Rationally Designed High-Temperature Polymer Dielectrics for Capacitive Energy Storage: An Experimental and Computational Alliance
Progress in Polymer Science,
Год журнала:
2025,
Номер
unknown, С. 101931 - 101931
Опубликована: Фев. 1, 2025
Язык: Английский
Insights into Synthesis and Optimization Features of Reverse Osmosis Membrane Using Machine Learning
Materials,
Год журнала:
2025,
Номер
18(4), С. 840 - 840
Опубликована: Фев. 14, 2025
Reverse
osmosis
membranes
have
been
predominantly
made
from
aromatic
polyamide
composite
thin-films,
although
significant
research
efforts
dedicated
to
discovering
new
materials
and
synthesis
technologies
enhance
the
water-salt
selectivity
of
in
past
decades.
The
lack
breakthroughs
is
partly
attributed
limited
comprehensive
understanding
relationships
between
membrane
features
their
performance.
Insights
into
intrinsic
reverse
(RO)
based
on
metadata
were
obtained
using
explainable
artificial
intelligence
understand
unify
efforts.
related
chemistry,
structure,
modification
methods,
performance
RO
derived
dataset
more
than
1000
membranes.
Seven
machine
learning
(ML)
models
constructed
evaluate
performances,
applicability
for
tasks
was
assessed
metadata.
contribution
analyzed,
ranking
importance
revealed.
This
work
holds
promise
analysis,
evaluating
against
state
art
developing
an
inverse
design
strategy
discovery
high-performance
Язык: Английский
Tuning membrane surface wetting behaviour via dual-nanomaterial functionalization for efficient water purification
Journal of Membrane Science,
Год журнала:
2025,
Номер
unknown, С. 123970 - 123970
Опубликована: Март 1, 2025
Язык: Английский
Machine learning in membrane science: Bridging materials, structures, and performance for next-generation membrane design
Separation and Purification Technology,
Год журнала:
2025,
Номер
unknown, С. 133091 - 133091
Опубликована: Апрель 1, 2025
Язык: Английский
PLGA-based long-acting injectable (LAI) formulations
Journal of Controlled Release,
Год журнала:
2025,
Номер
unknown, С. 113758 - 113758
Опубликована: Апрель 1, 2025
Язык: Английский
Advances in Porous Materials for Transuranic Element Separation
Acta Chimica Sinica,
Год журнала:
2025,
Номер
83(4), С. 401 - 401
Опубликована: Янв. 1, 2025
Язык: Английский
Explainable Artificial Intelligence (XAI) for Material Design and Engineering Applications: A Quantitative Computational Framework
International journal of mechanical system dynamics,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 20, 2025
ABSTRACT
The
advancement
of
artificial
intelligence
(AI)
in
material
design
and
engineering
has
led
to
significant
improvements
predictive
modeling
properties.
However,
the
lack
interpretability
machine
learning
(ML)‐based
informatics
presents
a
major
barrier
its
practical
adoption.
This
study
proposes
novel
quantitative
computational
framework
that
integrates
ML
models
with
explainable
(XAI)
techniques
enhance
both
accuracy
property
prediction.
systematically
incorporates
structured
pipeline,
including
data
processing,
feature
selection,
model
training,
performance
evaluation,
explainability
analysis,
real‐world
deployment.
It
is
validated
through
representative
case
on
prediction
high‐performance
concrete
(HPC)
compressive
strength,
utilizing
comparative
analysis
such
as
Random
Forest,
XGBoost,
Support
Vector
Regression
(SVR),
Deep
Neural
Networks
(DNNs).
results
demonstrate
XGBoost
achieves
highest
(),
while
SHAP
(Shapley
Additive
Explanations)
LIME
(Local
Interpretable
Model‐Agnostic
provide
detailed
insights
into
importance
interactions.
Additionally,
deployment
trained
cloud‐based
Flask‐Gunicorn
API
enables
real‐time
inference,
ensuring
scalability
accessibility
for
industrial
research
applications.
proposed
addresses
key
limitations
existing
approaches
by
integrating
advanced
techniques,
handling
nonlinear
interactions,
providing
scalable
strategy.
contributes
development
interpretable
deployable
AI‐driven
informatics,
bridging
gap
between
data‐driven
predictions
fundamental
science
principles.
Язык: Английский
Integration of response surface methodology (RSM), machine learning (ML), and artificial intelligence (AI) for enhancing properties of polymeric nanocomposites‐A review
Polymer Composites,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 12, 2025
Abstract
This
review
elucidates
the
amalgamation
of
machine
learning
(ML),
artificial
intelligence
(AI),
and
response
surface
methodology
(RSM)
for
optimization
fabrication
enhancement
properties
polymeric
nanocomposites.
It
analyzes
recent
accomplishments,
methodologies,
future
possibilities
in
this
interdisciplinary
field.
Polymers
their
nanocomposites
are
garnering
attention
because
cost‐effectiveness,
biodegradability,
non‐toxicity.
Polymeric
have
been
employed
several
technical
applications;
nevertheless,
restricted
mechanical,
electrical,
thermal
impeded
extensive
use.
Numerous
additives,
including
clay,
fiber,
two‐dimensional
materials
such
as
graphene
or
MoS
2
,
were
extensively
nanofillers
to
enhance
qualities.
The
effects
filler
concentration
thoroughly
examined
by
conventional
approaches;
however,
via
statistical
techniques
may
be
more
suitable.
method
produces
accurate
results
with
a
reduced
number
tests.
Diverse
techniques,
Taguchi
RSM,
alongside
ML
algorithms,
can
ascertain
optimal
concentration,
type,
method,
characterization,
process
parameters
properties,
manufacturing,
efficiency
polymers
polymer‐based
superior
compared
methods.
Nonetheless,
ML/AI
also
utilized
attain
additional
improvements
requisite
thermal,
electrochemical
properties.
Recent
advancements
emphasized,
use
is
proposed
progress.
Highlights
Summarized
Presented
process,
production,
additive
various
polymers.
ML‐based
efficiency.
Future
directions:
AI
improve
nanocomposite
Язык: Английский