Artificial-Intelligence Based Horizontal Well Placement Optimization Leveraging Geological and Engineering Attributes, and Expert-Based Workflows
Bibliographic record
Abstract
Abstract Horizontal wells provide a highly efficient way to maximize contact with the reservoir target and to increase overall recovery by allowing a larger drainage pattern. Traditionally, the identification of optimal horizontal well locations involves domain expertise across multiple disciplines and takes a long time to complete. In this work, a fully streamlined artificial intelligence (AI)-based workflow is introduced to facilitate horizontal opportunity identification by combining geological and engineering attributes in all types of reservoirs. This workflow relies on automated geologic and engineering workflows to map the remaining oil in place and identify areas with high probability of success (POS) and high productivity potential. Advanced computational algorithms are implemented under a variety of physical constraints to identify best segments for placing the wellbores. Statistical and machine learning techniques are combined to assess neighborhood performance and geologic risks, along with forecasting the future production performance of the proposed targets. Finally, a comprehensive vetting and sorting framework is presented to ensure the final set of identified opportunities are feasible for the field development plan. The workflow incorporates multiple configuration and trajectory constraints for the horizontal wells’ placement, such as length/azimuth/inclination range, zone-crossing, fault-avoidance, etc. The optimization engine is initialized with an ensemble of initial guesses generated with Latin-Hypercube Sampling (LHS) to ensure all regions of good POS distribution in the model are evenly considered. The intelligent mapping between discrete grid indexing and continuous spatial coordinates greatly reduced the timing and computational resources required for the optimization, thus enabling a fast determination of target segments for multi- million-cell models. The optimization algorithm identifies potential target locations with 3D pay tracking globally, and the segments are further optimized using an interference analysis that selects the best set of non-interfering targets to maximize production. This framework has been successfully applied to multiple giant mature assets in the Middle East, North and South America, with massive dataset and complexity, and in situations where static and dynamic reservoir models are unavailable, partially available, or are out of date. In the specific case study presented here, the workflow is applied to a giant field in the Middle East where tens of deviated or horizontal opportunities are initially identified and vetted. The methodology presented turns the traditional labor-intensive task of horizontal target identification into an intelligently automated workflow with high accuracy. The implemented optimization engine, along with other features highlighted within, has enabled a lightning-fast, highly customizable workflow to identify initial opportunity inventory under high geological complexity and massive dataset across different disciplines. Furthermore, the data-driven core algorithm minimizes human biases and subjectivity and allows for repeatable analysis.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
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 teacher head, 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".