A Hybrid Analytical and Data-Driven Approach for Improved Prediction of Recovery Performance in Tight Oil Reservoirs
Bibliographic record
Abstract
Summary The heterogeneity of tight reservoirs, along with their complex geologic characteristics and the diverse completion practices used, presents challenges in developing accurate models to forecast the productivity for multifractured horizontal wells (MFHWs) completed in these reservoirs. This paper introduces a new early-time diagnostic tool that leverages early-time two-phase flowback data to forecast long-term productivity and evaluate completion efficiency. To achieve this, two novel models were developed. The first model, the water/oil-ratio model (WORM), uses a hybrid analytical and data-driven approach to describe the observed log-linear relationship between water/oil ratio (WOR) and load recovery (amount of fracturing water produced back after hydraulic fracturing operations) as an analogy to the log-linear relationship between the water/oil relative permeability ratio and water saturation. Next, a neural network is used to couple WORM parameters with key petrophysical properties to analyze the impact of fracture and formation properties on WOR performance, predict WOR as a function of load recovery, forecast ultimate load recovery, and estimate effective fracture volume and initial water saturation in fracture. The second model, the cumulative oil production model (COPM), is a data-driven model that predicts oil production as a function of load recovery during the matrix-dominated flow regime. The application of WORM and COPM on Niobrara and Codell formation wells showed that Codell wells generally exhibit better load recovery and larger effective fracture volume compared with Niobrara wells, but both formations exhibit similar oil recovery performance, indicating independent flow regimes within the effective fractures. The effective fracture volume estimated by WORM was validated against the estimated volume from recorded microseismic events. The results also showed that using the same completion practice to achieve a similar effective fracture volume in child wells does not necessarily lead to similar oil productivity. This paper introduces a holistic workflow that links early two-phase flowback data with well productivity and completion efficiency and is anticipated to aid petroleum engineers in optimizing hydraulic fracturing operations.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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 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".