American Oil and Gas Reporter - July 2016 - 76

SpecialReport: Big Data & Geostatistics

A central part of Devon Energy's strategy
to implement analytics and real-time digital technologies is dedicated "nerve centers" to monitor and support production
and drilling operations on a round-theclock basis.The company has decision support centers in all its field offices that serve
as real-time hubs for production operations, and a centralized well construction
facility devoted to optimizing drilling on all
Devon wells.

predictive model building, Ball explains, noting that the WellCon
team can monitor simultaneously all the rigs Devon has running.
The results have been game changing, according to Ball. Wells
drilled since WellCon was established have seen significantly less
out-of-zone footage and fewer sidetracks, resulting in improved
cycle times and lower drilling costs. These results coincide with
Devon moving to the top of its peer group in 2015 for new wells'
average 90-day initial production rates.
Optimizing the drilling operation and keeping wells in zone
also creates benefits that are harder to quantify, but are certainly no less impactful, Bell suggests. For example, she points out,
drilling a high-quality borehole that stays in target allows the subsequent completion operation to maximize the amount of interval that can be stimulated, which ultimately improves productivity and recovery per well.
"Analytics is the key driver to drilling a good well," Ball insists. "We use big data to figure out where to drill a formation
while looking across an entire basin, and make sure the well stays
in the formation while it is being drilled."
During stimulation, WellCon experts use analytics to optimize
hydraulic fracturing operations, including analyzing microseismic information to detect subtle patterns the human eye cannot
see, Ball adds. "The centers also predict the effect of simultaneous operations so that drilling and completions work can be done
in parallel with the least risk of interference to ongoing production operations," she says. "We also can use analytics to select
the best vertical and horizontal candidates for refracturing."
Yet, despite the rapid evolution of data science technology, the
most powerful source of analytical capabilities in any company
is the human mind, Ball emphasizes. "Experienced engineers, scientists and technicians have learned what signals and conditions
can be used to predict performance or future problems, and they
know how to tune systems for optimal performance," she reasons.
"We are acutely aware that we could lose valuable insights with76 THE AMERICAN OIL & GAS REPORTER

out an explicit program to capture the knowledge these individuals possess."
Consequently, Ball reports that Devon has an active analytics program to capture the knowledge base of its seasoned professionals and transfer key learnings to the next generation. "We
document how they approach different problems," she explains.
"We seek the unwritten rules they use to predict performance and
failure. Then we automate and create analytical routines."
Ball says she sees further enhancement of this knowledge transfer process as Devon incorporates video analytics, machine learning, and natural language processing. "There is so much we can
do today and even more that is just over the horizon," she comments.
Vetting Projects
According to Ball, every potential project at Devon begins with
a request for analytical services. Each project is vetted by the analytics team, often beginning with an investigation into the underlying question or problem to be solved. Critical early steps in
any project are defining a clear objective, delineating how to capture the required data, and specifying what valuable insights can
be obtained, she notes.
To be approved, an analytics project must show a tie to Devon's strategic plan. "If it does not, what is the point?" Ball asks.
"It also must pass what we call the 'so what' test. If the project
owner cannot articulate the value, then how can we be sure to
achieve it?"
If a project proposal makes it over those first two hurdles, it
then faces a final triad of criteria to ensure it is actionable, datadriven, and has a measureable monetary impact, she goes on.
Analysis is about finding patterns, whether singular or a pattern over time, notes Ball. Her team focuses on pattern seeking
with a reference point. "We usually start with a defined problem
to solve, because if we wait to see what the data tell us, we can

American Oil and Gas Reporter - July 2016

Table of Contents for the Digital Edition of American Oil and Gas Reporter - July 2016