Formation Fluid Sampling Simulation: The Key to Successful Job Design and Post-Job Performance Evaluation
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 Acquisition of fluid samples using wireline formation testers (WFTs) is an integral part of reservoir evaluation and fluid characterization. The increasing complexity of fluid sampling operations, especially in remote or offshore fields, requires a careful planning process involving systematic de-risking of the sampling objectives through quantitative evaluation of sampling hardware performance under uncertain downhole conditions and reservoir properties. During job execution, the cleanup of mud filtrate is monitored using downhole fluid analysis (DFA) sensor measurements. In addition to quantifying produced contamination and providing guidance for real-time decisions, these measurements hold valuable information about formation and fluid properties that can be extracted through advanced interpretation workflows. In this paper, we demonstrate how a quantitative, model-based workflow was applied to both planning and interpretation for a series of sampling jobs in a remote and harsh environment. At its core, the workflow consists of high-resolution numerical flow models for the filtrate cleanup process that cover both conventional and focused sampling tools. To enable real-time, interactive, and probabilistic workflows, we use machine learning techniques to construct fast, high-fidelity proxy models, which, after thorough validation, replace numerical simulation in the workflow. Finally, the workflow employs methods for uncertainty quantification, global sensitivity analysis, and model inversion. During the pre-job planning phase, the model-based workflow was used to select and mobilize the optimal sampling hardware, estimate sampling time uncertainty, and pinpoint the dominant sources of this uncertainty through global sensitivity analysis. After successful sample acquisition, the DFA measurements were reconciled with the cleanup model and the petrophysical evaluation to extract additional value from the measurements. Using measurements of water-cut and pressure, and conditioned to the petrophysical evaluation, the cleanup model was inverted for two-phase relative permeabilities. This recently developed methodology complements laboratory measurements of relative permeability on core samples. Building on previous work in this area, this paper demonstrates the practical application of advanced planning and interpretation workflows for downhole fluid sampling. The methodology presented couples traditional, full-physics flow modeling with modern machine learning techniques to achieve highly agile workflows, enabling operators to more efficiently plan sampling jobs and extract value from the measurements.
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 | 0.001 | 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 | 0.001 |
| 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