It is a contradiction that our industry has a
reputation for being, and in fact is, very conservative when it comes to
adopting new technologies and yet is made up of individuals (also known as
consumers) who are anything but that: the latter will pick up a Blackberry like
they are going out of fashion but drop it in favour of a smartphone almost
overnight!
And when I talk to colleagues in the industry and ask
them about their reaction to specific new technologies and to those marketing
them, they will say things like “this is a solution looking for a problem; they
have no domain knowledge, etc”.
In fact the phrase “solution(s) looking for a problem”
seemed to me to have become a shorthand for “we ain’t going to buy it!” so the
other day I googled on this phrase and came upon this interesting short
article. It is worth clicking on this to get it onto a
separate Tab and coming back to my article when you have read it!
You will see that he is referring specifically to
entrepreneurs when he says “I have found that when they have
worked in the industry and have lived the problem they are trying to solve,
they have a much better shot at success.” To me this
defines what the comment about ‘domain knowledge’ implies…..….the folk pitching
the technology don’t understand the problem that might be solved.
So I thought I would do a couple of things.
Firstly I would write down no more than 4 or 5 problems
which I see in E&P: these are my ideas and others will have different ones
– a point which will I will come to in 5 or 6 lines. How do we:
1. Explore
for onshore oil?
2. Move
seismic interpretation out of the Stone Age?
3. Solve
the “cloud of points” problem?
4. Improve
Projects – they are invariably late, over budget and oftentimes do not deliver
what was promised production rates?
5. Spot
equipment failures ahead of the “Aw, snap!!” message?
I will work my way through these five shortly but
please feel free to tell me/us if you have another problem that you think is
important to crack.
1.
Exploring for onshore oil
We
need to remind ourselves that we are not just interpreters of 3D or 4D (towed
streamer) seismic but actually need to integrate a wide variety of data.
Exploring
onshore, we might have to integrate satellite and airborne data, a significant
number of well results (logs, cuttings, core, flow rates), potential field,
seismic, surface geology etc.
How
might satellite and airborne data help?
Well,
it is fairly well documented that seepage of petroleum, and here I am talking
about micro-seepage, can impact both the health of vegetation and the colour of
surface-exposed rocks. Such changes should be visible both from space and from
altitude, and the data available to us has mushroomed both in amount and in the
variety and resolution of sensor technologies. Can we get at the meaningful
patterns using Analytics?
2. Moving seismic interpretation out
of the Stone Age
You may have seen the news of the resounding win by the artificial intelligence program AlphaGo (built in
the UK! Hooray!! Now owned by Google…..)
over the South Korean world champion, the Go master, in the complex board game Go back in March.
AI experts had
predicted – last year, I think - that a computer program needed at least 10
more years of development before it would be able to beat a Go master. However,
as I understand it, any rules-based system such as Go – and see below! – is a
prime target for Machine Learning.
Well-established ‘rules’ have been proven for Stratigraphy,
Structural Geology, Sedimentology and describing Petroleum Systems (especially by
creating GDE, CRS and CCRS maps). Nowadays these ‘rules’ are most commonly
applied through seismic data, especially 3D seismic data.
The key ‘technologies’ are a) large quantities of
inexpensive multi-client 3D seismic and b) commoditised interpretation
workstations.
In truth, this methodology has now become completely
commoditised: little commercial advantage accrues from getting it right, simply
disadvantage flows from incompetent execution.
Hmmm, an interesting
message there for the folks who have been telling me that it will take “a
decade or more” for AI to replace Subsurface Scientists in the oil & gas
industry!
How long before an AI
system can actually do all of this?
3. The ‘cloud of points’ problem
Thirty years ago, a “previous employer” had an
internal R&D project which rejoiced in the name of Lithology & Fluid
Prediction (LFP).
Now LFP was founded on the idea that not only does
seismic data show us geological geometries – folds, downlaps, onlaps, erosional
truncation and the like – but that the very existence of reflections depends on
rock physics, contrasts in impedances, and that we might get smart enough to
predict actual lithologies and – wait for it – hydrocarbon content. And of
course this notion has had some success, with AVO anomalies, flat spots etc
etc.
However, I assert that we have not done as well as we
might with such predictions and that this is primarily due to the relatively
weak calibration that can be derived from well logs.
Who has worked in this arena and not found that well
log-derived parameters such as sonic velocity, density or resistivity exhibit
“cloud of points” behaviour when plotted against for example depth? A “cloud of
points” through which it is a pretty brave person who fits a straight line or
series of such lines, and then uses them to make lithology/fluid predictions?
Part of the problem has been selection and
prejudgement. So many wells have penetrated, for example, the Kimmeridge Clay
Formation in the UKCS that the problem only seems tractable if only a limited
selection of them are used. And then a model is imposed – for example that the
particular property will vary most strongly with depth or, perhaps, stress (if
we have a way of calculating it).
Thus a sample of the available data is exposed to
bi-variate analysis whereas the correct approach would be to subject all of it
to a multi-variate analysis.
Maybe then we might even find some more oil in mature
provinces such as the North Sea or South East Asia!