3D Generalised Inversion (AVO, AI) as Direct Input to the Reservoir Model. Deepwater Exploration Offshore North West Borneo, Malaysia – A Case Study.
Bibliographic record
Abstract
Abstract The need to rapidly produce a notional field development plan, to reduce costs and cycle-time has driven a fast-track reservoir characterization and reservoir model-building project for one of many fields offshore North West Borneo, Malaysia. The objectives of the study have been defined based on the deliverables stated by the reservoir engineers. Considering the list of data and limited time available, an efficient generalised inversion workflow was designed to process a large volume of deepwater 3D seismic data with a single exploration well to: Locate and map all sands (3D geobody identification) versus non-reservoir rocks.Sub-divide reservoir sands into 4 lithofacies (well log neural net based calibration).Propagate 4 lithofacies to entire reservoir volume (within two fluid types).Integrate the fault framework with the sand and fluid distribution to build a first pass reservoir model.Include multiple realizations to manage uncertainty.Check sand connectivity and compute volumes of reserves in place. An innovative combination of 3D geostatistical and neural network techniques was used both for the well log data and for 3D seismic attributes (AVO, Acoustic impedance and dipazimuth combinations) to map the spatial distribution of the sand and their lithofacies. The results of the calibrated and quantitative generalised inversion were used in four different modes to assess the best way to build a first pass reservoir model and compute independent reserves within a short time-frame. This case study illustrates how a purposefully designed 3D/3D reservoir characterisation workflow can reduce the time required to build a first pass static reservoir model and how a similar process can be applied to other complex deepwater hydrocarbon accumulations. It focuses specifically on the different ways a static reservoir model can be built from 3D seismically derived volumes (3D/3D, Hybrid and grid-based).
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".