Development and Application of Algorithm for Stress Inversion Based on Image Log Data
Bibliographic record
Abstract
Abstract Successful well planning and stimulation in complex geological settings (especially in the horizontal wells and wells with a high degree of deviation) is bound with conducting geomechanical estimations. Identification of the stress regime, which is an imperative basis for the geomechanical modeling, can significantly alter the reservoir production scheme. Moreover, knowledge of the stress regime directly impacts the efficiency of hydraulic fracturing procedures and wellbore stability. For example, in case of reverse stress regime, the hydraulic fracturing operations could be inefficient due to the problems with the fracture initiation, high injection pressures, and risks associated with the proppant fallout in the wellbore. Fields experiencing hydraulic fracturing problems should be assessed via the geomechanical frame of reference for the comprehensive understanding of the issue. Assessing the state of stress is challenged by the absence of direct measurement tools of maximum horizontal stress. Application of the stress estimation methods commonly used in the industry (including the breakout width, acoustic anisotropy inversion and poroelastic modeling with the assumption of tectonic coefficients) have certain limitations which often lead to a broad range of obtained values of maximum horizontal stress, thus adding uncertainty to the drilling and hydraulic fracturing recommendations. Thus, the main goal of this work is to develop and apply an instrument for qualitative assessment of stress regime and direction. The reliable mathematical model, built upon the minimal set of required data, which is able to forecast the rock behavior under far-field and near wellbore stresses can be an extremely useful instrument for effective operations of drilling, fracturing, well placement and reservoir development. The underlying method for the development of the stress inversion algorithm was based on limiting the range of possible values of horizontal stresses using Anderson's definition of stress regimes, the frictional theory of Mohr-Coulomb and Kirch equations. The subsequent analysis of the breakout azimuths at the wellbore walls of several inclined wells from the image log data results in a reliable prediction of reservoir stress regime and direction. The optimal usage of the method required knowledge of vertical stress and the borehole failures logged in the deviated wells with the inclination of at least 20° and varying azimuthal directions. The developed algorithm of the improved identification of stress regime was then applied for a real field case in order to understand the geomechanical roots of the problems experienced during hydraulic fracturing treatment. Learning the stress regime and the orientation of the horizontal stresses allowed building reliable geomechanical models, necessary for the optimization of the hydraulic fracturing program and improvement of well operating efficiency. The conclusion upon the conducted work was that the methods of horizontal stress detection should be further studied for the cases where the data is not enough (for example no deviated bores logged). Moreover since all methods of SHmax estimation are inverse, the most value can be brought only by creating a tool where all the techniques (existing and the ones under development) are integrated.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| 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) | 0.004 | 0.003 |
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".