Application of ANN-Based Proxy and Metaheuristic Algorithms in Well Spacing Optimization in a Fractured Tight Reservoir
Bibliographic record
Abstract
Abstract Optimizing well spacing is a critical step in the development of an oilfield. Several approaches have been employed over the past decades in an attempt to obtain an efficient and cost-effective well spacing methodology. The desire to achieve a fast-paced well spacing optimization outcome is not yet realized. This study explores the use of a data-driven surrogate model and metaheuristic optimization algorithms in optimizing the well spacing in a fractured tight reservoir in Saskatchewan, Canada. The wells considered drain oil from the Viking Formation located in the Avon Hill field. Multilayer perceptron (MLP) neural network is trained to predict time-series cumulative oil and gas production. The training and testing data were obtained from the history matched numerical reservoir model of the Avon Hill field. The artificial neural network (ANN) surrogate model is then coupled with Particle Swarm Optimization (PSO) algorithm, and Genetic Algorithm (GA). Maximization of the net present value (NPV) is set as the objective function with well spacing, fracture conductivity, fracture half-length as the control variables. 3 well spacing optimization workflows are then developed comprising of ANN based proxy only, ANN-PSO and ANN-GA. It is found that the use of the ANN-based proxy model enables various combinations of well spacing and fracture designs to be tested at higher computational speed compared to numerical simulation. The results also show that the PSO outperformed GA in terms of converging at a higher objective function value and at a higher convergence speed. Applying the proposed workflows to the Avon Hill field, it is found that the optimal well spacing ranges between 124 m to 132 m. This work reveals that variations in fracture geometry design significantly affects hydrocarbon recovery and economic performance of a fractured tight reservoir and these variations can be efficiently explored by the use of machine learning techniques.
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".