S-wave Velocity Prediction Research Articles

Pore pressure prediction based on rock physics theory and its application in seismic inversion

Formation overpressure seriously affects drilling and downhole operation. Accurate prediction on the formation pore pressure can not only reduce the probability of drilling accidents, but also quantitatively evaluate the original formation pressure of underground pore space, which provides an important reference for site selection of carbon sink projects using underground space resources such as CO2 geological storage. It is therefore necessary to set up a widely applicable method that is based on rock physics theory and conforms to the characteristics of rock mechanics and fluid mechanic. This method is suitable for both logging prediction and seismic inversion of pore pressure. The traditional method of predicting pore pressure based on P-wave velocity has multiple solutions, and the prediction based on S-wave velocity which is not sensitive to fluid has new significance. Based on the Hertz-Mindlin petrophysical model that considering pressure variation and the Gassmann fluid substitution equation that addresses the change in fluid saturation, this paper firstly derived rock physical formulas for predicting pore pressure in logging, and then derived the intrinsic power function relationship between the effective pressure (Pe) and S-wave velocity (Vs) as well as S-wave impedance (Is). Based on this, a set of geophysical methods integrating S-wave velocity prediction, pore pressure prediction in well and seismic inversion is finally established. The efficacy of this method has been well validated, with an average error of 2.35% in S-wave velocities prediction, 4.5% in single-well pore pressure prediction. The results of seismic inversion of pore pressure are consistent with the phenomenon of overpressure development in actual working area. This method can be further extended to other areas, providing invaluable reference for underground operation such as oil and gas exploration and CO2 geological storage.

S-wave log construction through semi-supervised regression clustering using machine learning: A case study of North Sea fields

Accurate prediction of S-wave velocity from well logs is essential for understanding subsurface geological formations and hydrocarbon reservoirs. Machine learning techniques, including clustering and regression, have emerged as effective methods for indirectly estimating S-wave logs and other rock properties. In this study, we employed clustering algorithms to identify similarities among well log datasets, encompassing depth, sonic, porosity, neutron, and apparent density, facilitating the discovery of correlations among various wells. These identified correlations served as a foundation for predicting S-wave values using a novel semi-supervised approach. Our approach combined clustering, specifically k-means clustering, with different types of regressors, including Least Squares Regression (LSR), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP). Our results demonstrate the superior performance of this integrated approach compared to traditional regression methods. We validated our methodology using various parametric and non-parametric regression techniques, showcasing its effectiveness not only on wells within the training region but also on wells outside the study area. We achieved a significant improvement in the R2 score metric, ranging from 2.22% to 6.51%, and a reduction in Mean Square Error (MSE) of at least 31% when compared to predictions made without clustering. This study underscores the potential of machine learning techniques for accurate prediction of S-wave velocity and other rock properties, thereby enhancing our comprehension of subsurface geology and hydrocarbon reservoirs.

Shear-wave velocity prediction of tight reservoirs based on poroelasticity theory: A comparative study of deep neural network and rock physics model

The absence of shear-wave (S-wave) velocity in well log data limits the effective seismic characterization of lithology, petrophysical properties, and fluid distribution of tight reservoirs in the Chang 7 shale oil formations of Ordos Basin, west China. However, conventional rock physics models (RPMs), e.g., the Xu-White model, struggle to accurately obtain the key parameters such as pore aspect ratio in the process of S-wave velocity prediction. This work performs a comparative study of S-wave velocity prediction based on deep neural network (DNN) and RPM for such reservoirs. By employing the poroelasticity equations which are capable of describing elastic wave propagation in the complex reservoirs saturated with viscous fluid, the relation between elastic and petrophysical properties is established with a DNN-based method. This approach quantifies the connection between P-/S-wave velocities and rock properties. On the other hand, we reformulate the traditional Xu-White model by incorporating the decoupled Kuster-Toksöz (K-T) model and the poroelasticity equations with viscoelastic fluid in the modeling process. The variation of pore aspect ratio with depth is also considered to characterize the complex pore structures, which is appropriate for improving the accuracy of prediction. Log data from the three wells are considered for verification, of which results show that the S-wave velocity prediction methods help improve the final result. Aided by the DNN-based method, the prediction exhibits a better performance if the training data is sufficient. In particular, provided a small amount of measured S-wave data (even ten data points), the trained DNN model can also provide reasonable predictions.

Shear wave velocity prediction based on 1DCNN-BiLSTM network with attention mechanism

The Shear wave (S-wave) velocity is an essential parameter in reservoir characterization and evaluation, fluid identification, and prestack inversion. However, the cost of obtaining S-wave velocities directly from dipole acoustic logging is relatively high. At the same time, conventional data-driven S-wave velocity prediction methods exhibit several limitations, such as poor accuracy and generalization of empirical formulas, inadequate exploration of logging curve patterns of traditional fully connected neural networks, and gradient explosion and gradient vanishing problems of recurrent neural networks (RNNs). In this study, we present a reliable and low-cost deep learning (DL) approach for S-wave velocity prediction from real logging data to facilitate the solution of these problems. We designed a new network sensitive to depth sequence logging data using conventional neural networks. The new network is composed of one-dimensional (1D) convolutional, bidirectional long short-term memory (BiLSTM), attention, and fully connected layers. First, the network extracts the local features of the logging curves using a 1D convolutional layer, and then extracts the long-term sequence features of the logging curves using the BiLSTM layer, while adding an attention layer behind the BiLSTM network to further highlight the features that are more significant for S-wave velocity prediction and minimize the influence of other features to improve the accuracy of S-wave velocity prediction. Afterward, the nonlinear mapping relationship between logging data and S-wave velocity is established using several fully connected layers. We applied the new network to real field data and compared its performance with three traditional methods, including a long short-term memory (LSTM) network, a back-propagation neural network (BPNN), and an empirical formula. The performance of the four methods was quantified in terms of their coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The new network exhibited better performance and generalization ability, with R2 greater than 0.95 (0.9546, 0.9752, and 0.9680, respectively), RMSE less than 57 m/s (56.29, 23.18, and 30.17 m/s, respectively), and MAE less than 35 m/s (34.68, 16.49, and 21.47 m/s, respectively) for the three wells. The test results demonstrate the efficacy of the proposed approach, which has the potential to be widely applied in real areas where S-wave velocity logging data are not available. Furthermore, the findings of this study can help for a better understanding of the superiority of deep learning schemes and attention mechanisms for logging parameter prediction.

S-wave velocity prediction using physical model-driven Gaussian process regression: A case study of tight sandstone reservoir

Knowing S-wave velocity is critical to characterize the tight sandstone reservoir owing to its insensitive elastic responses. However, it is challenging to precisely acquire S-wave information due to the high cost and technical difficulties. Here, beyond the conventional model- and statistical data-driven methods, we propose a numerical scheme based on Gaussian process regression (GPR) to predict the S-wave velocity with P-wave velocity and lithologic parameters as input. The GPR is a nonparametric kernel-based probabilistic model, which is explicitly defined by the mean and covariance functions. Compared with other machine-learning methods even the deep learning method, the GPR is a small data-based machine learning method, which is significant for geophysical issues. In addition, through training a small data set, the GPR-based scheme not only accurately estimates S-wave velocity but also quantifies the uncertainty of the results. Compared with conventional methods such as the Castagna relations, the comprehensive formula, and the bidirectional long short-term memory, the S-wave velocity predicted by GPR is more accurate in terms of the mean-squared error, root-mean-squared error, average relative error, and correlation coefficient. The field data test demonstrates that the proposed GPR-based scheme is superior and can be satisfactorily implemented for logging data.

Estimation of pore aspect ratio and capillary pressure coefficient to predict S-wave velocity based on rockphysics modeling in orthorhombic anisotropic reservoirs

Accurate prediction of S-wave velocity is of great significance in many aspects, such as inversion, migration, brittleness index calculation, etc. Under normal circumstances, the more types of known input parameters there are, the more accurate the rock’s specific situation, and the more accurate the predicted S-wave velocity. However, considering the actual situation, the types of parameters obtained through logging curves are relatively limited. Some parameters cannot be measured and calculated, which limits the accuracy of S-wave prediction. Therefore, if the parameters can be predicted, a more accurate underground situation is able to described by these parameters. Through rockphysical analysis, the pore aspect ratio and capillary pressure coefficient can affect the velocity. In this way, a new orthorhombic (ORT) rockphysical modeling process considering the pore aspect ratio and capillary pressure coefficient is proposed. The model consists of VTI anisotropy from compaction or textural alignment of minerals, and HTI anisotropy from high-angle fractures caused by stratum pressure, thus showing ORT anisotropy. The inputs of the model can be multiple minerals. And the pore structure and the modulus of the mixed fluids in the pores are considered. We use inverse theory (quantum genetic algorithms) to obtain the pore aspect ratio and capillary pressure coefficient and finally calculate the S-wave velocity through the above parameters. The calculation results in a shale reservoir show that the predicted S-wave velocity is in good agreement with the real logging data. This shows that the proposed rockphysical modeling process and inverse algorithm method are effective.

Research on Prediction Method of Volcanic Rock Shear Wave Velocity Based on Improved Xu–White Model

Volcanic rock reservoirs have received extensive attention from scholars all over the world because of their geothermal, mineral, and oil and gas resources. Shear wave velocity is the essential information for AVO (amplitude variation with offset) analysis and the reservoir description of volcanic rocks. However, due to factors such as cost, technical reasons, and so on, shear wave velocity is not provided in many logging data. This paper proposes a shear wave velocity prediction method suitable for the conventional logging of volcanic rocks. Firstly, the Xu–White model is improved. The probability distributions formed by the prior information of the logging area are used to initialize the key petrophysical parameters in the model instead of the fixed parameter value to establish the statistical petrophysical model between the logging curve and shear wave velocity. Then, based on the Bayesian inversion method, the simulated P-wave velocity is matched with the actual P-wave logging data to calculate the key petrophysical parameters, and is then used for S-wave velocity prediction. The method is applied to the actual logging data of the No. 5 structure in Nanpu Sag, eastern China. The prediction effect of shear wave velocity is better than that of the conventional method, indicating the feasibility and effectiveness of this method. This study will provide more accurate shear wave velocity data for the exploration and development of volcanic reservoirs.

S-wave velocity inversion and prediction using a deep hybrid neural network

S-wave velocity inversion and prediction using a deep hybrid neural network

Automatic prediction of shear wave velocity using convolutional neural networks for different reservoirs in Ordos Basin

Shear wave velocity (S-wave velocity) has great significance for reservoir characterization and can effectively reduce the ambiguity in seismic interpretation. However, owning to its high cost and technical difficulties, it is usually difficult to obtain for the whole region. Therefore, the prediction of S-wave velocity currently has turned into an urgent task. Thus, the S-wave velocity was predicted using 1D convolutional neural network (1D-CNN) with the well logs. In the first step, the traditional Xu-White and Xu-Payne model were used to carry out the inversion of bulk modulus, shear modulus and density, and illustrated the phenomenon for the traditional rock-physics model. Then, 1D-CNN, including one input layer, four convolutional layers, three fully connected layers and one output layer, was proposed, in which three types of well logs (conventional well logs, array induction well logs and gamma ray spectral well logs) sensitive to the S-wave velocity were determined through the well logs analysis. Finally, based on the established 1D-CNN model, the influence of different well logs combination on the S-wave velocity prediction was analyzed, indicating that the addition of different well logs can improve the accuracy of S-wave velocity. And different machine learning methods (MLs), including back-propagation (BP) and support vector regression (SVR), were also compared, showing that the predicted accuracy of 1D-CNN has been improved by 4.2% on average. Two cases for sandstone and carbonate reservoirs also showed that 1D-CNN proposed can achieve higher accuracy and better performance than traditional MLs and rock-physics models. Furthermore, the proposed method can be applied to the other oil and gas exploration fields, improving the exploration accuracy and increasing the production of oil and gas.

Spatiotemporal Synergistic Ensemble Deep Learning Method and Its Application to S-Wave Velocity Prediction

Spatiotemporal Synergistic Ensemble Deep Learning Method and Its Application to S-Wave Velocity Prediction

Research on prediction method of S-wave velocity based on deep learning

Aiming at the s-wave velocity prediction problem, based on the analysis of the advantages and disadvantages of the empirical formula method and the rock physics modeling method, combined with the s-wave velocity prediction principle, the deep learning method is introduced, and a deep learning-based logging s-wave velocity prediction method is proposed. This method uses a deep neural network algorithm to establish a nonlinear mapping relationship between reservoir parameters (acoustic time difference, density, neutron porosity, shale content, porosity) and s-wave velocity, and then applies it to the s-wave velocity prediction at the well point. Starting from the relationship between p-wave and s-wave velocity, the study explained the feasibility of applying deep learning technology to s-wave prediction and the principle of sample selection, and finally established a reliable s-wave prediction model. The model was applied to s-wave velocity prediction in different research areas, and the results show that the s-wave velocity prediction technology based on deep learning can effectively improve the accuracy and efficiency of s-wave velocity prediction, and has the characteristics of a wide range of applications. It can provide reliable s-wave data for pre-stack AVO analysis and pre-stack inversion, so it has high practical application value and certain promotion significance.

Data-driven S-wave velocity prediction method via a deep-learning-based deep convolutional gated recurrent unit fusion network

The S-wave velocity ([Formula: see text]) is a fundamental parameter in geophysical analysis, prestack seismic inversion, and reservoir prediction. For various reasons, the availability of directly measured values of [Formula: see text] is low, especially in old wells. Therefore, indirect estimations of [Formula: see text] data on the basis of available reservoir information are important, and the development of a high-efficiency and low-cost prediction method is necessary. We have developed a novel prediction method that combines the convolutional neural network (CNN) and the gated recurrent unit (GRU) algorithms, based on a deep convolutional GRU (DCGRU) approach. More specifically, a CNN structure is used to identify and memorize the complex relationship between [Formula: see text] and well-log data, whereas a GRU network is introduced to extract key features of the data series in the depth direction. Owing to its structure, the DCGRU approach can seamlessly account for data trends with depth, local correlations across data series, and the actual depth accumulation effect. This approach is tested on data sets from an actual reservoir; it provides more reliable and accurate [Formula: see text] predictions not only compared with empirical models but also compared with the CNN and GRU algorithms applied separately. Our approach has potential for accurately estimating [Formula: see text] from log data.

Registration-Free Multicomponent Joint AVA Inversion Using Optimal Transport

Seismic multicomponent, here refers to P-P wave (PP) and P- shear wave (SV), joint inversion is an important approach to improve the accuracy of S-wave velocity and density prediction. Compared with P-P wave data, converted wave data are more sensitive to these parameters. Thus, introducing these data to the seismic inversion could improve the inversion accuracy of S-wave velocity and density. Due to the travel-time gap between the multicomponent data, multicomponent inversion usually needs to be prepared for registration processing in advance. However, registration methods often suffer from matching errors, which ultimately affect the quality of the inversion results. Based on the optimal transmission idea, a registration-free multicomponent joint amplitude variation with offset/angle (AVO/AVA) inversion algorithm is developed in this article. The proposed method adopts the Earth mover’s distance between the synthetic P-SV wave and the observed P-P wave by calculating the optimal transport path. Besides <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${\ell _{1-2}}$ </tex-math></inline-formula> norm is exploited as the penalty norm, where the regularized misfit function is minimized by the alternating direction method of multipliers (ADMM) algorithm. The synthetic data test and real seismic data application show that the proposed method can retrieve the S-wave velocity and density information better than the conventional method. The proposed method can not only effectively avoid the cumbersome registration steps, but also minimize the registration error and avoid the subsequent error accumulation.

Rock physics model-based prediction of shear wave velocity utilizing machine learning technique for a carbonate reservoir, southwest Iran

S-wave velocity provides important information for the purpose of seismic reservoir characterization. However, it is not usually acquired in all wells due to the high cost and technical difficulties. Hence, different methods are developed for S-wave velocity prediction from other conventional petrophysical logs, generally using rock physics methods or artificial intelligence algorithms. Both of these methods have their own challenges for predicting S-wave velocity for complex reservoirs, which affects their prediction accuracy and efficiency accordingly. This paper proposes a combination of rock physics and machine learning methods on a carbonate reservoir to predict S-wave velocity. We used the Xu and Payne model and improved the estimation of the S-wave velocity by modifying the Gassmann's fluid substitution model and deriving a simplified form of it with a so-called C-factor exponent. Firstly, an inversion-based strategy is used to calculate this C-factor in a reference well as the training input data. Then, exponential Gaussian process regression is chosen to estimate the C-factor from the measured reservoir properties. The predicted C-factor, furthermore, is used to invert for a pore model, which was also validated with the computed tomography scanning analysis results. Our results confirm that this pore model, along with the computed C-factor, gives a better estimation for S-wave velocity in a blind well where the errors associated with the routine approaches are reduced significantly.

Multivariate S-wave velocity prediction in the assessment of elastic parameters in shale formations

Multivariate S-wave velocity prediction in the assessment of elastic parameters in shale formations

Improvement of petrophysical workflow for shear wave velocity prediction based on machine learning methods for complex carbonate reservoirs

Shear wave velocity (S-wave velocity or Vs) is one of the most critical issues for carbonate reservoirs characterization, because of its complexity of rock compositions and pore structures. The Xu-Payne petrophysical model is a commonly used method to predict S-wave velocity. However, the model excessively depends on the interpretation accuracy of rock compositions, pore structures, fluid properties and fluid saturation, which makes the prediction result potentially uncertain. With the development of intelligent algorithms, a machine learning method (Long-short Term Memory Neural Network, LSTM) is proposed to improve the traditional petrophysical workflow. With the capabilities of deep learning and data mining, the LSTM model can deeply mine the rich information in the wireline logs and then establish the relationships between S-wave velocity and wireline logs. In order to illustrate the prediction effect, the carbonate reservoir in the Majiagou Formation Member 5(Ma 5 Member) which belongs to the Ordovician system in the D area of Sulige gas field is taken as an example. Six kinds of sensitive wireline logs, including compensated acoustic log (AC), natural gamma ray log(GR), photoelectric absorption cross-section log (PE), density log (DEN), deep lateral resistivity log(RLLD), neutron log(CNL), are selected as the input data of the LSTM model. The results reveal that the accuracy of LSTM method is up to 98.9%, whereas the Xu-Payne model is only 73%. With the predicted result of all wells in the areas using LSTM, the sensitive elastic properties, including P-and S-wave velocity, P- and S-wave impendences, ratio of P- and S-wave velocity, Poisson's ratio, lame coefficient and fluid sensitivity factor, are also concluded. Compared with the Xu-Payne model, the newly proposed workflow is proved to be convenient and suitable for the prediction of S-wave velocity in carbonate reservoirs.

An effective method for shear-wave velocity prediction in sandstones

Shear-wave velocity is essential in various seismic exploration applications, including seismic modeling, amplitude variation with offset analysis, multicomponent seismic data interpretation and other exploration applications. This study presents a simple but effective method for S-wave velocity prediction from P-wave velocity based on granular media model. In the proposed method, the soft-sand, intermediate stiff-sand and stiff-sand models are unified with the expression of the soft-sand model with an effective coordination number. The shear modulus of dry rocks can be related to bulk modulus through the coordination number in the unified model. Elastic-wave velocities of water-saturated rocks at low frequencies can be predicted from the moduli of dry rock using Gassmann’s equation. Thus, the coordination number can be inverted from P-wave velocity of saturated rocks by combining the unified granular media model and Gassmann’s equation. Eventually, S-wave velocity of saturated rock is computed with the inverted effective coordination number. The numerical results indicate that the predicted S-wave velocities agree well with the measured velocities for the laboratory data and well logging data. The proposed method is applicable to sandstones with lithification of large ranges because the unified granular media model accounts for the media between Hashin–Shtrikman lower bound and upper bound. Moreover, the new method is quite suitable for the prediction of S-wave velocity in sandstones deposited in deep-water environment, particularly for turbidite sediment.

Prediction of porosity and gas saturation for deep-buried sandstone reservoirs from seismic data using an improved rock-physics model

In recent years, many important discoveries have been made in global deep oil and gas exploration, which indicates that deep exploration has gradually become one of the most important areas in current and future hydrocarbon exploration. However, the prediction of deep reservoirs is very challenging due to their low porosity and complex pore structure characteristics caused by the burial depth and diagenesis. Rock physics provides a link between the geologic reservoir parameters and seismic elastic properties and has evolved to become a key tool of quantitative seismic interpretation. Based on the mineral component and pore structure analysis of studied rocks, we propose an improved rock-physics model by introducing a third feldspar-related pore for deep-buried sandstone reservoirs to the traditional Xu–White model. This modelling process consists of three steps: first, rock matrix modelling using time-average equations; second, dry rock modelling using a multi-pore analytical approximation; and third, fluid-saturated rock modelling using a patchy distribution. It has been used in total porosity estimation, S-wave velocity prediction and rock-physics template establishment. The applicability of the improved rock-physics model is verified by a theoretical quartz-water model test and a real data total porosity estimation compared with the traditional Xu–White model and the density method. Then, a rock-physics template is generated by the improved rock-physics model for porosity and gas saturation prediction using seismic data. This template is carefully calibrated and validated by well-log data at both the well-log scale and seismic scale. Finally, the feasibility of the established rock-physics template for porosity and gas saturation prediction is validated by a deep-buried sandstone reservoir application in the East China Sea.

S-wave velocity prediction of marine-continental transitional coal measure rocks using multipole array sonic logs and the rock-matrix modulus extraction method

Accurate prediction of the S-wave velocity of highly heterogeneous coal measure strata using high-resolution logging can effectively identify high-quality reservoirs. We have used multipole array sonic logs to predict the S-wave velocity of coal measure strata based on the conventional empirical method (CEM), multiple regression method (MRM), and rock-matrix modulus extraction (MME) method. Moreover, we used a complex multiple parameter iterative computational method of forward calculation and inversion in the MME method. Our results indicate that the MME method can effectively extract several rock modulus parameters. There are good binomial relationships between the extracted rock modulus parameters ([Formula: see text]) and between the extracted modulus parameters and the P-wave impedance ([Formula: see text]). The average relative errors of the S-wave velocities predicted by the CEM, MRM, and MME methods are 7.58%, 5.64%, and 2.31%, respectively. The MME method can effectively extract and couple effective information from different types of conventional well logs and perform high-precision S-wave time difference prediction.

Prediction of S-wave velocity by a hybrid model based on the Greenberg-Castagna equation

In geophysics, more specifically in rock physics and petrophysics, empirical equations play an important role in data regularization, especially in datasets that are difficult to acquire in situ. In terms of well logging, a common scenario is the absence of shear wave slowness data, which can be handled by different methods that aim filling data gaps (regularization). This work consists of the application of a hybrid approach (based on Greenberg-Castagna method) to estimate S-wave velocity in brine-saturated lithologies on well-log datasets. The combination of local polynomial regressions with a fluid substitution analysis (Gassmann's equation) leads to an effective method of estimating shear wave velocity (VS) from compressional wave velocity (VP) when information about lithology and saturation are available. Well-log datasets (from the Norwegian Sea region) are used to demonstrate the feasibility of our methodology and show its usefulness for dataset regularization based on the local information. We selected learning and test wells from the Norne Field, where Lower to Middle Jurassic sandstones behave as hydrocarbon reservoirs. Our results show that the best fitting between the measured and predicted S-wave velocities were obtained from the modified Greenberg-Castagna method (in this work, named calibrated relation), also verified on a well from the North Viking Graben (validation dataset).