Buildings,
Год журнала:
2024,
Номер
14(9), С. 2894 - 2894
Опубликована: Сен. 13, 2024
This
study
focused
on
exploring
the
utilization
of
a
one-part
geopolymer
(OPG)
as
sustainable
alternative
binder
to
ordinary
Portland
cement
(OPC)
in
soil
stabilization,
offering
significant
environmental
advantages.
The
unconfined
compressive
strength
(UCS)
was
key
index
for
evaluating
efficacy
OPG
traditionally
demanding
substantial
resources
terms
cost
and
time.
In
this
research,
four
distinct
deep
learning
(DL)
models
(Artificial
Neural
Network
[ANN],
Backpropagation
[BPNN],
Convolutional
[CNN],
Long
Short-Term
Memory
[LSTM])
were
employed
predict
UCS
OPG-stabilized
soft
clay,
providing
more
efficient
precise
methodology.
Among
these
models,
CNN
exhibited
highest
performance
(MAE
=
0.022,
R2
0.9938),
followed
by
LSTM
0.0274,
0.9924)
BPNN
0.0272,
0.9921).
Wasserstein
Generative
Adversarial
(WGAN)
further
utilized
generate
additional
synthetic
samples
expanding
training
dataset.
incorporation
generated
WGAN
into
set
DL
led
improved
performance.
When
number
achieved
200,
WGAN-CNN
model
provided
most
accurate
results,
with
an
value
0.9978
MAE
0.9978.
Furthermore,
assess
reliability
gain
insights
influence
input
variables
predicted
outcomes,
interpretable
Machine
Learning
techniques,
including
sensitivity
analysis,
Shapley
Additive
Explanation
(SHAP),
1D
Partial
Dependence
Plot
(PDP)
analyzing
interpreting
models.
research
illuminates
new
aspects
application
real
data
properties
soil,
contributing
saving
time
cost.
Geosciences,
Год журнала:
2024,
Номер
14(9), С. 244 - 244
Опубликована: Сен. 15, 2024
This
study
explores
the
transformative
potential
of
artificial
intelligence
(AI)
in
revolutionizing
earthquake
risk
mitigation
across
six
key
areas.
Unlike
traditional
approaches,
this
paper
examines
how
AI-driven
innovations
can
uniquely
enhance
early
warning
systems,
enabling
real-time
structural
health
monitoring,
and
providing
dynamic,
multi-hazard
assessments
that
seamlessly
integrate
seismic
data
with
other
natural
hazards
such
as
tsunamis
landslides.
It
introduces
groundbreaking
applications
AI
earthquake-resilient
design,
where
generative
design
algorithms
predictive
analytics
create
structures
optimally
balance
safety,
cost,
sustainability.
The
also
presents
a
novel
discussion
on
ethical
implications
domain,
stressing
critical
need
for
transparency,
accountability,
bias
mitigation.
Looking
forward,
manuscript
envisions
development
advanced
platforms
capable
delivering
real-time,
personalized
assessments,
immersive
public
training
programs,
collaborative
tools
adapt
to
evolving
data.
These
promise
not
only
significantly
current
preparedness
but
pave
way
toward
future
societal
impact
earthquakes
is
drastically
reduced.
work
underscores
AI’s
role
shaping
safer,
more
resilient
future,
emphasizing
importance
continued
innovation,
governance,
efforts.
Energies,
Год журнала:
2025,
Номер
18(4), С. 918 - 918
Опубликована: Фев. 14, 2025
This
paper
explores
the
applications
and
impacts
of
artificial
intelligence
(AI)
in
building
envelopes
interior
space
design.
The
relevant
literature
was
searched
using
databases
such
as
Science
Direct,
Web
Science,
Scopus,
CNKI,
89
studies
were
selected
for
analysis
based
on
PRISMA
protocol.
first
analyzes
role
AI
transforming
architectural
design
methods,
particularly
its
different
roles
auxiliary,
collaborative,
leading
processes.
It
then
discusses
AI’s
energy-efficient
renovation
envelopes,
smart
façade
cold
climate
buildings,
thermal
imaging
detection.
Furthermore,
this
summarizes
AI-based
environment
covering
current
state
research,
applications,
impacts,
challenges
both
domestically
internationally.
Finally,
looks
ahead
to
broad
prospects
technology
architecture
fields
while
addressing
related
integration
personalized
environmental
sustainability
concepts.
Advancements
in
artificial
intelligence,
notably
the
groundbreaking
efforts
deep
learning
exemplified
by
physics-informed
neural
networks,
have
opened
up
innovative
pathways
for
addressing
intricate
ocean
acoustic
problems.
However,
conventional
networks
are
limited
solving
high-frequency
forward
and
inverse
This
paper
introduces
a
novel
generative
adversarial
network
integrating
forward-solving
(generator)
an
parameter-estimating
(discriminator).
The
generator
incorporates
convolutional
with
hard-constrained
boundary
conditions
optimized
loss
functions
to
effectively
predict
solution
governed
time-domain
wave
equation.
For
problems,
discriminator
is
introduced
parameter
estimation
complete
network.
Furthermore,
customized
optimization
strategies
adaptive
weighting
function
devised
boost
training
performance
further.
test
results
of
both
reverse
cases
show
advantage
our
model
over
existing
methods
terms
accuracy.
result
indicates
its
vast
potential
applications
acoustics
engineering.
