MétaCan
Menu
Back to cohort
Record W4220670117 · doi:10.2118/208883-ms

Refracturing Candidate Selection in Tight Oil Reservoirs Using Hybrid Analysis of Data and Physics Based Models

2022· article· en· W4220670117 on OpenAlexaff
Die Hu, Zhengdong Lei, Stephen Cartwright, Steven Samoil, Siqi Xie, Zhangxin Chen

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicReservoir Engineering and Simulation Methods
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsData miningComputer scienceAnalytic hierarchy processOffset (computer science)Selection (genetic algorithm)EngineeringArtificial intelligenceOperations research

Abstract

fetched live from OpenAlex

Abstract Refracturing candidate selection problems can be solved via production statistics, virtual intelligence and type-curve matching, and these methods are mostly developed using data-based models. They unleash great power of data but have not considered the influence of geological distributions in physics-based models. This paper combines the strengths of data and physics based models and proposes a hybrid analysis method to improve and strengthen the current methods. Three criteria, production performance, a completion index and a geological distribution around an offset well, and their sub-criteria are selected to build an evaluation system for refracturing candidate wells. Field data is collected and processed to calculate a completion index and production performance. To quantify a geological distribution around a well, a history-matched reservoir simulation model is required. Besides, a graph theory algorithm, Dijkstra’s shortest path, is used to quantify the influence of geological distributions in 3D reservoir models on wells. An analytic hierarchy process and grey correlation analysis are then used to establish a multi-level evaluation system and determine and rank each individual strategic factor. Finally, datapoints are shown in a 3D coordinate system, and custom defined weights are used to calculate the final ranking of potential refracturing wells. In addition, the hybrid analysis is presented on our self-developed visualization platform. A history-matched reservoir simulation model from the Y284 tight oil reservoir is used as a study case. Eight refractured wells’ data is collected and analyzed. As a grey correlation analysis result, a sub-criteron of productivity performance, relative productivity, ranks the first, followed by cumulative liquid production. Completion and resistance rank third and fourth with a small gap. Based on the analysis results, an evaluation system is built up. 14 refracturing candidate wells are analyzed and ranked using the evaluation system. These wells are displayed in a 3D coordinate system, where x, y and z directions represent three criteria separately. Wells distributed in the first quadrant are regarded as optimum candidates to apply refracturing treatments. Correlations of evaluation factors and increased oil production after refracturing treatment are plotted to validate the method. This study explores how to conduct hybrid analysis in a selection workflow of refracturing candidate wells. Combing visualization, interpretability, robust foundation and understanding of reservoir models with accuracy and efficiency, data-driven artificial intelligence algorithms, the experiences distilled, and insights gained from this project show great potential to apply hybrid analysis as well as modelling in oil and gas industry.

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 categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.380
Threshold uncertainty score0.434

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
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 head0.052
GPT teacher head0.303
Teacher spread0.251 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations2
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicReservoir Engineering and Simulation MethodsFrench-language works237,207