Forecasting geothermal temperature in western Yemen with Bayesian-optimized machine learning regression models
Geothermal Energy,
Год журнала:
2025,
Номер
13(1)
Опубликована: Янв. 12, 2025
Abstract
Geothermal
energy
is
a
sustainable
resource
for
power
generation,
particularly
in
Yemen.
Efficient
utilization
necessitates
accurate
forecasting
of
subsurface
temperatures,
which
challenging
with
conventional
methods.
This
research
leverages
machine
learning
(ML)
to
optimize
geothermal
temperature
Yemen’s
western
region.
The
data
set,
collected
from
108
wells,
was
divided
into
two
sets:
set
1
1402
points
and
2
995
points.
Feature
engineering
prepared
the
model
training.
We
evaluated
suite
regression
models,
simple
linear
(SLR)
multi-layer
perceptron
(MLP).
Hyperparameter
tuning
using
Bayesian
optimization
(BO)
selected
as
process
boost
accuracy
performance.
MLP
outperformed
others,
achieving
high
$$\text
{R}^{2}$$
R
2
values
low
error
across
all
metrics
after
BO.
Specifically,
achieved
0.999,
MAE
0.218,
RMSE
0.285,
RAE
4.071%,
RRSE
4.011%.
BO
significantly
upgraded
Gaussian
model,
an
0.996,
minimum
0.283,
0.575,
5.453%,
8.717%.
models
demonstrated
robust
generalization
capabilities
(MAE
RMSE)
sets.
study
highlights
potential
enhanced
ML
techniques
novel
optimizing
exploitation,
contributing
renewable
development.
Язык: Английский
Machine and deep learning-based prediction of potential geothermal areas in Hangjiahu Plain by integrating remote sensing data and GIS
Energy,
Год журнала:
2025,
Номер
315, С. 134370 - 134370
Опубликована: Янв. 1, 2025
Язык: Английский
A Machine Learning Approach for the Clustering and Classification of Geothermal Reservoirs in the Ying-Qiong Basin
Journal of Marine Science and Engineering,
Год журнала:
2025,
Номер
13(3), С. 415 - 415
Опубликована: Фев. 23, 2025
The
exploration
and
development
of
marine
geothermal
energy
is
a
field
with
significant
potential,
but
it
also
one
that
presents
considerable
challenges
costs.
assessment
reservoir
potential
currently
based
on
subjective
analysis,
this
study
proposes
an
innovative
clustering-based
method
to
classify
reservoirs
systematically.
Yingqiong
Basin
was
analysed
develop
machine
learning
framework
predict
the
(CPPOGR).
integrated
eight
key
features
into
unified
dataset,
employing
dimensionality
reduction
techniques
(principal
component
analysis
sparse
autoencoder)
SMOTE
balance
sample
size.
Machine
classifiers,
including
XGBoost,
BP
Neural
Networks,
Support
Vector
Machines,
K-Nearest
Neighbours,
Random
Forests,
were
utilised
for
prediction.
experimental
results
demonstrate
XGBoost
most
suitable
classifier,
achieving
excellent
performance
0.96
precision,
0.9556
recall,
0.9528
F1
score,
0.9623
accuracy.
These
effectiveness
proposed
CPPOGR
in
accurately
classifying
intrinsic
features.
This
underscores
integrating
cluster
efficient
characterisation,
thereby
offering
novel
approach
resource
assessment.
Язык: Английский
Leveraging Machine Learning for Subsurface Geothermal Energy Development
Highlights in Science Engineering and Technology,
Год журнала:
2024,
Номер
121, С. 440 - 449
Опубликована: Дек. 24, 2024
Geothermal
energy,
which
derives
heat
from
the
Earth's
core,
presents
a
promising
renewable
resource
for
meeting
sustainable
global
energy
needs.
Nevertheless,
challenges
including
high
initial
costs,
technical
risks,
and
complex
underground
conditions
have
limited
its
widespread
adoption.
Recent
advancements
in
Machine
Learning
(ML),
subset
of
Artificial
Intelligence
(AI),
offer
innovative
solutions
to
these
challenges.
This
paper
comprehensive
review
application
ML
techniques
geothermal
development,
focusing
on
exploration,
drilling,
reservoir
characterization
engineering,
as
well
production/injection
engineering.
Various
algorithms
neural
networks,
clustering
methods,
decision
trees,
been
employed
analyze
geological
operational
data.
These
applications
led
improved
identification
resources,
optimized
drilling
operations,
enhanced
management,
increased
production
efficiency.
While
integration
offers
significant
advantages,
limitations
like
data
quality
issues
computational
demands
persist.
highlights
need
interdisciplinary
collaboration,
sharing,
investment
research
development
overcome
The
ongoing
advancement
AI
technologies
is
anticipated
drive
innovation
exploration
enhancing
efficiency,
reliability,
economic
viability
cornerstone
systems.
Язык: Английский