An Advanced Workflow and Tool to Map New Sweet Spot and Enhanced Well Placement Strategy using Machine Learning in Unconventional Reservoir
Bibliographic record
Abstract
Abstract Unlike conventional reservoirs where the reservoir rock formations are recipient of hydrocarbons from the source rock, unconventional formations constitute both the source and the hydrocarbon containing reservoir units. For the field development, horizontal wells are drilled and later hydraulically fractured in order to produce the gas. The placement of horizontal wells is crucial for the economic viability of the field. This paper describes developing an advanced workflow of new sweet spot mapping and a standalone tool to enhance horizontal well placement and completion optimization using machine learning. The tool, called Sweet Spots Machine Learning (SS-ML) is developed to integrate petrophysics, geomechanics, seismic, completions attributes and production data in order to map out high productivity zone that will help optimize well placement strategy. This study focused on a case study in Unconventional reservoirs in Canada. The procedure integrates all data from multiple domains such as Petrophysics-Geomechanics-Seismic-Completions attributes with the field production data and establishes a machine learning model (ML) in order to predict and map-out production sweet spots. The output 3D predicted production volume can then be employed to help optimize well placement and completions strategy. In general, unconventional reservoirs are difficult to produce as they are made up of very tight rocks containing hydrocarbons that cannot be produced without stimulation. Twelve key factors influencing subsurface parameters were identified for controlling production performance in this unconventional reservoir. High productivity sweet spots were identified to be zones with high organic content, high rock stiffness, and low horizontal stress condition. The machine learning model was developed and validated against production wells for sweet spot prediction. Then, 6 new wells were drilled and successfully identified sweet spots with success ratio above 83%. According to the findings, most current production levels fall within an acceptable range that exceeds predictions. The advanced workflow and new developed tool ML model allow future well placement optimization for this unconventional reservoir in Canada. Zone-based splitting of training and testing wells is recommended for unconventional reservoirs ML modelling to improve accuracy.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".