Acoustic Impedance Inversion from Seismic Imaging Profiles Using Self Attention U-Net

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.

Multi-trace acoustic impedance inversion with multiplicative regularization

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

Deep learning neural networks offer some advantages over conventional methods in acoustic impedance inversion. Because labeled data may be difficult to obtain in realistic field data settings, it can be difficult to obtain high-accuracy inversion results. Some generative adversarial network (GAN)-based acoustic impedance inversion methods have been proposed to solve this problem. However, due to the existence of lateral discontinuity in inversion results of these GAN-based methods, inversion accuracy of these proposals is still not fully satisfactory. Therefore, to tackle the shortcomings of GAN, we develop an acoustic impedance inversion method based on dual Wasserstein GAN condition (dual-WGAN-c). Dual-WGAN-c can perform seismic inversion and forward calculation simultaneously and take the low-frequency information of acoustic impedance as conditional input to obtain accurate acoustic impedance inversion results in the case of insufficient labeled data. Through a data simulation experiment, compared with GAN-based seismic acoustic impedance inversion methods, dual-WGAN-c can obtain more accurate inversion results, with high robustness when the seismic data are noisy. Dual-WGAN-c also can obtain accurate results in acoustic impedance inversion of the recorded seismic data when one has insufficient labeled well-log data.

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

Inversion for acoustic impedance of a wall by using artificial neural network

Hydrocarbons are the main energy source in the world, especially in Indonesia, this is what makes hydrocarbons a natural resource that has been extensively explored to determine the presence of hydrocarbons. The exploration used is the Geophysics method, namely the seismic method and the well logging method, both methods are processed to provide an overview of the subsurface. The data processing technique used is acoustic impedance inversion modeling which aims to determine the characteristics of the reservoir based on changes in the acoustic impedance value in each layer. In this study using model-based acoustic impedance inversion using an artificial neural network (ANN) algorithm and the results obtained in the inversion analysis obtained an error of 0.002, so that the model can be used on seismic trace data to produce an acoustic impedance model. modeling section with a value of less than 5000 which may mean that there are hydrocarbons in the research location. Keywords: Artificial Neural Network, Hydrocarbons, Acoustic Impedance, Inversion.

Estimating Vsand and reservoir properties from seismic attributes and acoustic impedance inversion: A case study from the Mansuri oilfield, SW Iran

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.

The integration of geophysical data, especially 3-D seismic data, with well data can improve the spatial characterization of heterogeneous reservoirs.Various kind of geophysical surveys, such as 3-D seismic, VSP and crosswell seismic, have been carried out for four years at the central part of Amarume oil field in Yamagata prefecture, Japan to characterize the thin sandstone reservoirs.Model-based inversion was confirmed to bring more precise acoustic impedance information of subsurface layers than recursive inversion. So the model-based inversion was applied to three 2-D sections through wells which were selected from the 3-D seismic data volume. We got not only the distribution area of each sand-stone reservoir with lens-shape but also the information of impedance change within the same sand unit. This impedance change can be related to changes of rock properties and physical conditions in the reservoir. The acoustic impedance inversion is being applied to the whole 3-D seismic data.It is expected that geophysical data will play an important role to create models for hetergeneous reservoirs in the future.

Dynamic simulation of CO2 migration requires a variety of modeling parameters fed by geomechanical models. The confidence of these parameters of material groups such as porosity and permeability is crucial in achieving successful simulations. Based on the geomechanical and geophysical parameters, we estimated porosity distributions on the Paaratte Formation in the Otway site, one of the CO2 storage project in Australia. Considering the nonlinear relations between porosity logs and seismic data, we applied the neural network scheme that addresses the porosity value across a whole domain. With only one monitoring well and two injection wells at the site, seismic data are used to restore the spatial absence in porosity. The technique of the neural network was conducted based on the integration of the well logs to the seismic volume and the inversion of acoustic impedance. The results indicated that a correlation value of the well and the seismic tie is 75% and the value between the recorded and the estimated porosity is 87% on average. Further, the time slice maps of porosity at a depth of the injection interval demonstrated a CO2 plume developed in the Paaratte formation of the Otway site.

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

Seimic impedance inversion based on semi-supervised learning

Summary Seismic impedance inversion is a technique that converts seismic data interface information into stratigraphic information, serving as a bridge between seismic data, well logging, and geological information. Although the existing deep learning impedance inversion methods have improved inversion accuracy, they do not involve the quantitative evaluation of uncertainty in the inversion results. Based on these effects, we improved the existing CNN impedance inversion model by incorporating Bayesian theory and approximate Bayesian inference. We implemented two methods for impedance inversion: one based on a Bayesian convolution neural network (BCNN), and the other is a CNN based on Monte Carlo (MC) sampling and Dropout using approximate Bayesian inference. These methods allow for uncertainty modeling and incorporation of uncertainty into the inversion model. The uncertainty of the inversion results is quantified through the output probability distribution. The results of field data applications clarify the effectiveness and characteristics of the two methods. MC Dropout CNN method is superior in efficiency due to approximate theory, while BCNN shows advantages in accuracy, resolution, and uncertainty quantification.