertainty quantification is crucial to inverse problems, as it could provide decision-makers with valuable information about the inversion results. For example, seismic inversion is a notoriously ill-posed inverse problem due to the band-limited and noisy nature of seismic data. It is therefore of paramount importance to quantify the uncertainties associated to the inversion process to ease the subsequent interpretation and decision making processes. Within this framework of reference, sampling from a target posterior provides a fundamental approach to quantifying the uncertainty in seismic inversion. However, selecting appropriate prior information in a probabilistic inversion is crucial, yet non-trivial, as it influences the ability of a sampling-based inference in providing geological realism in the posterior samples. To overcome such limitations, we present a regularized variational inference framework that performs posterior inference by implicitly regularizing the Kullback-Leibler divergence loss with a CNN-based denoiser by means of the Plug-and-Play methods. We call this new algorithm Plug-and-Play Stein Variational Gradient Descent (PnP-SVGD) and demonstrate its ability in producing high-resolution, trustworthy samples representative of the subsurface structures, which we argue could be used for post-inference tasks such as reservoir modelling and history matching. To validate the proposed method, numerical tests are performed on both synthetic and field post-stack seismic data.

stat.ML↗
arXiv2022

Transfer learning for self-supervised, blind-spot seismic denoising

Noise in seismic data arises from numerous sources and is continually evolving. The use of supervised deep learning procedures for denoising of seismic datasets often results in poor performance: this is due to the lack of noise-free field data to act as training targets and the large difference in characteristics between synthetic and field datasets. Self-supervised, blind-spot networks typically overcome these limitation by training directly on the raw, noisy data. However, such networks often rely on a random noise assumption, and their denoising capabilities quickly decrease in the presence of even minimally-correlated noise. Extending from blind-spots to blind-masks can efficiently suppress coherent noise along a specific direction, but it cannot adapt to the ever-changing properties of noise. To preempt the network's ability to predict the signal and reduce its opportunity to learn the noise properties, we propose an initial, supervised training of the network on a frugally-generated synthetic dataset prior to fine-tuning in a self-supervised manner on the field dataset of interest. Considering the change in peak signal-to-noise ratio, as well as the volume of noise reduced and signal leakage observed, we illustrate the clear benefit in initialising the self-supervised network with the weights from a supervised base-training. This is further supported by a test on a field dataset where the fine-tuned network strikes the best balance between signal preservation and noise reduction. Finally, the use of the unrealistic, frugally-generated synthetic dataset for the supervised base-training includes a number of benefits: minimal prior geological knowledge is required, substantially reduced computational cost for the dataset generation, and a reduced requirement of re-training the network should recording conditions change, to name a few.

physics.geo-ph↗
arXiv2022

Coherent noise suppression via a self-supervised blind-trace deep learning scheme

Coherent noise regularly plagues seismic recordings, causing artefacts and uncertainties in products derived from down-the-line processing and imaging tasks. The outstanding capabilities of deep learning in denoising of natural and medical images have recently spur a number of applications of neural networks in the context of seismic data denoising. A limitation of the majority of such methods is that the deep learning procedure is supervised and requires clean (noise-free) data as a target for training the network. Blindspot networks were recently proposed to overcome this requirement, allowing training to be performed directly on the noisy field data as a powerful suppressor of random noise. A careful adaptation of the blind-spot methodology allows for an extension to coherent noise suppression. In this work, we expand the methodology of blind-spot networks to create a blind-trace network that successfully removes trace-wise coherent noise. Through an extensive synthetic analysis, we illustrate the denoising procedure's robustness to varying noise levels, as well as varying numbers of noisy traces within shot gathers. It is shown that the network can accurately learn to suppress the noise when up to 60% of the original traces are noisy. Furthermore, the proposed procedure is implemented on the Stratton 3D field dataset and is shown to restore the previously corrupted direct arrivals. Our adaptation of the blind-spot network for self-supervised, trace-wise noise suppression could lead to other use-cases such as the suppression of coherent noise arising from wellsite activity, passing vessels or nearby industrial activity.

physics.geo-ph↗