Data-Driven Production Forecasting of Unconventional Wells with Apache Spark
Bibliographic record
Abstract
Abstract Real-time decision making, field surveillance, and production optimization improve the performance of existing operations to increase hydrocarbon recovery and reduce emissions. In this regard, the oil and condensate flow metering in offshore gas condensate platforms is always confronted by environmental, economic, and operational challenges resulting in uncertain production management plans. Although production forecasting of unconventional gas condensate systems is more challenging than for conventional wells, it is of great interest to support decisions by knowing the future of the wells as far as possible. The virtual flow metering techniques make it possible to utilize daily production data sets and extract information on how wells and reservoir will respond to different operational conditions. The objective of this study is to embed artificial intelligence algorithms in reservoir uncertainty modeling and present a mechanistically-supported data-driven model applicable for production forecasting of gas condensate wells with higher confidence. The outcome entails a new set of mathematical models, implemented using Apache Spark cluster computing engine with APIs in Python, that enables rigorous and robust optimization of the recovery process, designing and discovering hidden patterns in production data, and extracting reservoir information indirectly in seconds. The observations used to demonstrate the performance of the proposed hybrid model include 1600 well-testing data points together with 420 days of production history of an offshore gas condensate platform. The daily platform production is allocated efficiently to individual wells using a multilayer perceptron neural network model adaptively trained with well-testing and daily production datasets, and supported by the Energy and mass balance equations.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".