Surrogate permeability modelling of low-permeable rocks using convolutional neural networks

Tian, Jianwei; Qi, Chongchong; Sun, Yingfeng; Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬, Zaher Mundher

doi:10.1016/j.cma.2020.113103

Cited by 44 publications

(19 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other recent applications of deep learning in subsurface flow settings include the use of a CNN-based surrogate model to predict permeability in tight rocks with strong heterogeneity [16], and the use of neural networks in the context of multicomponent thermodynamic flash calculations [17]. The latter development could be quite useful in compositional reservoir simulation, as a substantial fraction of the computational effort is often associated with the phase equilibria calculations.…”

Section: Introductionmentioning

confidence: 99%

A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

Tang

Liu

Durlofsky

2020

Journal of Computational Physics

249

View full text Add to dashboard Cite

A deep-learning-based surrogate model is developed and applied for predicting dynamic subsurface flow in channelized geological models. The surrogate model is based on deep convolutional and recurrent neural network architectures, specifically a residual U-Net and a convolutional long short term memory recurrent network. Training samples entail global pressure and saturation maps, at a series of time steps, generated by simulating oil-water flow in many (1500 in our case) realizations of a 2D channelized system. After training, the 'recurrent R-U-Net' surrogate model is shown to be capable of accurately predicting dynamic pressure and saturation maps and well rates (e.g., time-varying oil and water rates at production wells) for new geological realizations. Assessments demonstrating high surrogatemodel accuracy are presented for an individual geological realization and for an ensemble of 500 test geomodels. The surrogate model is then used for the challenging problem of data assimilation (history matching) in a channelized system. For this study, posterior reservoir models are generated using the randomized maximum likelihood method, with the permeability field represented using the recently developed CNN-PCA parameterization. The flow responses required during the data assimilation procedure are provided by the recurrent R-U-Net. The overall approach is shown to lead to substantial reduction in prediction uncertainty. High-fidelity numerical simulation results for the posterior geomodels (generated by the surrogate-based data assimilation procedure) are shown to be in essential agreement with the recurrent R-U-Net predictions. The accuracy and dramatic speedup provided by 1 arXiv:1908.05823v1 [cs.LG] 16 Aug 2019 the surrogate model suggest that it may eventually enable the application of more formal posterior sampling methods in realistic problems. our case), this surrogate model can provide flow predictions in close agreement with the underlying flow simulator, but with a significant reduction in computational cost. Thus this approach enables the application of accurate but computationally demanding inverse modeling procedures.There has been extensive research on constructing surrogate models for subsurface flow prediction. These can be generally classified, based on the mathematical formulation, into physics-based and data-driven procedures (though these categories are not mutually exclusive). The physics-based methods typically neglect or simplify physical or numerical aspects of the problem, through, for example, reduced-physics modeling, coarse-grid modeling, or proper orthogonal decomposition (POD) based reduced-order modeling (ROM). A variety of POD-based ROMs, in which the state variables and the system of equations are projected into low-dimensional space and then solved, have been applied for a range of subsurface flow problems [1, 2, 3, 4, 5]. These ROMs can be effective, although they are generally only accurate when new (test) runs are sufficiently 'close' to training runs. In addition, the applicat...

show abstract

Section: Introductionmentioning

confidence: 99%

A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

Tang

Liu

Durlofsky

2020

Journal of Computational Physics

249

View full text Add to dashboard Cite

show abstract

“…For future research, the permeability and saturation index should be quantified using machine learning models, which could remarkably contribute to this research domain through new soft computing technology (Tian et al, 2020a(Tian et al, , 2020bYaseen et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

Effect of Water Flooding on Oil Reservoir Permeability: Saturation Index Prediction Model for Giant Oil Reservoirs, Southern Iraq

Awadh

Al-Mimar

Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬

2021

Nat Resour Res

Self Cite

View full text Add to dashboard Cite

This research was conducted on five oilfields in the Mishrif reservoir, southern Iraq, to illustrate the effects of permeability on the damage caused by the injection of river water into the oilfield. Oilfield flooding has dramatically changed the pH and brine chemistry of the reservoir and resulted in the deposition of carbonates and native sulfur. The air permeability test and scanning electron microscope (SEM) analysis revealed how the precipitated minerals and materials (e.g., residual heavy oil, asphaltene, wax, native sulfur and authigenic and diagenetic clay minerals) reduced the permeability by lining the pore necks. The PHREEQC software and saturation index (SI) model revealed several types of porelining scales formed in a porous matrix. The SI model indicates that barite, celestite, calcite and pyrite are common scales lining the pore spaces, which precipitated in response to the injection of sulfate-and carbonate-rich river water into an oil well. This research generated useful findings that can be taken into consideration for future oil production worldwide. Additionally, the permeability values were used as evidence for discrimination of sedimentary environment, particularly reef and non-reef facies.

show abstract

Section: Introductionmentioning

confidence: 99%

“…These methods have successfully replicated forward model results with dramatic reductions in computational cost, but have not been applied directly to experimentally constrained permeability inversion tasks. At the pore scale, CNNs have been used to determine the average permeability or dispersion of a geologic sample from a pore-scale digital rock image (Kamrava et al, 2021;Sudakov et al, 2019;Tian et al, 2020). These digital workflows-reviewed in detail by Y. D. Wang et al (2021)-are a promising avenue for experiment-free parameterization of flow and transport properties in geologic materials; however, they require repeated discrete analysis to characterize permeability spatial variation at the continuum scale.…”

mentioning

confidence: 99%

Three‐Dimensional Permeability Inversion Using Convolutional Neural Networks and Positron Emission Tomography

Huang

Kurotori

Pini

et al. 2022

Water Resources Research

View full text Add to dashboard Cite

Quantification of heterogeneous multiscale permeability in geologic porous media is key for understanding and predicting flow and transport processes in the subsurface. Recent utilization of in situ imaging, specifically positron emission tomography (PET), enables the measurement of three‐dimensional (3‐D) time‐lapse radiotracer solute transport in geologic media. However, accurate and computationally efficient characterization of the permeability distribution that controls the solute transport process remains challenging. Leveraging the relationship between local permeability variation and solute advection behavior, an encoder‐decoder based convolutional neural network (CNN) is implemented as a permeability inversion scheme using a single PET scan of a radiotracer pulse injection experiment as input. The CNN can accurately capture the 3‐D spatial correlation between the permeability and the radiotracer solute arrival time difference maps in geologic cores. We first test the inversion accuracy using synthetic test datasets and then test the accuracy on a suite of experimental PET imaging datasets acquired on four different geologic cores. The network‐predicted permeability maps from the geologic cores are used to parameterize forward numerical models that are directly compared with the experimental PET imaging data. The results indicate that a single trained network can generate robust 3‐D permeability inversion maps in seconds. Numerical models parameterized with these permeability maps closely capture the experimentally observed solute arrival time behavior. This work provides an unprecedented approach for efficiently characterizing multiscale permeability heterogeneity in complex geologic samples.

show abstract

Surrogate permeability modelling of low-permeable rocks using convolutional neural networks

Cited by 44 publications

References 56 publications

A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

Effect of Water Flooding on Oil Reservoir Permeability: Saturation Index Prediction Model for Giant Oil Reservoirs, Southern Iraq

Three‐Dimensional Permeability Inversion Using Convolutional Neural Networks and Positron Emission Tomography

Contact Info

Product

Resources

About