Integration of an Iterative Update of Sparse Geologic Dictionaries with ES-MDA for History Matching of Channelized Reservoirs

Kim, Sung-Il; Min, Baehyun; Lee, Kyungbook; Jeong, Hoonyoung

doi:10.1155/2018/1532868

Cited by 16 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DCT is also used to extract the main information of a static model in a history matching area [27][28][29][30][31][32][33][34][35]. After original data are transformed to coefficients of discrete cosine functions, the coefficients are arranged in descending order of frequencies of cosine functions.…”

Section: Combined Distancementioning

confidence: 99%

“…The selection of a subset of DCT coefficients depends on the objective of the research. For example, to characterize channel reservoirs, several papers applied DCT to permeability data to extract only the main channel trends in the ensemble models with low frequencies' coefficients [27][28][29][30][31][32]34,35]. The channel trends in reservoirs can be described with only a small number of coefficients.…”

Section: + ( − 3) =mentioning

confidence: 99%

See 1 more Smart Citation

Efficient Assessment of Reservoir Uncertainty Using Distance-Based Clustering: A Review

et al. 2019

Self Cite

View full text Add to dashboard Cite

This paper presents a review of 71 research papers related to a distance-based clustering (DBC) technique for efficiently assessing reservoir uncertainty. The key to DBC is to select a few models that can represent hundreds of possible reservoir models. DBC is defined as a combination of four technical processes: distance definition, distance matrix construction, dimensional reduction, and clustering. In this paper, we review the algorithms employed in each step. For distance calculation, Minkowski distance is recommended with even order due to sign problem. In the case of clustering, K-means algorithm has been commonly used. DBC has been applied to various reservoir types from channel to unconventional reservoirs. DBC is effective for unconventional resources and enhanced oil recovery projects that have a significant advantage of reducing the number of reservoir simulations. Recently, DBC studies have been performed with deep learning algorithms for feature extraction to define a distance and for effective clustering.

show abstract

Section: Combined Distancementioning

confidence: 99%

Section: + ( − 3) =mentioning

confidence: 99%

Efficient Assessment of Reservoir Uncertainty Using Distance-Based Clustering: A Review

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…With this in mind, one drawback of K-SVD is its large size of sparse geologic dictionaries (Khaninezhad et al, 2012). References from the literature show that sparse coding implementation with a transformation of parameter space could significantly reduce both computational complexity and costs that are simultaneously required for model calibration (Khaninezhad et al, 2012, Kim et al, 2018, Sana et al, 2016.…”

Section: K-svd Algorithm For Obtaining a Dictionarymentioning

confidence: 99%

“…They incorporate a greedy algorithm, in particular, orthogonal matching pursuit (OMP), for the sparse representations of the static properties (permeability field) which then is updated by ES-MDA. In a similar but slightly different approach, Kim et al (2018) couple an iterative form of sparse coding in a transformed space with ES-MDA to construct a set of geologically plausible models that preserve the non-Gaussian distribution of lithofacies in a synthetic channelised reservoir. DCT of sand-shale facies is then followed by repeated K-SVD steps to construct sparse geologic dictionaries.…”

Section: Introductionmentioning

confidence: 99%

4D Seismic History Matching Incorporating Unsupervised Learning

Etienam

2019

SPE Europec Featured at 81st EAGE Conference and Exhibition

View full text Add to dashboard Cite

The work discussed and presented in this paper focuses on the history matching of reservoirs by integrating 4D seismic data into the inversion process using machine learning techniques. A new integrated scheme for the reconstruction of petrophysical properties with a modified Ensemble Smoother with Multiple Data Assimilation (ES-MDA) in a synthetic reservoir is proposed. The permeability field inside the reservoir is parametrised with an unsupervised learning approach, namely K-means with Singular Value Decomposition (K-SVD). This is combined with the Orthogonal Matching Pursuit (OMP) technique which is very typical for sparsity promoting regularisation schemes. Moreover, seismic attributes, in particular, acoustic impedance, are parametrised with the Discrete Cosine Transform (DCT). This novel combination of techniques from machine learning, sparsity regularisation, seismic imaging and history matching aims to address the ill-posedness of the inversion of historical production data efficiently using ES-MDA. In the numerical experiments provided, I demonstrate that these sparse representations of the petrophysical properties and the seismic attributes enables to obtain better production data matches to the true production data and to quantify the propagating waterfront better compared to more traditional methods that do not use comparable parametrisation techniques.

show abstract

“…However, it takes preprocessing time to construct a set of prototype realizations called a dictionary. As a remedy, a combination of DCT and iterative K-SVD was proposed to complement the limitations of both methods [23]. Canchumuni et al [18] coupled AE with ES-MDA for an efficient parameterization and compared its performance with that of ES-MDA coupled with principal component analysis.…”

Section: Introductionmentioning

confidence: 99%

History Matching of a Channelized Reservoir Using a Serial Denoising Autoencoder Integrated with ES-MDA

et al. 2019

Self Cite

View full text Add to dashboard Cite

For an ensemble-based history matching of a channelized reservoir, loss of geological plausibility is challenging because of pixel-based manipulation of channel shape and connectivity despite sufficient conditioning to dynamic observations. Regarding the loss as artificial noise, this study designs a serial denoising autoencoder (SDAE) composed of two neural network filters, utilizes this machine learning algorithm for relieving noise effects in the process of ensemble smoother with multiple data assimilation (ES-MDA), and improves the overall history matching performance. As a training dataset of the SDAE, the static reservoir models are realized based on multipoint geostatistics and contaminated with two types of noise: salt and pepper noise and Gaussian noise. The SDAE learns how to eliminate the noise and restore the clean reservoir models. It does this through encoding and decoding processes using the noise realizations as inputs and the original realizations as outputs of the SDAE. The trained SDAE is embedded in the ES-MDA. The posterior reservoir models updated using Kalman gain are imported to the SDAE which then exports the purified prior models of the next assimilation. In this manner, a clear contrast among rock facies parameters during multiple data assimilations is maintained. A case study at a gas reservoir indicates that ES-MDA coupled with the noise remover outperforms a conventional ES-MDA. Improvement in the history matching performance resulting from denoising is also observed for ES-MDA algorithms combined with dimension reduction approaches such as discrete cosine transform, K-singular vector decomposition, and a stacked autoencoder. The results of this study imply that a well-trained SDAE has the potential to be a reliable auxiliary method for enhancing the performance of data assimilation algorithms if the computational cost required for machine learning is affordable.

show abstract

Integration of an Iterative Update of Sparse Geologic Dictionaries with ES-MDA for History Matching of Channelized Reservoirs

Cited by 16 publications

References 40 publications

Efficient Assessment of Reservoir Uncertainty Using Distance-Based Clustering: A Review

Efficient Assessment of Reservoir Uncertainty Using Distance-Based Clustering: A Review

4D Seismic History Matching Incorporating Unsupervised Learning

History Matching of a Channelized Reservoir Using a Serial Denoising Autoencoder Integrated with ES-MDA

Contact Info

Product

Resources

About