MétaCan
Menu
Back to cohort
Record W4405367314 · doi:10.2118/223954-pa

Completion Design Optimization as a Function of Reservoir Quality in Tight Reservoirs: A Big Data Approach

2024· article· en· W4405367314 on OpenAlexaffabout
Tamer Moussa, Hassan Dehghanpour

Bibliographic record

VenueSPE Journal · 2024
Typearticle
Languageen
FieldEngineering
TopicHydraulic Fracturing and Reservoir Analysis
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsWorkflowTight gasBig dataKrigingPetroleum engineeringHydraulic fracturingGeologyComputer scienceData miningMachine learningDatabase

Abstract

fetched live from OpenAlex

Summary Over the past decade, more than 40,000 multifractured horizontal wells (MFHWs) were completed in the Western Canada Sedimentary Basin (WCSB), making Canada the third largest oil exporter in 2022. However, this process consumed more than 56 billion gallons of water, with more than 30 billion gallons unrecovered—equivalent to the annual water consumption of a city of 1 million for nearly 5 years. This raises concerns about water use efficiency in fracturing operations. Can big data mining reveal the relationship between reservoir quality, fracturing design parameters, and process efficiency? This research aims to develop a hybrid analytical and machine learning (ML) workflow to optimize completion design as a function of reservoir quality in tight reservoirs. To achieve this objective, we analyze data from more than 14,000 wells in the Montney formation. Using core analysis and well log data, we develop a support vector machine (SVM) to predict permeability and a fuzzy clustering model to estimate fracturability. We categorize Montney’s lithology through hierarchical clustering. With 3D kriging interpolation, we fill missing data and create high-resolution 3D petrophysical maps, which help derive a reservoir quality index (RQI) map to identify the sweet spots for completing new wells. We introduce a stage placement efficiency (SPE) metric to evaluate fracture stage placements in-line with the RQI. Finally, we develop neural network–based proxies that predict well performance based on reservoir quality, geomechanical properties, and completion design, incorporating more than 40 completion parameters, the RQI, and historical production data. The results reveal a higher degree of homogeneity in the upper Montney compared to the middle and lower segments. Generally, completion design parameters significantly impact MFHW productivity more than formation characteristics. Applying the proposed proxy to Montney-oil MFHWs could increase fracturing water recovery by 94.4%, reduce injected water volume by 22%, and boost cumulative oil production by 37.9%. The proxy aims to enhance fracturing water efficiency. A 1% reduction in freshwater consumption in the WCSB could save more than 100 million gallons of fresh water and cut CO2 emissions by up to 2,000 tons, equivalent to removing more than 1,000 gasoline cars from Canadian roads.

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)0.002
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: none
Teacher disagreement score0.952
Threshold uncertainty score0.481

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
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 integrity0.0000.001
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 head0.101
GPT teacher head0.300
Teacher spread0.199 · 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

Citations3
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueSPE JournalSame topicHydraulic Fracturing and Reservoir AnalysisFrench-language works237,207