Case Study in Production Optimization Applying Information Technology
Bibliographic record
Abstract
Abstract Well data for oil and gas wells drilled in the Western Canadian Sedimentary Basin (WCSB) exists in many places and multiple formats with ranging detail. Multiple data sources, both internal and external, are needed to truly optimize the well stimulation and the production optimization process. Production and well data in the WCSB is considered the highest in quantity and quality for reservoir description in the world. This data repository exists due to royalty and tax issues and is strictly enforced by government legislation. Unfortunately, detailed completion data is not part of the public record. However, companies such as BJ Services whose core business includes drilling and completion field services usually do keep a comprehensive and detailed collection of data. These drilling and completion companies often have data that is unavailable in the public databases. This paper outlines the first steps in developing a synergistic approach to integrating publicly available production and well data with detailed completion data from private sources. The case study presented shows the effectiveness of combining internal detailed completion data with external third party data. The case study evaluates completions in a Medicine Hat formation shallow gas play in southeast Alberta, Canada and the production impact realized. Introduction There are various sources of information regarding oil and gas activity in the WCSB. Operators, government bodies, data vendors and service companies all collect information. The formats vary from paper to electronic and from organized databases to scattered documents. Information on a large scale is most valuable when combined with related information from different sources. A common point of reference such as the Public Petroleum Data Model (PPDM) implemented in a powerful relational database such as Oracle creates this value when different data sources are mapped into it. Data will typically exist on several different platforms. The highly structured data stored in relational databases such as Oracle, Microsoft SQL Server, or even Microsoft Access is the easiest to work with. Semi-structured data is found in Lotus Notes and Microsoft Exchange. While having the advantage of being centrally administered like a database, it is often more difficult to work with the data due to the "flexible" nature of the underlying technologies. Finally, the huge collection of documents, electronic and paper, created over many decades are on various hardware platforms from mainframe to handheld. The apparently endless variety of layouts and file formats in word processors, spreadsheets, and specialized engineering applications are the most difficult to work with, but often are also the most rewarding. After all, these reports were usually created by engineers thinking deeply before committing their ideas to paper. Several vendors offer a variety of local data installations and/or Internet data hubs. Their data may be either hand entered from original source documents or received on tape from government boards. Information varies widely since there are so many datasets and sources to choose from. Some types of datasets available:
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.006 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".