Summary
Sustained increases in energy prices have focused attention on gas resources
in low-permeability shale or in coals that were previously considered
economically marginal. Daily well deliverability is often relatively small,
although the estimates of the total volumes of recoverable resources in these
settings are often large. Planning and development decisions for extraction of
such resources must be areawide because profitable extraction requires
optimization of scale economies to minimize costs and reduce risk. For an
individual firm, the decision to enter such plays depends on
reconnaissance-level estimates of regional recoverable resources and on cost
estimates to develop untested areas. This paper shows how simple nonparametric
local regression models, used to predict technically recoverable resources at
untested sites, can be combined with economic models to compute regional-scale
cost functions. The context of the worked example is the Devonian Antrim-shale
gas play in the Michigan basin. One finding relates to selection of the
resource prediction model to be used with economic models. Models chosen
because they can best predict aggregate volume over larger areas (many hundreds
of sites) smooth out granularity in the distribution of predicted volumes at
individual sites. This loss of detail affects the representation of economic
cost functions and may affect economic decisions. Second, because some analysts
consider unconventional resources to be ubiquitous, the selection and order of
specific drilling sites may, in practice, be determined arbitrarily by
extraneous factors. The analysis shows a 15-20% gain in gas volume when these
simple models are applied to order drilling prospects strategically rather than
to choose drilling locations randomly.
Introduction
Sustained increases in energy prices have focused attention on the
development of marginally economic resources such as natural gas in
low-permeability shale or in coal. The daily deliverability of these resources
from individual wells is often relatively small, whereas the estimates of the
total volume of recoverable resources in these settings are often large.
Planning and development decisions for extraction of such resources are, by
nature, areawide because profitable extraction requires the optimization of
scale economies to minimize costs and reduce risk. For an individual firm, the
decision to enter such plays depends on reconnaissance-level estimates of
regional recoverable resources and on cost estimates to develop untested areas.
This paper demonstrates how simple nonparametric-regression-model predictions
of technically recoverable unconventional gas resources at untested sites can
be used with economic models to compute, at the regional scale, the costs of
developing and producing such resources in partially developed areas. The
predictive models are described in the next section. Following this
description, the data, prediction results, and the predictive distributions of
recoverable gas volumes are discussed. The assumptions and fundamental
components of the economic analysis are then presented. The paper also
demonstrates the benefits of applying the model predictions in the strategic
ordering of drilling prospects and the benefit of updating predictions when the
results of new drilling become available. The cost models provide a way to
evaluate the economic payoff associated with the application of local
prediction models. A worked example, that used data from the Devonian
Antrim-shale gas play of the Michigan basin, provides the context for testing
the usefulness of the local prediction models at the regional scale and also
for strategic drilling decisions. In summary, the analysis shows that these
models can be applied usefully to assess the regional economic potential and,
at the strategic level, to rank prospects by order of value in partially
developed areas.
© 2008. Not subject to copyright. This document was prepared by
government employees or with government funding that places it in the public
domain.
View full textPDF
(
2,291 KB
)
History
- Original manuscript received:
2 February 2007
- Meeting paper published:
1 April 2007
- Revised manuscript received:
8 February 2008
- Manuscript approved:
8 April 2008
- Version of record:
29 December 2008
View Cart
