The popularity of blended acquisition is surging in the field of seismic exploration because of its higher efficiency and lower cost. As a compromise, a sophisticated deblending framework should be applied to remove interference noise. However, blended sources are usually fired at off-the-grid (OTG) samples, and the recorded data are incomplete because of some inevitable barriers and instrument errors, increasing the challenges to apply classic deblending methods to OTG data. Typically, the binning process and data reconstruction will be introduced for OTG incomplete data before subsequent deblending. Nevertheless, the binning process may cause amplitude and phase distortion, degrading the deblending accuracy. To overcome this problem, we propose a deep learning (DL)-based method without a binning process for OTG deblending and reconstruction, namely, OTGDR, avoiding the errors related to preprocessing routines. The proposed OTGDR framework contains two components: deep image prior (DIP)-inspired coherency-enhancing network and bilinear operator-guided projection onto convex set (POCS) iteration. The DIP incorporates several fully connected (FC) layers, attention mechanism, and skip connection to extract useful features selectively for superior performance, and the following POCS aims to remove the blending and ambient noise iteratively for enhanced signal-to-noise ratio (SNR). Moreover, the proposed OTGDR is completely data-driven and does not require labels for training, which increases its generality and enables it to adapt to different datasets. In our experiments, we compare the proposed OTGDR with classic deblending methods, and the results demonstrate that OTGDR shows superior performance on OTG denoising and reconstruction in terms of fidelity and SNR.

Seismic data is commonly contaminated by different types of noise with varying amplitudes, increasing the challenges of retrieving effective signals from strong background noise. Such issues become even worse when attenuation effects are considered because the amplitude of seismic waves will dissipate after propagation, making seismic signals easier to be inundated by noise, especially at deeper positions. To implement data enhancement and attenuation compensation without noise amplification, we propose a robust framework in a blind manner to reconstruct attenuation-compensated seismic data with a higher signal-to-noise ratio (SNR), namely, structural-oriented blind Q-compensated denoising (SBQD) method. Unlike classic Q-compensated denoising methods, the proposed SBQD does not require wavelet as a prior and can iteratively estimate wavelet and reflectivity series simultaneously, and the final stationary seismic data can be obtained by convolving the estimated wavelet with the reflectivity series. Moreover, guided by local adaptive structural regularization, the proposed SBQD can provide superior results with higher accuracy and fidelity and remove those noise-related artifacts during denoising and compensation. Compared with conventional two-step methods (e.g., denoising and attenuation compensation), the proposed SBQD can implement denoising and compensation simultaneously, which avoids introducing compensation-related errors (e.g., noise amplification) and effectively preserves useful signals. Synthetic and field examples are used to validate the robustness of the proposed SBQD method on noise removal and attenuation compensation for seismic data.

Multiple attenuation plays an important role in marine seismic data processing, and a slew of methods have been developed for multiple attenuation. However, due to acquisition limitation, the performance of such methods will degrade when it comes to incomplete seismic data. Here, we proposed a novel method to implement data reconstruction and multiple suppression simultaneously. Compared with the two-step methods (e.g., interpolation and multiple attenuation), the proposed method can restore and highlight primary reflections directly without data reconstruction in advance, which avoids introducing interpolation-related errors and simplifies the data processing routines. Based on the incomplete data, we first sort seismic data into common midpoint (CMP) gathers and use normal moveout (NMO) to flatten the primary reflections, and the multiples still retain parabolas. Then, we reassigned the seismic traces randomly to decrease the coherency of the multiples from near-offset to far-offset and applied the damped rank reduction (DRR) method to the disordered traces to reconstruct seismic data and remove the unexpected multiples simultaneously. Compared with conventional two-step methods, the proposed one-step method can suppress multiples and benefit useful signal preservation more effectively. Moreover, in addition to multiples, the proposed method can remove random ambient noise and provide superior results with an improved signal-to-noise ratio (SNR). Synthetic and field examples are used to validate the validity of the proposed method on data reconstruction and multiple attenuation for incomplete seismic data.

Quality factor Q is an important parameter that accounts for the amplitude dissipation and phase distortion of seismic waves propagating in the Earth’s interior. Q estimation with improved accuracy benefits nonstationary seismic inversion, seismic imaging, fluid identification, and so on. Usually, logarithmic spectral ratio (LSR) is widely used to estimate Q based on vertical seismic profile (VSP) and poststack data. However, LSR is very sensitive to noise, and the effect of normal moveout (NMO) distorts the spectrum of the stacked seismic data, leading to an inferior Q estimation result. To weaken the effect of NMO and enhance the accuracy of Q estimation, we expand an improved LSR method in the zero-offset traveltime-local slope (e.g.,$t_{0}-p$) domain and propose a robust prestack Q estimation method based on common midpoint (CMP) gathers. The proposed method incorporates warped mapping (WM) and shaping regularization to stabilize it during Q estimation in the case of low signal-to-noise ratio (SNR). Additionally, we incorporate nonzero-offset information for Q estimation, which weakens the strong dependence on zero-offset information during prestack Q estimation. Compared with the single-gather prestack Q estimation methods (SPQEM), we make the most of the spatial coherence between the adjacent CMP to eliminate the unexpected noise-related outliers during spectral division for improved robustness and accuracy. Numerical examples are used to validate the superior performance of the proposed method, even in the presence of strong ambient noise.

Coherent and incoherent noise in seismic data inevitably reduces the quality of subsequent processing, e.g., migration and inversion. Different from random noise, erratic noise follows the non-Gaussian distribution and has high amplitude, which is a challenge to the conventional denoising frameworks based on deep learning (DL). In this study, we propose an unsupervised learning framework with a multi-branch attention mechanism (MANet) to attenuate the erratic and random noise in 2-D and 3-D seismic data. MANet can adaptively attenuate noise in multi-dimensional seismic data without the need to manually generate labels to train the network. MANet integrates global features of waveforms extracted from multiple branches in a weighted way to enhance attention to significant features, thus obtaining a global and comprehensive representation of weights. To enhance the migration ability of shallow-level to deep-level features, we add some skip connections in the corresponding encoder and decoder. We use a robust mean-Huber loss function that is less sensitive to outliers to improve the denoising performance of erratic noise. We apply the proposed network for both 2-D and 3-D synthetic and field data. The denoising results demonstrate that the proposed method has better signal preservation and noise attenuation abilities compared with the conventional denoising methods and the state-of-the-art unsupervised learning framework. We improve the interpretability of the network by visualizing the weight matrices and different encoders. Besides, the visualization schemes proposed in this paper can be applied to more research, such as geological event interpretation, geological resource detection, and surface morphology analysis.

Salt body segmentation is a critical part of structural interpretation and oil and gas exploration for subsalt reservoirs. Existing automatic salt body segmentation techniques mostly use supervised learning strategies. It is challenging to generate a large number of labels by manual labeling, especially for 3-D salt bodies. Here, we propose a self-supervised learning (SSL) framework called Salt3DNet, for 3-D salt body segmentation. This framework is divided into two stages: pretraining and fine-tuning of downstream tasks. In the pretraining stage, we use the Barlow twins (BTs) method to pretrain the encoder and reduce redundancy in a contrastive learning manner to learn high-level data representations. In the fine-tuning stage, we construct two encoders to reconstruct 3-D seismic data and segment salt bodies in a multitask collaborative learning way. The encoder and decoder are composed of the 3-D fully convolutional DenseNet and soft attention mechanism, where the latter represents the selective kernel block (SKB) with multiple kernels of different sizes. Salt3DNet calculates the correlation matrix of features from different perspectives in the pretraining stage and makes it close to the identity matrix to obtain a more prosperous feature representation. Then, Salt3DNet uses a limited number of labeled samples for training. According to the evaluation metrics, the proposed network has demonstrated promising salt segmentation performance in 3-D SEG advanced modeling (SEAM) synthetic data and$F3$block real seismic data. In addition, the proposed network is demonstrated to have higher prediction accuracy than state-of-the-art salt segmentation frameworks through ablation experiments.

Passive seismic source location imaging is important to various scientific and engineering research topics spanning from unconventional reservoir development in exploration seismology to seismic hazard prevention in the earthquake seismology community. The emerging machine-learning (ML) techniques enable the location of passive seismic sources with unprecedented efficiency and accuracy. Most of the state-of-the-art ML methods are based on waveforms, as required by the most popular convolutional neural network (CNN) architecture, which is prone to the sensitivity of velocity models. Here, we present a traveltime-based ML method, RFloc3D, to locate passive seismic sources from manually or automatically picked P- and S-wave arrivals. The proposed method is similar to traditional traveltime-based location methods, where the inverse mapping from arrival times to the passive source location is obtained by inverting a nonlinear inverse problem, but differs in leveraging the random forest (RF) method to learn the inverse mapping relation from numerous eikonal-based forward simulations. Details and analyses of the proposed RFloc3D method are illustrated based on a microseismic monitoring setup. Numerical and real data examples show that the proposed method is capable of real-time location. The inclusion of S-wave arrivals, most importantly, the differential time between P- and S-wave arrivals, helps significantly to reduce the depth error (e.g., decreasing the mean absolute error (MAE) to a half) of the located sources.

We propose to implement a compact convolutional transformer (CCT) for picking the earthquake phase arrivals (EQCCT). The proposed method consists of two branches, with each of them responsible for picking the arrival times of the P- or S-wave phases. We use the STEAD dataset to train and validate the proposed EQCCT algorithm. We split the STEAD dataset into 85% for training, 5% for validation, and 10% for testing To facilitate the training process, we implement several data augmentation strategies to the training set by adding Gaussian noise, randomly shifting the waveforms, adding a second earthquake to the input window, and dropping one or two channels from the seismogram in the STEAD dataset. As a result, the EQCCT model outperforms both EQTransformer and PhaseNet, the two most popular deep-learning-based phase-picking methods. Considering the true positive criterion as the picked phases arriving within 0.5 s of the reference times, the EQCCT achieves the lowest mean absolute error (MAE) compared to the EQTransformer and PhaseNet methods for the STEAD, Japanese, Instance and Texas datasets. Our EQCCT network also demonstrates superior performance in other metrics such as precision, recall, and F1 score. We apply the pre-trained model to three independent datasets (not included in the training set), i.e., the Japanese, Texas, and Instance datasets, and achieve higher picking accuracy than the EQTransformer and the PhaseNet in terms of various statistical metrics, demonstrating a stronger robustness and generalization ability of the EQCCT. The real-time application of EQCCT in the Texas Seismological Network (TexNet) further demonstrates its production-ready performance in terms of detection and phase-picking accuracy.

Accurate estimation of reservoir parameters (e.g., permeability and porosity) helps to understand the movement of underground fluids. However, reservoir parameters are usually expensive and time-consuming to obtain through petrophysical experiments of core samples, which makes a fast and reliable prediction method highly demanded. In this article, we propose a deep learning model that combines the 1-D convo- lutional layer and the bidirectional long short-term memory network to predict reservoir permeability and porosity. The mapping relationship between logging data and reservoir parameters is established by training a network with a combination of nonlinear and linear modules. Optimization algorithms, such as layer normalization, recurrent dropout, and early stopping, can help obtain a more accurate training model. Besides, the self-attention mechanism enables the network to better allocate weights to improve the prediction accuracy. The testing results of the well-trained network in blind wells of three different regions show that our proposed method is accurate and robust in the reservoir parameters prediction task.

We develop a random forest (RF) model for rapid earthquake location with an aim to assist earthquake early warning (EEW) systems in fast decision making. This system exploits P-wave arrival times at the first five stations recording an earthquake and computes their respective arrival time differences relative to a reference station (i.e., the first recording station). These differential P-wave arrival times and station locations are classified in the RF model to estimate the epicentral location. We train and test the proposed algorithm with an earthquake catalog from Japan. The RF model predicts the earthquake locations with high accuracy, achieving a mean absolute error (MAE) of 2.88 km. As importantly, the proposed RF model can learn from a limited amount of data (i.e., 10% of the dataset) and much fewer (i.e., three) recording stations and still achieve satisfactory results (MAE < 5 km). The algorithm is accurate, generalizable, and rapidly responding, thereby offering a powerful new tool for fast and reliable source-location prediction in EEW.

Random noise attenuation of seismic data is a fundamental problem in seismic data processing. It is not only an important problem itself but also is a crucial step for the subsequent tasks, e.g., migration and inversion. We propose a local orthogonalization constrained unsupervised deep learning denoiser (LOUD) to suppress seismic random noise based on a new loss function that specifically adapts to seismic data. Through unsupervised learning, we eliminate the common need in supervised learning approaches of collecting or generating sizable clean and noisy image pairs, which is challenging and expensive, especially for seismic data. We utilize a deep convolutional autoencoder to reconstruct the clean seismic image and leverage the local signal-and-noise orthogonalization as a constraint to guarantee that the removed noise component is orthogonal to the recovered signal. Experimental results on both synthetic and field datasets exhibit the effectiveness of our proposed method over traditional denoising methods.

5D data is the original recorded form in the 3D seismic acquisition, which includes sufficient information from all five dimensions. However, environmental and economic logistic difficulties often severely impact the data acquisition geometry, leading to raw data with missing traces and strong contaminating random noise. This deficiency often causes troubles in subsequent processing. Thus, an efficient interpolation and denoising method is required to recover useful signals. Unfortunately, practical applications of many existing reconstruction algorithms are limited by their intensive computational cost when applied to the 5D data. Additionally, the stability of these algorithms is also challenged by complex geological structures, which often degrades the reconstruction performance. To seek solutions to the aforementioned problems, we design a simple and effective framework for fast reconstruction and denoising of under-sampled 5D seismic data via a two-step process. First, we prepare the initial model from the original recordings by constructing a 3D gather at each common offset point. This step effectively interpolates the missing traces in 3D common offset gathers by exploiting the data coherency in the adjacent areas (i.e., nearby mid-points). In the second step, the processed 5D data is reorganized into 3D common mid-point gathers, with each of them further sorted into a 2D section according to absolute offset values. Then a conventional 2D processing algorithm (e.g., F-X prediction, wavelet thresholding, or multichannel singular spectrum analysis) is invoked to filter the obtained 2D section. The proposed workflow has a low overall computational cost and preserves signal fidelity. We use this framework to simultaneously denoise and interpolate the low-quality and extremely sparse seismic data. The synthetic and field examples both demonstrate the superb performance of the proposed framework in comparison with conventional methods.

We simultaneously estimate fault probabilities, strikes, and dips directly from a seismic image by using a single convolutional neural network (CNN). In this method, we assume a local 3-D fault is a plane defined by a single combination of strike and dip angles. We assume the fault strikes and dips, respectively, are in the ranges of [0°, 360°] and [64°, 85°], which are divided into 577 classes corresponding to the situation of no fault and 576 different combinations of strikes and dips. We construct a 7-layer CNN to classify the fault strike and dip in a local seismic cube and obtain the classification probability at the same time. With the fault probability, strike and dip estimated at some seismic pixel, we further compute a fault cube (centered at the pixel) with fault features elongated along the fault plane. By sliding the classification window within a full seismic image, we are able to obtain a lot of overlapping fault cubes which are stacked to compute three full images of enhanced and continuous fault probabilities, strikes, and dips. To train the CNN model, we propose an effective and efficient workflow to automatically create 900 000 synthetic seismic cubes and the corresponding fault class labels. Although trained with only synthetic data sets, our CNN model can be applied to accurately estimate fault probabilities, strikes, and dips within field seismic images that are acquired at totally different surveys. With the estimated three fault images, we further construct fault cells that are represented as small 3-D squares, each square is colored by fault probability and oriented by fault strike and dip. We recursively link the fault cells by following the fault strikes and dips to finally construct fault skins, which are simple linked data structures to represent fault surfaces.

SCons (from software construction) is a well-known open-source program designed primarily for building software. In this paper, we describe our method of extending SCons for managing data processing flows and reproducible computational experiments. We demonstrate our usage of SCons with a simple example.