Williston Basin - A History of Continuous Performance Improvements Drilling Through the Bakken
Bibliographic record
Abstract
Abstract The Williston Basin has become one of the more lucrative oil reservoirs in North America over the past few years. The main reservoir occupies about 200,000 square miles of the subsurface of the Williston Basin, covering parts of Western North Dakota, Eastern Montana, and Southern Saskatchewan. The Bakken Formation was first discovered in 1951, but efforts to extract oil from it have historically been difficult. Efficient production of the Bakken has been achieved with long horizontal wells drilled through reservoirs at depths ranging from 8,000 ft to 10,500 ft (2,438 m to 3,200 m) true vertical depth (TVD). The target reservoir depths and the extended lateral wellbore lengths, require more powerful rigs to meet the operational demands of these well designs. The increased cost and tight economics associated with this play present a strong incentive to improve the drilling performance by reducing drilling time and cost. As a result, a strong focus was placed on improving drilling efficiency in the 9,000 ft to10,000 ft (2,743 m to 3,048 m) lateral wellbore sections, which have the largest impact on the overall well cost. This paper will introduce the challenges encountered when drilling these wellbore designs and outline the approach taken to optimize the drilling process. The usage of high-performance drilling motors, a review of previously used bottom hole assembly (BHA) concepts, and the benefits of gathering additional real-time downhole drilling data to validate or change best practices will all be discussed. The data presented has been gathered over the past 18 months, mainly in Dunn County of North Dakota, and will show rate of penetration (ROP) improvements of about 50% over this time period. This improvement in drilling efficiencies has proven to reduce the overall drilling time and has impacted the economics of this play significantly.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 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".