MétaCan
Menu
Back to cohort
Record W2057854609 · doi:10.2118/168978-ms

Probabilistic Forecasting of Horizontal Well Performance in Unconventional Reservoirs Using Publicly-Available Completion Data

2014· article· en· W2057854609 on OpenAlexaboutno aff
G. W. Voneiff, Seyed Hamidreza Sadeghi, P. A. Bastian, Benjamin Wolters, J. E. Jochen, B. Chow, King Lau Chow, M. Gatens

Bibliographic record

VenueSPE Unconventional Resources Conference · 2014
Typearticle
Languageen
FieldEngineering
TopicHydraulic Fracturing and Reservoir Analysis
Canadian institutionsnot available
Fundersnot available
KeywordsProbabilistic logicComputer scienceReservoir modelingWorkflowData miningMultivariate statisticsRegressionRange (aeronautics)Statistical modelUnconventional oilMachine learningOil shaleArtificial intelligencePetroleum engineeringGeologyEngineeringStatisticsMathematics

Abstract

fetched live from OpenAlex

Abstract In this paper, we present a methodology to predict the performance of horizontal gas wells in unconventional reservoirs using publicly available completion data. Our process combines public domain data with statistical analysis and probabilistic simulation methods to forecast well performance without a detailed reservoir characterization. We have tested our methodology using a 425-well dataset from the unconventional Montney resource play in British Columbia, Canada. We believe this workflow can be applied to other resource plays with similar data. In our SPE Paper 167154 [1], we determined the sensitivity of production performance to completion parameters using multivariate regression analysis on the same 425-well dataset from the Montney formation. We found that the number of fracture stages and the number of perforation clusters per stage were the most influential predictors of well performance. In this paper, we discuss how we combined the regression analysis results with probabilistic methods to predict well performance. The model converts the deterministic regression coefficients into probabilistic distributions to account for parameters not considered in the original regression analysis, including reservoir properties. The results of our study show that by using this model, we can match the range of actual well performance outcomes with a 95% confidence. Considering the importance of shale gas resources to the North American energy supply and the difficulty of characterizing shale gas reservoirs, this methodology offers a distinct advantage by providing a predictive model for well performance without the need for a detailed reservoir characterization. This also could be a beneficial tool to use in scoping studies where high-level, rapid evaluation is required.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.011
Version: metacan-v3-hybrid-931329e0061cValidation 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 score0.052
Threshold uncertainty score0.104

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.011
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0020.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.072
GPT teacher head0.242
Teacher spread0.170 · 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 source (direct Gemma or distilled Codex), 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

Citations15
Published2014
Admission routes1
Has abstractyes

Explore more

Same venueSPE Unconventional Resources ConferenceSame topicHydraulic Fracturing and Reservoir AnalysisFrench-language works237,207