Potable
water
accessibility
is
becoming
the
scarcest
matter
all
over
world.
It
essential
to
assess
quality
indices.
This
paper,
aimed
create
a
user-friendly
MATLAB
interface
tailored
for
practitioners
with
limited
programming
experience.
built
on
base
of
natural
phenomena
and
consists
algorithmic
complex
solutions
by
combining
particle
swarm
optimization
(PSO)
support
vector
machines
(SVMs).
employed
fundamental
Artificial
Intelligent
Machine
Learning
methods
predict
quality,
merging
PSO
SVMs.
investigation
delved
into
classification
predictive
AI
systems,
leading
development
four
individual
models,
hybrid
metaheuristic
regression
model,
ensemble
techniques
(stacking,
voting,
bagging).
Initial
focus
singular
technique,
SVM.
The
primary
goal
propose
versatile
framework
modeling.
approach
enhance
both
accuracy
practical
application
models.
resulting
empowers
administrators
hydrologists
select
suitable
analytical
tools
management
using
techniques.
system
shows
96%
accurate
result.
Frontiers in Earth Science,
Journal Year:
2024,
Volume and Issue:
12
Published: April 8, 2024
The
status
of
surrounding
rocks
dramatically
influences
the
safety
construction
workers,
so
quality
assessment
has
great
significance.
uniaxial
saturated
compressive
strength
rock
(X
1
),
index
2
frictional
coefficient
structural
surface
3
joint
spacing
4
state
groundwater(X
5
and
integrity
6
)
are
selected
as
initial
evaluation
index.
Then,
game
theory
combination
weighting-normal
cloud
model
is
introduced.
Second,
certainty
degree
matrix
each
established,
weight
coefficients
indexes
determined
based
on
weighting
method.
Finally,
level
judged.
Compared
with
traditional
methods,
proposed
solves
fuzziness
randomness
different
indexes,
improves
reliability
process,
enhances
predictive
accuracy
results.
In
addition,
it
can
provide
a
solution
scheme
for
indicators,
which
difficult
to
quantify,
reduce
influence
human
factors.
results
obtained
from
suggested
consistent
current
specification.
Its
approaches
100%,
method
feasible
rocks,
providing
new
technique
approach
assessing
risk
rocks.
Buildings,
Journal Year:
2025,
Volume and Issue:
15(3), P. 495 - 495
Published: Feb. 5, 2025
Natural
and
man-made
disasters
significantly
challenge
the
safety
stability
of
urban
infrastructure
(UI),
disrupting
daily
operations
impeding
economic
development.
However,
existing
research
on
resilience
(UIR)
lacks
comprehensive
categorization
critical
infrastructure,
insufficiently
considers
impacts
natural
disasters,
offers
limited
empirical
analysis
interactions
among
pressure,
state,
response
(PSR)
dimensions.
This
study
aims
to
establish
a
UIR
assessment
index
examine
coupling
coordination
(CC)
levels
obstacle
indicators
PSR
across
four
Chinese
municipalities.
The
results
reveal
that
(1)
is
most
influential
overall
more
amenable
artificial
interventions
than
pressure
state
resilience;
(2)
generally,
CC
in
municipalities
were
relatively
high,
advancing
from
an
inferiorly
intermediately
balanced
development
stage
over
period,
highlighting
effective
strategies
such
as
enhanced
resource
allocation
post-disaster
recovery
initiatives
are
recommended
for
adoption
by
similar
cities;
(3)
identified,
targeted
proposed
based
each
municipality’s
unique
characteristics.
findings
offer
theoretical
insights
practical
implications
enhancing
perspective
utilizing
models.
Research Square (Research Square),
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 27, 2025
Abstract
Groundwater
is
a
commodity
we
depend
on
for
diverse
needs,
and
maintaining
its
quality
must
be
considered
vital.
We
Machine
Learning
(ML)
operations
Explainable
Artificial
Intelligence
(XAI)
to
predict
the
nitrate
concentration
levels
in
groundwater
of
India
years
2019
2023.
The
variables
used
this
study
are
Latitude,
Longitude,
pH,
EC,
CO3,
HCO3,
Cl,
SO4,
PO4,
TH,
Ca,
Mg,
Na,
K,
F,
TDS,
SiO2,
NO3
dataset
Fe,
As,
U,
2023
dataset.
prepared
GIS
surface
maps
using
interpolation
supported
by
Empirical
Bayesian
Kriging
method.
investigated
model
efficiency
feature
importance
presence
absence
location
attributes.
19
ML
models
filtered
Light
Gradient
Boosting
(LightGBM)
Liner
Regression
(LR)
that
exhibited
relatively
better
accuracy.
first
trained
these
fed
them
XAI
via
SHAP
(SHapley
Additive
exPlanations),
which
was
dependent
game
theory.
obtained
28.23%
24.88%
increase
accuracy
when
comparing
datasets
with
attributes,
respectively.
also
observed
28.3%
without
attribute
used.
conclude
can
integrated
improve
prediction
studies.
