Parent-Child Well Dynamics: Insights for Mitigating Frac Hits Using a Data Science Approach
Bibliographic record
Abstract
Abstract During the development of unconventional reservoirs, interactions between parent and child wells, known as Fracture Driven Interactions (FDIs), are frequently observed. These interactions can either enhance, diminish, or have no effect on the performance of parent wells. This study addresses the industry's challenge of predicting the response of parent well to neighboring completion activities, known as frac-hit, by correlating these responses with controllable factors such as well spacing, completion design and operational strategy during offset completion activities. The analysis employs a metadata including 15,000+ wells from the Marcellus play. After a comprehensive quality control of the drilling, completion and production data, wells were grouped based on landing proximity, represented as 3D line segments using well coordinates. Parent and child wells were identified using spatial and temporal criteria, including drilling and completion dates. Frac-hit events were detected by analyzing the mean slope and variability of production profiles. In addition, frac-hit signatures were confirmed with child well completion dates. The assessment of the impact of a frac-hit on parent well involves evaluating production trends over ten months period, including five months before, the exact month, and five months after the detected frac-hit event. The clustered wells with that met the frac-hit criteria resulted in identification of over 1,000 parent wells, each with at least one significant frac-hit event. Through a data quality procedure, approximately 450 events with high confidence were selected. Predictive modeling and interpretability techniques were employed to analyze key independent variables and define thresholds. These thresholds were then used to construct a two-dimensional quadrant map to visualize the relationships between impact categories and influencing factors. Quadrant of impact vs well spacing and completion design demonstrates the minimum required spacing and fracturing criteria to avoid negative impact on parent wells. This study bridges multiple disciplines, combining geospatial analysis, statistical modeling and data science for identifying and interpreting frac-hits to optimize well performance. The methodology and outcome provide operators with a practical screening tool to mitigate detrimental impacts on parent wells as suboptimal drilling and/or completion designs often lead to excessive communication, reduced productivity, and financial inefficiencies.
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 | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".