Henk
Kombrink, in an article for GeoExPro, which spurred this post, asks:
“How fast are AI and automation replacing the need to
have geological boots on the ground?”
Notice that he doesn’t ask
if, but essentially when. Certain tasks of field geologists can be automated,
and some can do a better job, not because they are smarter than geologists, but
because they can specialize in specific tasks, provide continuous coverage and
monitoring, and provide faster and more accurate determinations of some
parameters.
Kombrick describes some talks he heard at the recent Operations Geology Conference in London. He mentions a talk by Aaron Swanson of Diversified Well Logging LLC, ‘Automated Real-Time Cuttings Analytics and AI-Assisted Decision Support for Operations Geoscience.’ Kombrink notes that the talk centered around a drill cuttings sampler machine that automates both collecting and analyzing cuttings samples.
Diversified
calls their Robologger automated sampler “the
industry’s only fully automated sample collection device.”
“It is designed to collect 25 to 30-gram samples at a
maximum rate of 2 minutes per sample.”
“It potentially saves around 6 bodies on the rig,” he
{Swanson} said, “also reducing the carbon footprint that comes with moving
people around.” The company has deployed the machine not only in the US, where
HQ is located, but also abroad, such as in Saudi Arabia.
Diversified's Robologger also comes in an EZ form that can collect and analyze samples when a manned mudlogging crew is onsite.
Next, Kombrink mentions a
talk by Calvin Holt from DrillDocs. It was titled, ‘Size AND Shape Matter:
Digital Shaker Surveillance and Its Path to Improved Drilling Performance.’
Shaker surveillance is not only important for understanding geological or
formation changes, but also to analyze hole conditions. Kombrink describes
DrillDocs as:
“….a new and automated process to analyse cuttings and
detect cavings using a camera that monitors the materials falling off the
shakers. “Rather than taking let’s say three samples an hour,” he said, “our
device monitors cuttings continuously.” It doesn’t only result in a much better
timing as to when cavings start to appear, the camera and associated software
also analyses the shape of the cavings, allowing to make inferences on the
geomechanical conditions down the hole. It is yet another task that shifts from
human eyes to the eyes of a relatively simple camera.”
Kombrink notes that in both
cases he describes, it is clear that the automated systems/services can
outperform the field geologist. As a former operations geologist and, before
that, as a field geologist doing some of these tasks, I agree. However, some of
those field positions, such as mudlogger and/or onsite geosteerer, allow one to
learn quite a lot about drilling and evaluating cuttings, so losing them could
hurt the knowledge base. Even so, it is worth it to have better and more
consistent collection and analysis of samples, better shale shaker
surveillance, and fewer personnel on-site. Managing the field processes can be
done remotely. Mudlogging, especially, has sometimes been deemed a thankless,
low-paying job (compared to other oil & gas jobs) with little opportunity for
advancement, even though one learns quite a lot. Unfortunately, these automated
functions are bad news for newly graduating geologists looking to begin their
careers.
“And what will be the long-term consequence of this
development? The result is that fewer people who enter the industry have a
feeling of what the real and hard data look like. If anything, this should
reinforce the need to at least replace this element of practical experience
with a level of training.”
Another very interesting
service is SLB’s Automated Lithology service that can describe drill cuttings in
detail and pick up things a field geologist can miss, such as detailed microfossil
identification. It can integrate digital logs and other datasets into its
workflow and output accurate borehole logs, and can even do reservoir analysis.
SLB’s Automated Lithology has
three features. Litholink captures high-resolution images from drill cuttings
and “embeds metadata, enabling geologists to analyze lithologies in high
detail from the drillsite at labs around the world. AI-driven machine learning
continually makes more accurate digitalized descriptions."Lithoscribe is
an interface that “improves the characterization process, giving you digital
descriptions and data of your rock cuttings matched to capture geological
features. The descriptions create a digital database of the subsurface of the
well, providing quantitative and calibrated color identification based on the
Munsell rock color chart.”Litholog presents the drill cuttings analysis in
a detailed borehole log.
“Interpreted lithology translates cutting percentages
from depth intervals into the actual geological layers. Litholog generates
illuminated lithology layers with ROP data and gamma ray technology to improve
quality. This process is done automatically, and all geological properties are
displayed as curves.”
Of course, the logs and other products still need to be evaluated by actual geologists somewhere in order to arrive at decisions involving the well.
References:
If
automation and AI are progressing in the way they are, we surely need fewer
geologists – not more: That is the only conclusion one can draw after attending
the Operations Geology Conference in London last week. Henk Kombrink, GeoExPro.
June 22, 2026. If automation and AI are progressing
in the way they are, we surely need fewer geologists – not more - GeoExpro
The Future
of Precision Measurements & Automation: Next-Generation Reservoir
Intelligence. Diversified Well Logging. Home - Diversified Well Logging
Assumptions
to Assurance… and Action. You can’t react to what you don’t see. DrillDocs
solves that. DrillDocs. (website). DrillDocs – Assumptions to Assurance… and Action
Automated
Lithology: Increase your lithological accuracy and enhance well planning. SLB. Automated Lithology | SLB
No comments:
Post a Comment