International Journal of Design & Nature and Ecodynamics,
Journal Year:
2024,
Volume and Issue:
19(02), P. 605 - 611
Published: April 25, 2024
The
Water
Quality
Index
(WQI)
is
an
effective
water
test
that
assesses
quality,
identifies
contaminants,
and
aids
in
decision-making.However,
it
inefficient
to
analyze
samples
laboratories
due
high
costs,
time-consuming
processes,
limited
ability
record
temporal
or
geographical
oscillations.Recently,
the
use
of
modern
technologies
such
as
Remote
Sensing
(RS)
data,
Geographic
Information
Systems
(GIS),
Artificial
Neural
Networks
(ANN),
combination
with
survey
has
confirmed
efficient
tool
generate
WQI
map
Euphrates
River
Ramadi,
Iraq.In
present
study,
RS
Landsat
8
9
images,
laboratory
tests
were
used
develop
a
database
for
based
on
spectral
reflectance
using
radial
basis
neural
network
model.The
result
this
model
was
then
manipulated
within
ArcGIS
10.8
spatial
analyst
digital
WQI.This
evaluated
seven
criteria,
which
are
correlation
coefficient
(r),
mean
absolute
error,
normalized
lowest
maximum
root
square
equation
coefficients
(RMSE).The
value
0.93,
shows
remarkable
prediction
accuracy.Therefore,
calculation
method
calculating
producing
precise
maps
quality.
Water,
Journal Year:
2024,
Volume and Issue:
16(21), P. 3082 - 3082
Published: Oct. 28, 2024
Scouring
is
a
major
concern
affecting
the
overall
stability
and
safety
of
bridge.
The
current
research
investigated
effectiveness
various
artificial
intelligence
(AI)
techniques,
such
as
neural
networks
(ANNs),
adaptive
neuro-fuzzy
inference
system
(ANFIS),
random
forest
(RF),
for
scouring
depth
prediction
around
bridge
abutment.
This
study
attempted
to
make
comparative
analysis
between
these
AI
models
empirical
equations
developed
by
researchers.
paper
utilized
dataset
water
(Y),
flow
velocity
(V),
discharge
(Q),
sediment
particle
diameter
(d50)
from
controlled
laboratory
setting.
An
efficient
optimization
tool
(MATLAB
Optimization
Tool
(version
R2023a))
was
used
develop
scour
estimation
formula
abutments.
findings
investigation
demonstrated
superior
performance
models,
especially
ANFIS
model,
over
precisely
capturing
non-linear
complex
interactions
parameters.
Moreover,
result
sensitivity
be
most
influencing
parameters
results
highlight
precise
accurate
abutment
using
models.
However,
equation
(Equation
2)
better
with
higher
R-value
0.90
lower
MSE
value
0.0012
compared
other
equations.
revealed
that
ANFIS,
when
combined
fuzzy
logic
systems,
produced
highly
ANN
Geomatics Natural Hazards and Risk,
Journal Year:
2024,
Volume and Issue:
15(1)
Published: July 9, 2024
Soil
erosion
significantly
impacts
dam
functionality
by
leading
to
reservoir
siltation,
reducing
capacity,
and
heightening
flood
risks.
This
study
aims
map
soil
within
a
Geographic
Information
Systems
(GIS)
framework
estimate
the
siltation
of
K'sob
compare
these
estimates
with
bathymetric
observations.
Focused
on
one
Hodna
basin's
sub-basins,
watershed
(1477
km2),
assessment
utilizes
Revised
Universal
Loss
Equation
(RUSLE)
integrated
GIS
remote
sensing
data
predict
spatial
distribution
erosion.
Remote
were
pivotal
in
updating
land
cover
parameters
critical
for
RUSLE,
enhancing
precision
our
predictions.
Our
results
indicate
an
average
annual
rate
7.83
t/ha,
variations
ranging
from
0
224
t/ha/year.
With
typical
relative
error
about
13%
predictions,
figures
confirm
robustness
methodology.
These
insights
are
crucial
crafting
mitigation
strategies
areas
facing
high
extreme
loss
will
assist
governmental
agencies
prioritizing
actions
formulating
effective
management
policies.
Future
studies
should
explore
integration
real-time
advanced
modeling
techniques
further
refine
predictions
expand
their
applicability
similar
environmental
assessments.
Scientific Reports,
Journal Year:
2023,
Volume and Issue:
13(1)
Published: Oct. 25, 2023
This
study
aims
to
assess
the
practicality
of
utilizing
artificial
intelligence
(AI)
replicate
adsorption
capability
functionalized
carbon
nanotubes
(CNTs)
in
context
methylene
blue
(MB)
removal.
The
process
generating
involved
pyrolysis
acetylene
under
conditions
that
were
determined
be
optimal.
These
included
a
reaction
temperature
550
°C,
time
37.3
min,
and
gas
ratio
(H2/C2H2)
1.0.
experimental
data
pertaining
MB
on
CNTs
was
found
extremely
well-suited
Pseudo-second-order
model,
as
evidenced
by
an
R2
value
0.998,
X2
5.75,
qe
163.93
(mg/g),
K2
6.34
×
10-4
(g/mg
min).The
system
exhibited
best
agreement
with
Langmuir
yielding
0.989,
RL
0.031,
qm
250.0
mg/g.
results
AI
modelling
demonstrated
remarkable
performance
using
recurrent
neural
network,
achieving
highest
correlation
coefficient
=
0.9471.
Additionally,
feed-forward
network
yielded
0.9658.
modeling
hold
promise
for
accurately
predicting
capacity
CNTs,
which
can
potentially
enhance
their
efficiency
removing
from
wastewater.
