Analysis of Waterflooding Through Application of Neural Networks
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Petroleum reservoirs demonstrate a very complex behavior that changes with time in a non-linear manner. Application of neural networks for field-wise analysis of waterflooding projects is very appropriate because a structural model between injection and production does not need to be specified in order to predict performance. The neural network approach recognizes that individual well behavior may depend on the well history and the injection/production conditions of surrounding wells. The outcome of this neural network analysis could determine injection and production policies that would lead to determining the minimum injection water leading to maximum oil recovery. This paper presents application of neural network for analyzing data from a Canadian oil field that has been under waterflooding for several years. At first, production data for the last 20 years were obtained. Currently, there are 13 injection and 108 production wells in this pool. This neural network model uses this data and divides the field into several areas based on the performance of waterflooding, which helps the field engineers to focus on parts of the field that waterflooding is not very effective. Additionally, the neural network developed in this study is capable of predicting future oil recovery due to waterflooding. Introduction Recent progress in the available computational power and better understanding of the theory of neural networks has gain increasing attention of engineers and researchers working in petroleum industry. The ability techniques, such as neural network and fuzzy logic, to work with noisy data and solve problems even if information related to detailed physics of the system is not known or the system is too complex to be solved by traditional formal methods has provided new means of addressing these complex processes. Artificial intelligence, and both fuzzy logic and neural networks in particular, can give the petroleum industry new tools for better understanding and controlling recovery processes and therefore achieving efficient and profitable oil recovery[1,2]. One of the most widely used processes in mature oil fields is waterflooding. Field-wise management of these waterflooding processes provides several important challenges. Some of the questions facing engineers and mangers during designing and operating waterflood projects are; the location and pattern used for injection wells, amount and rate of water injection, and so on. Reservoir simulation is the common tool utilized to deal with these issues, however reservoir simulation cannot be used extensively because it is both time consuming and expensive. Lack of knowledge about the reservoir formations and detailed geology of these fields adds additional difficulty to correctly simulate oil fields. Fuzzy logic and neural networks can offer an alternative solution. Today most of oil reservoirs are under production for many years and a lot of production information has been cumulated over time. Using the ability of the neural networks to approximate relationships without knowing the exact mechanisms involved we can "simulate" the reservoir behavior and its response to the changes in recovery parameters. There is no "best" type of the network. Each network topology has its own advantages and disadvantages.
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.
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 it