A Robust Strategy of Geophysical Logging for Predicting Payable Lithofacies to Forecast Sweet Spots Using Digital Intelligence Paradigms in a Heterogeneous Gas Field
Natural Resources Research,
Journal Year:
2024,
Volume and Issue:
33(4), P. 1741 - 1762
Published: May 14, 2024
Language: Английский
Reservoir rock typing assessment in a coal-tight sand based heterogeneous geological formation through advanced AI methods
Scientific Reports,
Journal Year:
2024,
Volume and Issue:
14(1)
Published: March 7, 2024
Abstract
Geoscientists
now
identify
coal
layers
using
conventional
well
logs.
Coal
layer
identification
is
the
main
technical
difficulty
in
coalbed
methane
exploration
and
development.
This
research
uses
advanced
quantile–quantile
plot,
self-organizing
maps
(SOM),
k-means
clustering,
t-distributed
stochastic
neighbor
embedding
(t-SNE)
qualitative
log
curve
assessment
through
three
wells
(X4,
X5,
X6)
complex
geological
formation
to
distinguish
from
tight
sand
shale.
Also,
we
reservoir
rock
typing
(RRT),
gas-bearing
non-gas
bearing
potential
zones.
Results
showed
gamma-ray
resistivity
logs
are
not
reliable
tools
for
identification.
Further,
highlighted
high
acoustic
(AC)
neutron
porosity
(CNL),
low
density
(DEN),
photoelectric,
values
as
compared
While,
5–10%
values.
The
SOM
clustering
provided
evidence
of
good-quality
RRT
facies,
whereas
other
clusters
related
shale
poor-quality
RRT.
A
t-SNE
algorithm
accurately
distinguished
was
used
make
CNL
DEN
plot
that
presence
low-rank
bituminous
rank
study
area.
presented
strategy
shall
provide
help
comprehend
coal-tight
lithofacies
units
future
mining.
Language: Английский
Artificial intelligence-driven assessment of salt caverns for underground hydrogen storage in Poland
Scientific Reports,
Journal Year:
2024,
Volume and Issue:
14(1)
Published: June 20, 2024
Abstract
This
study
explores
the
feasibility
of
utilizing
bedded
salt
deposits
as
sites
for
underground
hydrogen
storage.
We
introduce
an
innovative
artificial
intelligence
framework
that
applies
multi-criteria
decision-making
and
spatial
data
analysis
to
identify
most
suitable
locations
storing
in
caverns.
Our
approach
integrates
a
unified
platform
with
eight
distinct
machine-learning
algorithms—KNN,
SVM,
LightGBM,
XGBoost,
MLP,
CatBoost,
GBR,
MLR—creating
rock
deposit
suitability
maps
The
performance
these
algorithms
was
evaluated
using
various
metrics,
including
Mean
Squared
Error
(MSE),
Absolute
(MAE),
Percentage
(MAPE),
Root
Square
(RMSE),
Correlation
Coefficient
(R
2
),
compared
against
actual
dataset.
CatBoost
model
demonstrated
exceptional
performance,
achieving
R
0.88,
MSE
0.0816,
MAE
0.1994,
RMSE
0.2833,
MAPE
0.0163.
novel
methodology,
leveraging
advanced
machine
learning
techniques,
offers
unique
perspective
assessing
potential
is
valuable
asset
stakeholders,
government
bodies,
geological
services,
renewable
energy
facilities,
chemical/petrochemical
industry,
aiding
them
identifying
optimal
Language: Английский
Leveraging Automated Deep Learning (AutoDL) in Geosciences
Computers & Geosciences,
Journal Year:
2024,
Volume and Issue:
188, P. 105600 - 105600
Published: April 28, 2024
Language: Английский
Data-driven total organic carbon prediction using feature selection methods incorporated in an automated machine learning framework
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: March 27, 2025
An
accurate
assessment
of
shale
gas
resources
is
highly
important
for
the
sustainable
development
these
energy
resources.
Total
organic
carbon
(TOC)
analysis
thus
becomes
fundamental
understanding
distribution
and
quality
hydrocarbon
source
rocks
within
a
reservoir.
The
elevation
TOC
often
associated
with
presence
rocks,
indicating
potential
oil
production.
performed
using
laboratory
methods,
which
can
be
time-consuming
costly.
Data-driven
models
have
been
successfully
applied
to
model
relationship
between
other
constituents
predict
content.
However,
methods
depend
on
extensive
parameter
adjustments
that
must
carefully
conducted
in
different
sedimentary
environments.
In
this
context,
Automated
Machine
Learning
(AutoML)
an
alternative
accurately
predicting
TOCs,
saving
fine-tuning
steps
development.
This
study
aims
develop
AutoML
strategy
estimating
well
log
data.
procedure
automatically
preprocesses
search
best
method
parameters,
reducing
execution
time.
Among
evaluated,
Extremely
Randomized
Trees
(XT)
(R
=
0.8632,
MSE
0.1806)
test
set.
proposed
provides
powerful
data-driven
method,
allows
real-world
use
assist
data
subsequent
decision-making.
Language: Английский
Optimizing Permeability and Porosity Prediction with Advanced Machine Learning: A Case Study Unlocking the Complexities of Late Cretaceous Reservoirs, Gulf of Suez, Egypt.
Amer A. Shehata,
No information about this author
Mohamed Ahmed,
No information about this author
Ahmed A. Kassem
No information about this author
et al.
Journal of African Earth Sciences,
Journal Year:
2025,
Volume and Issue:
unknown, P. 105670 - 105670
Published: April 1, 2025
Language: Английский
Advancing shale geochemistry: Predicting major oxides and trace elements using machine learning in well-log analysis of the Horn River Group shales
International Journal of Coal Geology,
Journal Year:
2025,
Volume and Issue:
unknown, P. 104767 - 104767
Published: April 1, 2025
Language: Английский
Reservoir Property Prediction in the North Sea Using Machine Learning
IEEE Access,
Journal Year:
2023,
Volume and Issue:
11, P. 140148 - 140160
Published: Jan. 1, 2023
The
North
Sea
sedimentary
basin
is
characterized
by
geological
complexity,
encompassing
a
wide
range
of
rock
types
and
structures,
including
multiple
reservoirs
(carbonates
siliciclastic)
with
variations
in
reservoir
quality
heterogeneity.
These
phenomena
pose
significant
challenges
for
accurately
predicting
properties
using
traditional
well
log
analysis.
Moreover,
these
are
further
compounded
complex
conditions
scarcity
available
data.
Hence,
the
aim
this
study
was
to
address
applying
advanced
machine
learning
techniques
within
basin.
This
delves
into
both
supervised
unsupervised
approaches
forecast
essential
petrophysical
that
crucial
assessing
quality.
encompass
total
porosity,
effective
shale
volume,
all
derived
from
data
originating
models
were
trained
four
wells
consisting
32,215
points
(80%
training,
10%
testing,
validation).
Furthermore,
our
introduced
pioneering
data-driven
preprocessing
workflow,
exploratory
analysis,
missing
imputation,
outlier
detection
improve
performance
models.
ANN
RF
achieved
best
results
among
algorithms
evaluated,
an
average
MAE
0.01,
RMSE
R-squared
0.95
volume
shale,
respectively.
metrics
demonstrate
model
can
predict
challenging
basin,
even
limited
availability,
enabling
characteristics
field
development
optimization,
particularly
areas
where
core
scarce.
Language: Английский
Machine Learning-Based Prediction of Pore Types in Carbonate Rocks Using Elastic Properties
Ammar Abdlmutalib,
No information about this author
Abdallah Abdelkarim
No information about this author
Arabian Journal for Science and Engineering,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Aug. 13, 2024
Language: Английский
A novel score system to evaluate carbonate reservoir combining microscale and macroscale parameters
Journal of Petroleum Exploration and Production Technology,
Journal Year:
2024,
Volume and Issue:
14(5), P. 1101 - 1112
Published: Feb. 22, 2024
Abstract
The
central
Sichuan
Basin,
located
in
western
China,
holds
great
significance
terms
of
hydrocarbon
production,
especially
relation
to
complex
carbonate
reservoirs,
notably
the
Qixia
Formation
Middle
Permian
epoch.
However,
comprehensive
evaluation
this
geological
formation
presents
considerable
challenges
due
lithology,
limited
availability
reservoir
property
data
at
various
scales,
inadequacies
integration,
and
absence
a
reliable
ranking
system
for
development
decision
making.
Previous
studies
primarily
relying
on
conventional
level,
such
as
well
logs
information,
have
proven
insufficient
accurately
characterizing
reservoir.
This
is
evident
without
precise
lithological
information
detailed
knowledge
microscale
properties,
which
are
crucial
effective
evaluation.
To
address
these
challenges,
study
integrates
advanced
technologies
like
X-ray
diffraction,
micro-CT
scanning
electron
microscope
(SEM)
techniques
digital
drill
cutting
analysis
microscale.
A
novel
scoring
has
been
developed
using
prominent
component
(PCA)
approach
an
expert
system,
incorporates
existing
log
analysis.
validated
actual
production
data,
thus
establishing
robust
methodology
assessing
exploration
potential
optimizing
strategies
gas
reservoirs
Formation.
innovative
approach,
parameters
both
micro-
macroscales,
promising
facilitating
future
efforts.
Language: Английский