Multimodal data driven deep learning based seismic impedance inversion optimization

Numerical 3D high-resolution models of subsurface petroelastic properties are key tools for exploration and production stages. Stochastic seismic inversion techniques are often used to infer the spatial distribution of the properties of interest by integrating simultaneously seismic reflection and well-log data also allowing accessing the spatial uncertainty of the retrieved models. In frontier exploration areas, the available data set is often composed exclusively of seismic reflection data due to the lack of drilled wells and are therefore of high uncertainty. In these cases, subsurface models are usually retrieved by deterministic seismic inversion methodologies based exclusively on the existing seismic reflection data and an a priori elastic model. The resulting models are smooth representations of the real complex geology and do not allow assessing the uncertainty. To overcome these limitations, we have developed a geostatistical framework that allows inverting seismic reflection data without the need of experimental data (i.e., well-log data) within the inversion area. This iterative geostatistical seismic inversion methodology simultaneously integrates the available seismic reflection data and information from geologic analogs (nearby wells and/or analog fields) allowing retrieving acoustic impedance models. The model parameter space is perturbed by a stochastic sequential simulation methodology that handles the nonstationary probability distribution function. Convergence from iteration to iteration is ensured by a genetic algorithm driven by the trace-by-trace mismatch between real and synthetic seismic reflection data. The method was successfully applied to a frontier basin offshore southwest Europe, where no well has been drilled yet. Geologic information about the expected impedance distribution was retrieved from nearby wells and integrated within the inversion procedure. The resulting acoustic impedance models are geologically consistent with the available information and data, and the match between the inverted and the real seismic data ranges from 85% to 90% in some regions.

Summary The seismic data spectral inversion method, arisen in recent years, can improve the resolution of seismic data for obtaining reservoir characteristics. It does not rely on prior information such as well-logging data. By using partial spectrum information from the input seismic trace data, a sparse reflectivity series can be inverted. The inverted reflectivity series can be used to improve the resolution and impedance inversion for thin layer reservoir prediction. In this paper, we implement seismic spectral inversion based on a compressed sensing algorithm, which can solve the ill-posed problem of the inversion process. In the process of inversion, we introduce a quadratic spectrum method to calculate the spectrum of seismic wavelet in the frequency domain, which can stabilize the inversion and handle real field data. Synthetic and real field seismic data examples show that the proposed spectral inversion based on compressed sensing algorithm is stable and effective. Moreover, the real field data inversion results show a good signal-to-noise ratio (SNR) and lateral continuity.

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

<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>

Most deconvolution algorithms try to transform the seismic wavelet into spikes by designing inverse filters that remove an estimated seismic wavelet from seismic data. We assume that seismic trace subtle discontinuities are associated with acoustic impedance contrasts and can be characterized by wavelet transform spectral ridges, also called modulus maxima lines (WTMML), allowing us to improve seismic resolution by using the wavelet transform. Specifically, we apply the complex Morlet continuous wavelet transform (CWT) to each seismic trace and compute the WTMMLs. Then, we reconstruct the seismic trace with the inverse continuous wavelet transform from the computed WTMMLs with a broader band complex Morlet wavelet than that used in the forward CWT. Because the reconstruction process preserves amplitude and phase along different scales, or frequencies, the result looks like a deconvolution method. Considering this high-resolution seismic representation as a reflectivity approximation, we estimate the relative acoustic impedance (RAI) by filtering and trace integrating it. Conventional deconvolution algorithms assume the seismic wavelet to be stochastic, while the CWT is implicitly time varying such that it can be applied to both depth and time-domain data. Using synthetic and real seismic data, we evaluated the effectiveness of the methodology on detecting seismic events associated with acoustic impedance changes. In the real data examples, time and in-depth RAI results, show good correlation with real P-impedance band-pass data computed using more rigorous commercial inversion software packages that require well logs and low-frequency velocity model information.

Deep learning has been applied to tackle the seismic inversion problem, bringing more efficiency and accuracy. However, bad spatial continuity and poor generalizability limit the practical application. To solve these problems, we propose a 2D end-to-end seismic inversion method based on domain adaption. Firstly, the proposed 2D network learns the inversion mapping of seismic data under the constraint of domain adaption layer, which can reduce the difference between the features of real seismic data and synthetic seismic data, improving the generalization ability on real seismic data. Then, the trained model is finetuned with well logging data. In the first process, the spatial continuity of the inversion result is guaranteed by the 2D training scheme. Meanwhile, due to the constraint of the domain adaption layer, our model not only performs well on the synthetic data but also has good generalization ability on the real seismic data. And we carefully discuss the mechanism of domain adaption layer. In the second process, finetuning introduces well logging information, which can further improve the ability to invert details. Moreover, in order to improve the inversion accuracy on real seismic data, we develop a new training data generation method that can generate the synthetic samples close to the real samples, and a 2.5D training strategy is adopted to improve the continuity of the 3D data. The experiments on both synthetic and real seismic data show that our method performs better than both the recursive inversion method and the 1D closed-loop CNN methods.

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.

Seismic reflection amplitude data are increasingly used in reservoir modeling to provide information on changes in earth properties away from well locations. In geostatistical reservoir modeling, the most common application is to use seismic data as background data in some form of comodeling. Seismic data image reflectors and not earth layer properties. Therefore, prior to use in comodeling, seismic data must first be transformed into an earth layer property. Typically, the transform is to acoustic impedance using an appropriate seismic inversion method. Seismic inversion methods generate results that are generally band limited in nature, resulting in limits to vertical resolution. The vertical resolution achieved can be an order of magnitude below the vertical model resolution required from geostatistical reservoir modeling, which is in the order of well-log resolution. Hence, in using seismic data, geostatistical modelers encounter a problem of downscaling, not the more commonly encountered upscaling problem. This difference in scale introduces scatter between the primary data with well-log order resolution and the secondary seismically derived rock property data used in the comodeling. As a result, to preserve vertical heterogeneity, only limited use of the secondary data can be made in comodeling procedures. This results in models that only partially fit the seismic data, i.e., only limited use is made of the seismic information. If the secondary data are more strongly imposed, the fit to the seismic data improves, but the required vertical heterogeneity is not preserved. The inability to overcome this difference in scale issue, therefore, limits the value of the application of comodeling methods to integrate seismic data into reservoir models. One class of geostatistical methods that overcomes this limitation relies on iterative geostatistical modeling. In these methods, referred to as geostatistical seismic inversion, the iterative modeling process is conditioned such that the final models generated closely match the seismic data while maintaining the required vertical heterogeneity. The application of these methods is computationally expensive relative to comodeling methods but is now practical for large models on today's desktop hardware. Relative to comodeling, geostatistical seismic inversion methods make full use of the information carried in the seismic data, resulting in a significant reduction in model uncertainty away from well control.

Thin (<20 m), sand injectites, too small to resolve in conventional seismic reflection data, can constitute a large part of the net-to-gross volume and affect fluid flow in the reservoir. However, they may also cause challenges for well placement and reservoir development because they are too small to be reliably imaged in seismic reflection data. It is therefore important to better understand how small-scale injectites influence seismic images, and how they may be recognized and characterized above reservoirs. The Grane Field (North Sea) hosts numerous small-scale sand injectites above the main reservoir unit, challengin well placement, volume estimates and seismic interpretation. Here, we investigate how such small-scale sand injectites influence seismic images and may be characterized by (1) using well, 3D seismic and outcrop data to investigate geometries of small-scale sand injectites (0–15 m thick), (2) performing seismic convolution modelling to investigate how these would be imaged in seismic data, and (3) comparing these synthetic seismic images with actual 3D seismic data from the well-investigated Grane Field. Our results show that despite injectites being below seismic resolution, small-scale sand injectites can be detected in seismic data. They are more likely to be detected if they have high thickness (>5 m), steep dip (>30°), and when densely spaced. Furthermore, as the fraction of sand injectites increases the top reservoir amplitude will decrease. Moreover, comparison of the synthetic seismic images with real seismic data from the Grane Field indicates that the low-amplitude anomalies and irregularities observed above the reservoir may be a result of the overlying sand injectites. Additionally, the comparison strongly suggests that the Grane Field hosts sand injectites that are thicker and located further away from the top reservoir than is indicated by well observations. These results may be used to improve well planning and develop reservoirs with overlying sand injectites. Supplementary material: A PDF file containing all the seismic modelling results allowing the reader to flip back and forth between the models is available at https://www.doi.org/10.6084/m9.figshare.14333102 and well logs from well 25/11-18T2 are available at https://factpages.npd.no/pbl/wellbore_documents/2358_25_1_18_COMPLETION_REPORT_AND_LOG.pdf

Reservoir characterization (RC) is a process of finding petrophysical properties of the subsurface mainly from the seismic and well-log data. The nonlinear and heterogeneous nature of the subsurface is the major bottleneck in estimating the reservoir properties. In the past two decades, the RC has eventually turned out to be an interdisciplinary field of research involving computational science, signal processing, geostatistics, and geophysics. This article provides the interdisciplinary perspective in RC focusing on the applications of signal processing and machine learning (ML). We provide an account of various state-of-the-art algorithms while categorizing them into three stages in an RC framework: preprocessing, prediction, and postprocessing. RC has been known to be a highly data-driven problem. Huge volumes of seismic and well-log data are cleverly integrated by experts to decipher the subsurface properties. Some of the anomalies may lead to the existence of a potential reservoir. The signal processing tools are primarily required for information matching, preprocessing for noise and artifacts, and postprocessing for removing irregularities in the prediction, whereas the ML tools are required to map the seismic data to well logs. This article provides a comprehensive study on the recent advances in RC involving seismic volumes and well logs.

The elastic properties of subsurface media, such as density and P- and S-wave velocity, are essential for understanding the mechanical behavior of the subsurface as they reflect its physical and structural characteristics. Accurate elastic properties are increasingly critical for safety assessment, geological risk analysis, and reservoir characterization in subsurface applications. However, current data acquisition methods present complementary limitations: well-log data provide high-resolution and accurate elastic properties but offers only localized information due to spatial constraints, while seismic data covers regional areas but has lower resolution and accuracy. To address these limitations, this study develops a machine learning (ML) framework that integrates seismic and well-log data to improve the prediction accuracy of subsurface elastic properties. This study introduces a novel approach that integrates ML with Gaussian processes (GP), which allows not only elastic property prediction but also quantification of predictive uncertainty. The proposed approach was validated using well-log and post-stack seismic data from the Volve dataset. Five ML models were trained to predict density and P- and S-wave velocities, with the long short-term memory+GP model achieving superior performance among all tested models. The 3-D prediction capabilities were further validated by applying the trained model to a 3-D seismic cube from the Volve field, successfully estimating 3-D elastic properties and quantifying prediction uncertainty. While the approach improves uncertainty assessment, it should be noted that uncertainty quantification is often limited in highly heterogeneous zones, as prediction reliability is inherently dataset-dependent.

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

The transformation of seismic reflection data into quantitative rock properties can be very valuable in all phases of oil and gas exploration and production. In this study, public domain data from Australian offshore have been used to explain the logical workflow, which consists of systematic steps from seismic petrophysics to rock physics modeling and seismic inversion for quantitative rock property estimation. The application of seismic inversion technology offers many rewards, such as: better reservoir definition and management; better resource estimation; and reductions in uncertainty. The main benefit is that it improves direct and intangible interpretation of seismic data to provide meaningful geological boundaries in the subsurface. In order to provide the reliable estimate of rock properties for reservoir modeling the workflow is tested rigorously and divided into three categories which are based on the basic inversion types. The results reveal that relative impedance inversion should be performed first, which then followed by revision of seismic interpretation on impedance data. Full bandwidth rock properties are estimated by deterministic inversion. The results can be improved by several iterations of well to seismic tie, wavelet estimation, and low frequency models. As resolution with accuracy has always been challenging, the stochastic inversion approach is trailered for reservoir characterization and high resolution rock properties have been predicted. This produces a number of possible rock property models, as well as litho facies models and the results can be optionally constrained by the well data. It can be concluded that, to some degree, stochastic inversion is able to overcome the limited seismic bandwidth by integrating the rock physics properties of different lithologies. The examples of seismic inversion are discussed to demonstrate the significant benefits can be obtained by following an optimized workflow that is tailored to deal with the uncertainties that impact the end product. Introduction Seismic surveys are routinely performed to gather information about the geology of hydrocarbon fields. Seismic data, even when it has relatively low resolutions, can still deliver a structural model for the reservoir. The availability and coverage area of the data provides valuable information to constrain the reservoir model. Geophysicists are now able to extract greater quantitative information about reservoir rocks and fluid parameters from seismic data by working backwards using seismic inversion methods. Described as the flip-side of forward modeling, seismic inversion is the process of characterizing rocks and fluids that have produced the seismic data. In a sense, the process involves trying to determine the input (rock properties) by looking at the output (seismic data). It starts with actual measured data, removes the wavelet and derives acoustic impedance from reflection coefficient (Figure-1) with a low frequency model to infer rock properties and deliver earth model.

Seimic impedance inversion based on semi-supervised learning

Most deconvolution algorithms try to transform the seismic wavelet into spikes by designing inverse filters that attempts to remove an estimated seismic wavelet from seismic data. Considering that seismic trace singularities are associated with acoustic impedance contrasts, and can be characterized by wavelet transform modulus maxima lines (WTMML), we show how to improve seismic resolution by using the wavelet transform. Specifically, we apply complex Morlet continuous wavelet transform (CWT) to each seismic trace and compute the WTMML‟s. Then, we reconstruct the seismic trace with the inverse continuous wavelet transform (ICWT) from the computed WTMML‟s with a slightly different complex Morlet wavelet than that used in the forward CWT. As the reconstruction process preserves amplitude and phase along different scales, or frequencies, the result resembles a deconvolution process. Using synthetic and real seismic data we show the effectiveness of the methodology on detecting seismic events associated with acoustic impedance changes.