scholarly journals Target-oriented time-lapse waveform inversion using deep learning assisted regularization

Geophysics ◽  
2021 ◽  
pp. 1-75
Author(s):  
Tariq Alkhalifah ◽  
Qiang Guo ◽  
Yuanyuan Li
Keyword(s):  
High Resolution ◽  
Waveform Inversion ◽  
Computational Cost ◽  
Time Lapse ◽  
Well Logs ◽  
Target Zone ◽  
Inversion Domain ◽  
Production Wells ◽  
Velocity Changes ◽  
Property Changes

Detection of the property changes in the reservoir during injection and production is important. However, the detection process is very challenging using surface seismic surveys because these property changes often induce subtle changes in the seismic signals. The quantitative evaluation of the subsurface property obtained by full waveform inversion (FWI) allows for better monitoring of these time-lapse changes. However, high-resolution inversion is usually accompanied with a large computational cost. Besides, the resolution of inversion is limited by the bandwidth and aperture of time-lapse seismic data. We apply a target-oriented strategy through seismic redatuming to reduce the computational cost by focusing our high-resolution delineation on a relatively small zone of interest. The redatuming technique generates time-lapse virtual data for the target-oriented inversion. Considering the injection and production wells are often present in the target zone, we can incorporate the well velocity information to the time-lapse inversion by using regularization to complement the resolution and illumination at the reservoir. We use a deep neural network (DNN) to learn the statistical relationship between the inverted model and the facies interpreted from well logs. The trained network is employed to map the property changes extracted from the wells to the target inversion domain. We then perform another time-lapse inversion, in which we fit the predicted data difference to the redatumed one from observation, as well as fit the model to the predicted velocity changes. The numerical results demonstrate that the proposed method is capable of inverting for the time-lapse property changes effectively in the target zone by incorporating the learned model information from well logs.

Central-difference time-lapse 4D seismic full waveform inversion

Geophysics ◽  
2020 ◽  
pp. 1-42
Author(s):  
Wei Zhou ◽  
David Lumley
Keyword(s):  
High Resolution ◽  
Seismic Velocity ◽  
Waveform Inversion ◽  
Computational Cost ◽  
Time Lapse ◽  
Full Waveform Inversion ◽  
Central Difference ◽  
Data Set ◽  
Velocity Inversion ◽  
Full Waveform

Repeated seismic surveys contain valuable information regarding time-lapse (4D) changes in the subsurface. Full waveform inversion (FWI) of seismic data can provide high-resolution estimates of 4D change. We propose a new time-domain 2D acoustic time-lapse FWI method based on the central-difference scheme with higher-order mathematical accuracy and reasonable computational cost. The method is rigorously tested on the SEAM 4D time-lapse model and OBN data set. High-resolution 4D velocity estimates are obtained, which show strong ~25% velocity increases in a 75 m-thick gas layer, as well as weaker (5%) changes due to geomechanical effects, the latter of which are poorly recovered by the conventional parallel 4D FWI method. We also perform the bootstrap 4D FWI method and the result is contaminated by strong artifacts in the underburden, whereas the proposed central-difference method has fewer underburden artifacts allowing more reliable interpretations. In this realistic case study, acoustic FWI erroneously overfits the elastic scattered waves, and cannot fit the strong elastic 4D coda waves at all. The results show that the proposed central-difference 4D FWI method within the acoustic approximation may be a practical solution for time-lapse seismic velocity inversion.

Combining reflection and transmission information in time-lapse velocity inversion: A new hybrid approach

Geophysics ◽  
2019 ◽  
Vol 84 (4) ◽  
pp. R601-R611 ◽  
Author(s):  
Maria Kotsi ◽  
Jonathan Edgar ◽  
Alison Malcolm ◽  
Sjoerd de Ridder
Keyword(s):  
Waveform Inversion ◽  
Hybrid Approach ◽  
Time Lapse ◽  
Velocity Model ◽  
Nonlinear Inversion ◽  
Image Domain ◽  
Velocity Inversion ◽  
Reflected Waves ◽  
Deep Diving ◽  
Velocity Changes

Full-waveform inversion (FWI) uses the information of the full wavefield to deliver high-resolution images of the subsurface. Conventional time-lapse FWI primarily uses the transmitted component (diving waves) of the wavefield to reconstruct the low-wavenumber component of the velocity model. This requires large-offset surveys and low-frequency data. When the target of interest is deep, diving waves cannot reach the target and FWI will be dominated by the reflected component of the wavefield. Consequently, the retrieved model resembles a least-squares migration instead of a velocity model. Image-domain methods, especially image-domain wavefield tomography (IDWT), have been developed to obtain a model of time-lapse velocity changes in deeper targets using reflected waves. The method is able to recover models of deep targets. However, it also tends to obtain smeared time-lapse velocity changes. We have developed a form of time-lapse waveform inversion that we call dual-domain time-lapse waveform inversion (DDWI), whose objective function joins FWI and IDWT, combining information from the diving waves in the data-domain FWI term with information from the reflected waves in the image-domain IDWT term. During the nonlinear inversion, the velocity model is updated using constraints from both terms simultaneously. Similar to sequential time-lapse waveform inversion, we start the time-lapse inversion from a baseline model recovered with FWI. We test DDWI on a variety of synthetic models of increasing complexity and find that it can recover time-lapse velocity changes more accurately than when both methods are used independently or sequentially.

Time-lapse inverse theory with applications

Geophysics ◽  
2016 ◽  
Vol 81 (6) ◽  
pp. R485-R501 ◽  
Author(s):  
Musa Maharramov ◽  
Biondo L. Biondi ◽  
Mark A. Meadows
Keyword(s):  
Waveform Inversion ◽  
Significant Risk ◽  
Time Lapse ◽  
Long Wavelength ◽  
Full Waveform ◽  
Total Variation Model ◽  
Velocity Anomalies ◽  
Velocity Changes ◽  
Primary Focus ◽  
Production Effects

Compaction in the reservoir overburden can impact production facilities and lead to a significant risk of well-bore failures. Prevalent practices of time-lapse seismic processing of 4D data above compacting reservoirs rely on picking time displacements and converting them into estimated velocity changes and subsurface deformation. This approach relies on prior data equalization and requires a significant amount of manual interpretation and quality control. We have developed methods for automatic detection of production-induced subsurface velocity changes from seismic data. We have evaluated a time-lapse inversion technique based on a simultaneous regularized full-waveform inversion (FWI) of multiple surveys. In our approach, baseline and monitor surveys are inverted simultaneously with a model-difference regularization penalizing nonphysical differences in the inverted models that are due to survey or computational repeatability issues. The primary focus of our work was the inversion of long-wavelength “blocky” changes in the subsurface model, and this was achieved using a phase-only FWI with a total-variation model-difference regularization. However, we have developed a multiscale extension of our method for recovering long- and short-wavelength production effects. We have developed a theoretical foundation of our method and analyzed its sensitivity to a realistic 1%–2% velocity deformation. The method was applied in a study of overburden dilation above the Gulf of Mexico Genesis field and recovered blocky negative-velocity anomalies above compacting reservoirs.

Time-lapse velocity imaging via deep learning

2019 ◽  
Author(s):  
Congcong Yuan ◽  
Xiong Zhang ◽  
Xiaofeng Jia ◽  
Jie Zhang
Keyword(s):  
Iterative Methods ◽  
Network Architecture ◽  
Waveform Inversion ◽  
Time Lapse ◽  
Velocity Model ◽  
Double Difference ◽  
Target Velocity ◽  
Waveform Data ◽  
Processing Cost ◽  
Velocity Changes

Summary It is of great significance and a great challenge to quickly and effectively monitor subsurface time-lapse velocities in the earth. Over the past few decades, regularized iterative methods, such as traveltime and waveform inversions, have been presented to monitor velocity changes. Due to high processing cost, these iterative methods have been hardly employed in practice to investigate the subsurface velocity changes in real time. In this study, we propose a new time-lapse imaging technique that effectively eliminates these limitations and directly produces accurate velocity changes from the time-lapse data. The approach uses a fully convolutional neural network (FCN) to perform the inverse problem. The network architecture consists of a contracting path to quickly extract the features of waveform data and a symmetric expanding path to yield an accurate velocity model. With the known baseline velocity and data, we cast a mapping between time-lapse data and target velocity changes via the proposed FCN algorithm. Along with the observed time-lapse data, this mapping will generate a predictive estimation of the target velocity changes. We demonstrate the efficiency and accuracy of our approach in three 2D synthetic tests. The proposed technique is able to invert the velocity changes successfully with much higher efficiency than the regular double-difference full waveform inversion.

Target-oriented full-waveform inversion using Marchenko redatumed wavefields

2020 ◽  
Vol 223 (2) ◽  
pp. 792-810
Author(s):  
Tianci Cui ◽  
James Rickett ◽  
Ivan Vasconcelos ◽  
Ben Veitch
Keyword(s):  
High Resolution ◽  
Waveform Inversion ◽  
Computational Cost ◽  
P Wave ◽  
Full Waveform Inversion ◽  
High Resolution Imaging ◽  
Multiple Reflections ◽  
Full Waveform ◽  
Resolution Imaging ◽  
Full Domain

SUMMARY Full-waveform inversion (FWI) has demonstrated increasing success in estimating medium properties, but its computational cost still poses challenges in moving towards high-resolution imaging of targets at depth. Here, we propose a target-oriented FWI method that inverts for the medium parameters confined within an arbitrary region of interest. Our method is novel in terms of both local wavefield modelling and data redatuming, in order to build a target-oriented objective function which is sensitive to the target medium only without further assumptions about the medium outside. Based on the convolution-type representation theorem, our local forward modelling operator propagates wavefields within the target medium only while providing full acoustic coupling between the target medium and the surrounding geology. A key requirement of our local FWI method is that the subsurface wavefields surrounding and inside the target be as accurate as possible. As such, the subsurface wavefields are retrieved by the Marchenko method, which can redatum the single-sided surface reflection data to the target zone while preserving both primary and multiple reflections, with minimal a priori knowledge of the full-domain medium. Given a sufficiently accurate initial velocity macromodel, our numerical examples show that our local FWI method resolves the reservoir zone of a 2-D Barrett Unconventional P-wave velocity model much more efficiently than the conventional full-domain FWI without significantly sacrificing accuracy. Our method may further enable FWI approaches to high-resolution imaging of subsurface targets.

scholarly journals Using image warping for time-lapse image domain wavefield tomography

Geophysics ◽  
2014 ◽  
Vol 79 (3) ◽  
pp. WA141-WA151 ◽  
Author(s):  
Di Yang ◽  
Alison Malcolm ◽  
Michael Fehler
Keyword(s):  
Cost Function ◽  
Oil And Gas ◽  
Waveform Inversion ◽  
Time Lapse ◽  
Gas Production ◽  
Reservoir Properties ◽  
Image Domain ◽  
Seismic Waveform ◽  
Realistic Situation ◽  
Velocity Changes

Time-lapse seismic data are widely used for monitoring subsurface changes. A quantitative assessment of how reservoir properties have changed allows for better interpretation of fluid substitution and fluid migration during processes such as oil and gas production and carbon sequestration. Full-waveform inversion (FWI) has been proposed as a way to retrieve quantitative estimates of subsurface properties through seismic waveform fitting. However, for some monitoring systems, the offset range versus depth of interest is not large enough to provide information about the low-wavenumber component of the velocity model. We evaluated an image domain wavefield tomography (IDWT) method using the local warping between baseline and monitor images as the cost function. This cost function is sensitive to volumetric velocity anomalies, and it is capable of handling large velocity changes with very limited acquisition apertures, where traditional FWI fails. We described the theory and workflow of our method. Layered model examples were used to investigate the performance of the algorithm and its robustness to velocity errors and acquisition geometry perturbations. The Marmousi model was used to simulate a realistic situation in which IDWT successfully recovers time-lapse velocity changes.

Towards real-time monitoring: data assimilated time-lapse full waveform inversion for seismic velocity and uncertainty estimation

2020 ◽  
Vol 223 (2) ◽  
pp. 811-824
Author(s):  
Chao Huang ◽  
Tieyuan Zhu
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
Waveform Inversion ◽  
Time Lapse ◽  
Uncertainty Estimation ◽  
Covariance Matrices ◽  
Full Waveform Inversion ◽  
Full Waveform ◽  
Velocity Changes ◽  
Over Time

SUMMARY Rapid development of time-lapse seismic monitoring instrumentations has made it possible to collect dense time-lapse data for tomographically retrieving time-lapse (even continuous) images of subsurface changes. While traditional time-lapse full waveform inversion (TLFWI) algorithms are designed for sparse time-lapse surveys, they lack of effective temporal constraint on time-lapse data, and, more importantly, lack of the uncertainty estimation of the TLFWI results that is critical for further interpretation. Here, we propose a new data assimilation TLFWI method, using hierarchical matrix powered extended Kalman filter (HiEKF) to quantify the image uncertainty. Compared to existing Kalman filter algorithms, HiEKF allows to store and update a data-sparse representation of the cross-covariance matrices and propagate model errors without expensive operations involving covariance matrices. Hence, HiEKF is computationally efficient and applicable to 3-D TLFWI problems. Then, we reformulate TLFWI in the framework of HiEKF (termed hereafter as TLFWI-HiEKF) to predict time-lapse images of subsurface spatiotemporal velocity changes and simultaneously quantify the uncertainty of the inverted velocity changes over time. We demonstrate the validity and applicability of TLFWI–HiEKF with two realistic CO2 monitoring models derived from Frio-II and Cranfield CO2 injection sites, respectively. In both 2-D and 3-D examples, the inverted high-resolution time-lapse velocity results clearly reveal a continuous velocity reduction due to the injection of CO2. Moreover, the accuracy of the model is increasing over time by assimilating more time-lapse data while the standard deviation is decreasing over lapsed time. We expect TLFWI-HiEKF to be equipped with real-time seismic monitoring systems for continuously imaging the distribution of subsurface gas and fluids in the future large-scale CO2 sequestration experiments and reservoir management.

Integrated kinematic time-lapse inversion workflow leveraging full-waveform inversion and machine learning

2019 ◽  
Vol 38 (12) ◽  
pp. 943-948 ◽  
Author(s):  
Musa Maharramov ◽  
Bram Willemsen ◽  
Partha S. Routh ◽  
Emily F. Peacock ◽  
Mark Froneberger ◽  
...  
Keyword(s):  
Machine Learning ◽  
Waveform Inversion ◽  
Time Lapse ◽  
Learning Technologies ◽  
Full Waveform Inversion ◽  
Long Wavelength ◽  
Full Waveform ◽  
Velocity Changes ◽  
Image Difference

We demonstrate that a workflow combining emergent time-lapse full-waveform inversion (FWI) and machine learning technologies can address the demand for faster time-lapse processing and analysis. During the first stage of our proposed workflow, we invert long-wavelength velocity changes using a tomographically enhanced version of multiparameter simultaneous reflection FWI with model-difference regularization. Short-wavelength changes are inverted during the second stage of the workflow by a specialized high-resolution image-difference tomography algorithm using a neural network. We discuss application areas for each component of the workflow and show the results of a West Africa case study.

Sign in / Sign up

Export Citation Format

Share Document