Efficiency and Effectiveness - A Fine Balance: An Integrated System to Improve Decisions in Real-Time Hydraulic Fracturing Operations
Bibliographic record
Abstract
Abstract Hydraulic fracturing is a key driver of well productivity and field development planning, in addition to being the most significant portion of capex in shales. Recent breakthroughs in connectivity and digital technologies have enabled the monitoring and analyses of frac operations in real-time. However, most of the digitalization effort to date has been focused on increasing operational efficiency to reduce cost. Without an equal consideration for creating effective fracture geometries, this may lead to poor resource recovery and leave significant value behind. In this paper, we - 1) demonstrate the need to balance between optimizing fracture efficiency and effectiveness; 2) present an integrated system for frac optimization using real-time, historical data along with organizational knowledge; and 3) discuss the challenges of setting up such a system and key considerations, along with examples of large, untapped potential that can be unlocked with data science to deliver real value. Currently, several service providers exist to stream frac data with interactive analytics dashboards. While they offer some customizability, most do not provide a true frac optimization platform that goes beyond frac monitoring and analytics geared towards efficiency and cost indicators. We are still dependent on an individual operator's experience and rules of thumb to make job decisions during a frac stage. In this paper, a real-time optimization workflow is presented that uses advanced data science and statistical techniques to interpret and predict time-series treatment data, integrate historical and contextual information, and honor basin-specific knowledge that has been gathered and tested over the years. Examples are presented from diagnostic pads that highlight the need for balancing stimulation effectiveness with efficiency. We demonstrate a platform to host and execute an ensemble of models and visualizations that communicate actionable insights to an operator within minutes of identifying an event, gather feedback, and learn. Results from field testing show that our system accelerates the learning curve, enables consistent decision making by operators, and can generate significant cost savings. Finally, we share learnings from our digitalization journey. Completion and stimulation expenses account for approximately half of an unconventional well cost. Automated decision making for real-time fracture treatment is the holy grail of digital completions in shales. However, a blind pursuit of efficiency may lead to sub-par fracture treatments and significant value erosion for shale assets. We present an integrated framework that connects real-time data and organizational knowledge to guide an operator to pump the best frac stage while reacting to formation response within a set of constraints. To the best of our knowledge, this is the first paper to describe the general architecture and demonstrate the viability of such a system that relies only on standard wellhead measurements during fracturing.
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 | 0.007 | 0.014 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".