Journal of energy resources technology.,
Journal Year:
2024,
Volume and Issue:
1(1)
Published: May 20, 2024
Abstract
Separate-layer
injection
technology
is
a
highly
significant
approach
for
enhancing
oil
recovery
in
the
later
stages
of
oilfield
production.
Both
separate-layer
and
general
information
are
crucial
parameters
multi-layer
systems.
However,
significance
usually
overlooked
during
optimization
process
injection.
Moreover,
conventional
schemes
fail
to
meet
immediate
dynamic
demands
well
Consequently,
method
based
on
artificial
neural
network
residual
(ANN-Res)
model
was
proposed.
Firstly,
primary
controlling
factors
production
were
identified
through
grey
correlation
analysis
ablation
experiments.
Then,
data-driven
established
with
an
(ANN),
which
block
utilized
incorporate
information,
eventually
forming
ANN-Res
that
integrates
information.
Finally,
workflow
designed
association
model.
Analysis
factor
shows
combination
prediction
leads
redundancy.
The
results
injection–production
demonstrate
significantly
better
than
ANN
only
inputs
or
Furthermore,
result
proves
proposed
can
be
successfully
applied
optimization,
realizing
purpose
increasing
decreasing
water
cuts,
thereby
improving
development.
Energy Storage,
Journal Year:
2025,
Volume and Issue:
7(1)
Published: Jan. 6, 2025
ABSTRACT
Hydrogen
is
one
of
the
most
promising
alternatives
to
fossil
fuels
for
energy
as
it
abundant,
clean
and
efficient.
Storage
transportation
hydrogen
are
two
key
challenges
faced
in
utilizing
a
fuel.
Storing
H
2
form
metal
hydrides
safe
cost
effective
when
compared
its
compression
liquefaction.
Metal
leverage
ability
metals
absorb
stored
can
be
released
from
hydride
by
applying
heat
needed.
A
multi‐step
methodology
proposed
identify
intermetallic
compounds
that
thermodynamically
stable
have
high
storage
capacity
(HSC).
It
combines
compound
generation,
thermodynamic
stability
analysis,
prediction
properties
ranking
discovered
materials
based
on
predicted
properties.
The
US
Department
Energy
(DoE)
Materials
Database
Open
Quantum
(OQMD)
utilized
building
testing
machine
learning
(ML)
models
enthalpy
formation
compounds,
formation,
equilibrium
pressure
HSC
hydrides.
here
require
only
attributes
elements
involved
compositional
information
inputs
do
no
need
any
experimental
data.
Random
forest
algorithm
was
found
accurate
amongst
ML
algorithms
explored
predicting
all
interest.
total
349
772
hypothetical
were
generated
initially,
out
which,
8568
stable.
highest
these
3.6.
Magnesium,
Lithium
Germanium
constitute
majority
compounds.
predictions
using
present
not
DoE
database
reasonably
close
data
published
recently
but
there
scope
improvement
accuracy
with
HSC.
findings
this
study
will
useful
reducing
time
required
development
discovery
new
used
check
practical
applicability
Geothermal Energy,
Journal Year:
2025,
Volume and Issue:
13(1)
Published: Jan. 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
$$\text
{R}^{2}$$
R2
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.
