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.
