PATRICK NG, REAL CORE ENERGY, HOUSTON
TYLER CHESSMAN, MICROSOFT CORPORATION, HOUSTON
USE MODERN PORTFOLIO THEORY AND MACHINE LEARNING TO DRIVE PRUDENT DECISION MAKING
A hybrid approach to well economics
IN FINANCE, we’ve witnessed an emerging application of
machine learning algorithms, e.g., robo-advisor, and earthquake
prediction technology. Here, we illustrate with examples, practical applications of a hybrid approach that combines fundamental well economics modeling, modern portfolio theory, and
algorithmic machine learning to generate actionable insights
and drive prudent investment decisions.
FUNDAMENTAL ROI SENSITIVITY
Figure 1 shows how we can model discounted cash flows and
F1: ROI SENSITIVITY OF DRILL-UN-COMPLETE WELL
No DUC: 800
WTI uplift to make
DUC return favorable
Note: At $37 oil, ROC of DUC will match the base case of drill and
complete (dashed) if WTI hits $50 in 12 months (the time lag between
drilling and completion) at the crossover point.
-0.620 25 30 35 40 45 50 55
Oil price in 12 months @DUC time
F2: FULL-CYCLE ROI SENSITIVITY OF
REFRACKING A WELL
-0.520 25 30 35 40 45 50 55
Oil price in 24 months @refrack time
Note: At $37 oil, ROI for practical 800 bo/d will outperform base case with
400% uplift in 24 months (at the time of refracking) when oil price returns
to $45 to $50 range, above the crossover.
better understand the sensitivity of ROI over different WTI
prices for drill-but-uncomplete (DUC) and refracking a well.
Assume typical unconventional well costs and decline rates.
Implicit in DUC is how much WTI will rise to make it work
from a return perspective.
Figure 2, assuming $37 oil today, illustrates W TI will have to
increase by 40% to be viable when compared to the baseline
case of drill-and-complete. In refracking, we want to know if a
before-and-after uplift in production will have material impact.