Dual Wasserstein generative adversarial network condition: A generative adversarial network-based acoustic impedance inversion method

Most acoustic impedance sparse inversion methods include two parts: reflectivity inversion and extraction of acoustic impedance from reflectivity. This being the case, the acoustic impedance is easily affected by reflectivity and the value of acoustic impedance at time t=0, thus may become inaccurate. In this paper, we propose a seismic acoustic impedance inversion method with multi-parameter regularization. In our method, the acoustic impedance is calculated directly from objective functions to ensure the stability and accuracy of results. In addition, the total variation regularization, L1 norm constraint, and initial model constraint are used to make the inversion results better accordant with a priori geological information. Moreover, we use multitrace inversion to reflect the spatial and temporal correlation of the data. Since the objective function contains several different types of regularization term, we have developed an algorithm based on split Bregman iteration to calculate it. The inversion results of theoretical model and field data show that the proposed method has high inversion precision, strong anti-noise ability and good performance on stratigraphy delineation.

Model-constrained and data-driven double-supervision acoustic impedance inversion

Seismic method is one of the most frequently applied geophysical methods in the process of oil and gas exploration. This research is conducted in Nias Waters, North Sumatra using one line 2D post-stack time migration seismic section and two wells data. Reservoir characterization is carried out to obtain physical parameters of rocks affected by fluid and rock lithology. Seismic inversion is used as a technique to create acoustic impedance distribution using seismic data as input and well data as control. As final product, multi-attribute analysis is applied to integrate of inversion results with seismic data to determine the lateral distribution of other parameters contained in well data. In this research, multi-attribute analysis is used to determine the distribution of NPHI as a validation of hydrocarbon source rocks. In that area, there is a gas hydrocarbon prospect in limestone lithology in depth around 1450 ms. Based on the results of sensitivity analysis, cross-plot between acoustic impedance and NPHI are sensitive in separating rock lithology, the target rock in the form of limestone has physical characteristics in the form of acoustic impedance values in the range of 20,000-49,000 ((ft/s)*(g/cc)) and NPHI values in the range of 5-35 %. While the results of the cross-plot between the acoustic impedance and resistivity are able to separate fluid-containing rocks with resistivity values in the range about 18-30 ohmm. The result of acoustic impedance inversion using the model based method shows the potential for hydrocarbons in the well FYR-1 with acoustic impedance in the range 21,469-22,881 ((ft/s)*(gr/cc)).

Estimation of gas hydrate saturation in the Ulleung basin using seismic attributes and a neural network

Stochastic seismic acoustic impedance inversion via a Markov-chain Monte Carlo method using a single GPU card

Seismic impedance inversion is a vital way of geological interpretation and reservoir investigation from a geophysical perspective. However, it is inevitably an ill-posed problem due to the noise or the band-limited characteristic of seismic data. Artificial neural network have been used to solve nonlinear inverse problems in recent years. This research obtained an acoustic impedance profile by feeding seismic profile and background impedance into a well-trained self-attention U-Net. The U-Net got convergence by appropriate iteration, and the output predicted the impedance profiles in the test. To value the quality of predicted profiles from different perspectives, e.g., correlation, regression, and similarity, we used four kinds of indexes. At the same time, our results were predicted by conventional methods (e.g., deconvolution with recursive inversion, and TV regularization) and a 1D neural network was calculated in contrast. Self-attention U-Net showed to be robust to noise and does not require prior knowledge. Furthermore, spatial continuity is also better than deconvolution, regularization, and 1D deep learning methods in contrast. The U-Net in this paper is a type of full convolutional neural network, so there are no limits to the shape of the input. Based on this, a large impedance profile can be predicted by U-Net, which is trained by a patchy training dataset. In addition, this paper applied the proposed method to the field data obtained by the Ceduna survey without any label. The predictions prove that this well-trained network could be generalized from synthetic data to field data.

<p>Seismic inversion method is widely used to characterize reservoirs and detect zones of interest, i.e., hydrocarbon-bearing zone in the subsurface by transforming seismic reflection data into quantitative subsurface rock properties. The primary aim of seismic inversion is to transform the 3D seismic section/cube into an acoustic impedance (AI) cube. The integration of this elastic attribute, i.e., AI cube with well log data, can thereafter help to establish correlations between AI and different petrophysical properties. The seismic inversion algorithm interpolates and spatially populates data/parameters of wells to the entire seismic section/cube based on the well log information. The case study presented here uses machine learning-neural network based algorithm to extract the different petrophysical properties such as porosity and bulk density from the seismic data of the Upper Assam basin, India. We analyzed three different stratigraphic  units that are established to be producing zones in this basin.</p><p> AI model is generated from the seismic reflection data with the help of colored inversion operator. Subsequently, low-frequency model is generated from the impedance data extracted from the well log information. To compensate for the band limited nature of the seismic data, this low-frequency model is added to the existing acoustic model. Thereafter, a feed-forward neural network (NN) is trained with AI as input and porosity/bulk density as target, validated with NN generated porosity/bulk density with actual porosity/bulk density from well log data. The trained network is thus tested over the entire region of interest to populate these petrophysical properties.</p><p>Three seismic zones were identified from the seismic section ranging from 681 to 1333 ms, 1528 to 1575 ms and 1771 to 1814 ms. The range of AI, porosity and bulk density were observed to be 1738 to 6000 (g/cc) * (m/s), 26 to 38% and 1.95 to 2.46 g/cc respectively. Studies conducted by researchers in the same basin yielded porosity results in the range of 10-36%. The changes in acoustic impedance, porosity and bulk density may be attributed to the changes in lithology. NN method was prioritized over other traditional statistical methods due to its ability to model any arbitrary dependency (non-linear relationships between input and target values) and also overfitting can be avoided. Hence, the workflow presented here provides an estimation of reservoir properties and is considered useful in predicting petrophysical properties for reservoir characterization, thus helping to estimate reservoir productivity.</p>

Multi-trace acoustic impedance inversion with multiplicative regularization

Seismic inversion in geophysics is a method that uses certain prior information, such as known geological laws and well logging and drilling data, to infer the physical parameters of underground media, such as wave impedance, velocity, and density, from seismic observation data, and thereby obtain the spatial structure and physical properties of underground strata. Seismic inversion is a highly complex problem with multiple solutions, and with the advancement of collection equipment, the volume of geophysical observation data is increasing at an astonishing rate. This presents new challenges for the accuracy and speed of seismic data inversion methods. There is an urgent need to develop intelligent and efficient inversion technologies for seismic inversion.Deep learning networks have powerful nonlinear fitting capabilities and can be used to solve complex nonlinear problems, such as seismic inversion. However, the predictive ability of deep learning networks largely depends on the quantity of training data. In the early stages of oil and gas exploration and development, the amount of well logging label data available for training is very limited, which poses a challenge for the application of deep learning in seismic inversion. Semi-supervised learning seismic inversion methods consider both data mismatch issues and well logging data mismatch issues, and can better adapt to inversion problems in real-world scenarios. Unlike supervised learning approaches, semi-supervised learning does not require a large amount of labeled data, thus it can better handle situations of data scarcity or mismatch.This paper utilizes a semi-supervised learning workflow to perform inversion on post-stack seismic data and has conducted experimental validation on the Marmousi 2 model. The experimental results show that, compared to supervised learning networks, the semi-supervised learning network still exhibits good predictive performance with a limited amount of data, demonstrating better stability in the presence of noise and geological variations, and effectively learns the mapping relationship between seismic data and artificial intelligence. Furthermore, as the amount of training data increases, the performance of the network also improves, confirming the importance of data quantity for training deep learning networks. The application results of the network on actual data indicate that the network has broad application prospects and feasibility. However, since the network is based on a channel-by-channel inversion method, there is still a lack of representation in terms of lateral continuity, which requires further exploration and improvement in subsequent research.

Bayesian model is popular in seismic acoustic impedance inversion because of the statistical information from Bayesian model. However, there are many distributions to simulate impedance distribution. Different distribution has different result. In this paper, the Gamma distribution is used as the prior distribution. A Bayesian impedance inversion method is proposed, under the assumption that the prior distribution is a Gamma distribution. Through the test from the field and model data, this method is feasible and this model based on Gamma distribution has a result with tall resolution.

Seismic impedance inversion is a geophysical technique that transforms seismic data into quantitative subsurface properties, primarily acoustic impedance. This process enables the identification of rock boundaries, hydrocarbon reservoirs, and lithological variations, thus supporting informed drilling decisions and reducing exploration risks. However, conventional inversion methods face limitations such as noise sensitivity, low resolution, and reduced effectiveness in geologically complex areas, often resulting in oversimplified subsurface models. This study addresses these challenges by employing deep learning approaches, specifically LeNet, AlexNet, and conventional CNN architectures, to improve seismic resolution and synthetic seismogram generation. The methodology involves preprocessing seismic and well-log data, calculating acoustic impedance and reflection coefficients, and applying Continuous Wavelet Transform (CWT) for feature extraction. The models are trained using synthetic seismograms and validated against real seismic data. Among the models evaluated, AlexNet demonstrates superior performance in seismic data reconstruction, achieving the lowest MSE (0.0031), RMSE (0.0557), and MAE (0.052), along with the highest R2 score (0.993). The proposed technique demonstrates superior predictive accuracy, refined subsurface characterization, and reduced geological risk, thereby establishing a robust benchmark for advanced geophysical data analysis.

We combine acoustic impedance inversion of 3D seismic data, log-to-seismic correlation, and seismic attribute analyses to delineate gas-hydrate zones at the Mallik site, Mackenzie Delta, Northwest Territories, Canada. Well-log data define three distinct hydrate zones over a depth range of 890–1100 m. Synthetic seismic modeling indicates the base of the two deeper hydrate zones are prominent reflectors. The uppermost gas-hydrate zone correlates to seismic data with a lower degree of confidence. The extent and geometry of the two lower hydrate zones suggest that local geology plays a significant role in the lateral and vertical distribution of gas hydrate at Mallik. The reliability of the hydrate concentrations calculated from the inverted impedances isqualified by the match between original and synthetic seismic data to produce confidence maps for the two lower gas-hydrate-bearing intervals. A total in-place volume estimate of solid gas hydrate for an area of [Formula: see text] around well 5L-38 yields a value of approximately [Formula: see text] (equivalently, [Formula: see text] of gas). We further qualify our mapping of gas hydrates by some amount of continuous resource, defined as lateral continuity measured by seismic attribute similarity and sand-dominated rock. Using these attributes, the continuous amount of hydrate at Mallik is about half the in-place volume (i.e., [Formula: see text]). Elsewhere within the 3D seismic cube, the seismic impedance inversion yields evidence of potential gas-hydrate deposits near wells A-06 and P-59 at levels near the predicted base of the hydrate stability zone.

Combining impedance inversion and seismic similarity for robust gas hydrate concentration assessments – A case study from the Krishna–Godavari basin, East Coast of India

Seismic inversion methods are routinely used to estimate attributes such as P-impedance, S-impedance, density, P-wave and S-wave velocity, and elastic impedances from seismic and well log data. These attributes help to understand subsurface lithology and fluid content. There are several types of seismic inversion methods available in which model-based inversion has got more attention. In the present study, the model-based inversion and geostatistical methods namely probabilistic neural network (PNN), multi-layer feed-forward neural network (MLFN) and radial basis function neural network (RBFNN) are implemented to estimate acoustic impedance, porosity, density, gamma-ray volume and P-wave velocity in the inter-well region of the F-3 block, Netherlands. The aim of the study is to predict a number of petrophysical parameters and demonstrate how they can be used to interpret seismic reflection data. A comparative study is also performed to estimate the best suitable method to predict various petrophysical parameters. The assessment of inverted results demonstrates that the impedance in the region varies from 2550 m/s*g/cc to 6150 m/s/*g/cc, which is relatively low and indicates the presence of loose formation in the area. The correlation between synthetic seismic trace and initial seismic trace is estimated to be 0.98, and the synthetic relative error as 0.19, indicating excellent algorithm output. Further, the assessment of the geostatistical methods is carried out to predict petrophysical parameters in conjunction with Multi-Attribute Transform Analysis. The analysis shows that among the geostatistical methods, the PNN provides slightly better results. The petrophysical parameters that are estimated in this study are porosity, density, gamma-ray, and P-wave velocity volumes. These parameters reinforce the interpretation of seismic data, which is a significant step in any project of exploration and production. The technique is first implemented to the composite traces near to the well location, and the findings are analysed with well log data. Second, the entire seismic section is inverted for porosity, density, gamma-ray, and P-wave velocity after achieving satisfactory outcomes in the first step. The assessment demonstrates very high-resolution subsurface petrophysical parameters which strengthen the seismic data interpretation.

Mutriba is a prominent NNW‐SSE trending anticline in Western Kuwait. Hydrocarbon prospectively of the structure is confirmed with multiple pay zones at Triassic, Jurassic and Cretaceous levels. Such levels are well known in the Middle East for being severely contaminated by coherent inter‐bed multiple reflection events and the seismic data suffers from poor resolution at deeper levels. These multiples have the same velocities as primaries and cannot be adequately attenuated during processing. As a result, Acoustic Impedance (AI) predicted from such seismic data is significantly affected. We present here a recent study which incorporates an InterBed Multiple Modeling (IBMM) into the generation of synthetic seismograms, which are involved into the seismic inversion workflow. As the observed seismic events are honored, the prediction of the AI model is optimized and less corrupted by the presence of the inter‐bed multiples within the target levels. This methodology has been successfully applied on the Mutriba field. The evaluation of the inversion results obtained, confirms the presence of significant inter‐bed multiples within the Kra‐Al‐Maru (Triasic) and the Khuff (Paleozoic) intervals. The use of the IBMM improved the match between inversion results and the AI log at well A. Moreover, the results show that the use of the IBMM in the inversion helps to obtain more accurate vertical impedance contrast, associated to a better lateral homogeneity and better mapping of horizons at deeper levels.