MétaCan
Menu
Back to cohort
Record W2801853284 · doi:10.2118/190019-ms

Training-Image Assisted History Matching of Complex Multiple-Point Statistical Facies Models: A Pattern-Based Approach

2018· article· en· W2801853284 on OpenAlexfundno aff
Mohammad‐Reza M. Khaninezhad, Azarang Golmohammadi, Behnam Jafarpour

Bibliographic record

VenueSPE Western Regional Meeting · 2018
Typearticle
Languageen
FieldEngineering
TopicReservoir Engineering and Simulation Methods
Canadian institutionsnot available
FundersEnergi Simulation
KeywordsComputer scienceAlgorithmNonlinear systemFaciesMinificationArtificial intelligenceMathematical optimizationPattern recognition (psychology)MathematicsGeology

Abstract

fetched live from OpenAlex

Abstract Traditional geostatistical methods that rely on two-point statistics (i.e., variogram models) to describe the spatial variability in rock properties are not appropriate for representing the spatial continuity patterns associated with complex geologic objects (e.g., curvilinear fluvial patterns and turbidite systems). Modern geostatistical techniques are developed to simulate multiple-point statistical (MPS) patterns from a training image (TI), as a conceptual model of geologic continuity, to generate model realizations with complex geologic connectivity. A major difficulty in using MPS methods is related to conditioning the simulation results on nonlinear dynamic production data. We develop a pattern-based model calibration approach for conditioning MPS-based facies models on nonlinear flow data. The formulation begins with defining a minimization problem in which the mismatch between predicted and observed production data is minimized. Since facies distributions are discrete variables, we use a parameterization method to transform them into a small number of continuous parameters that can be updated using gradient-based minimization. For this purpose, k-SVD sparse dictionary learning is adopted to approximate the connectivity patterns in the distribution of facies models. Because of the approximation involved in the k-SVD parameterization, an additional step is introduced, after each iteration, to map the resulting continuous models to the TI. To implement the mapping, a local search template is used to scan the TI to find local discrete patterns with smallest distances from the corresponding local patterns in the continuous solution. This process is repeated for all the grid cells in the continuous solution and the resulting local patterns are stored. To estimate the facies type in each grid cell, the collected patterns that intersect with any given cell are used to find the facies type with the highest frequency and assign it to that cell. Once the discrete solution is identified, it is passed to the continuous minimization problem to serve as a regularization term, for the next update iteration. The process is repeated until the discrete solution provides an acceptable match to the data. Numerical experiments are presented to evaluate the performance of the proposed approach for facies calibration in complex fluvial systems. The results suggest that the developed method presents a promising pattern-based approach for integration of production data into MPS-based facies models.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.578
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.153
GPT teacher head0.301
Teacher spread0.148 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueSPE Western Regional MeetingSame topicReservoir Engineering and Simulation MethodsFrench-language works237,207