Sustainability,
Journal Year:
2024,
Volume and Issue:
16(23), P. 10634 - 10634
Published: Dec. 4, 2024
Accurately
predicting
the
state
of
surface
water
quality
is
crucial
for
ensuring
sustainable
use
resources
and
environmental
protection.
This
often
requires
a
focus
on
range
factors
affecting
quality,
such
as
physical
chemical
parameters.
Tree
models,
with
their
flexible
tree-like
structure
strong
capability
partitioning
selecting
influential
features,
offer
clear
decision-making
rules,
making
them
suitable
this
task.
However,
an
individual
decision
tree
model
has
limitations
cannot
fully
capture
complex
relationships
between
all
influencing
parameters
quality.
Therefore,
study
proposes
method
combining
ensemble
models
voting
algorithms
to
predict
classification.
was
conducted
using
five
monitoring
sites
in
Qingdao,
representing
portion
many
municipal
environment
stations
China,
employing
single-factor
determination
stringent
standards.
The
soft
algorithm
achieved
highest
accuracy
99.91%,
addressed
imbalance
original
categories,
reaching
Matthews
Correlation
Coefficient
(MCC)
99.88%.
In
contrast,
conventional
machine
learning
algorithms,
logistic
regression
K-nearest
neighbors,
lower
accuracies
75.90%
91.33%,
respectively.
Additionally,
model’s
supervision
misclassified
data
demonstrated
its
good
rules.
trained
also
transferred
directly
at
13
Beijing,
where
it
performed
robustly,
achieving
hard
97.73%
MCC
96.81%.
countries’
systems,
different
qualities
correspond
uses,
magnitude
related
categories;
critical
can
even
determine
category.
are
highly
capable
handling
nonlinear
important
allowing
identify
exploit
interactions
parameters,
which
especially
when
multiple
together
there
significant
motivation
develop
model-based
prediction
models.
Revista Politécnica,
Journal Year:
2025,
Volume and Issue:
55(2), P. 1 - 16
Published: May 16, 2025
La
falta
del
recurso
hídrico
en
cantidad
y
calidad
ha
generado
diferentes
intereses
las
instituciones,
investigadores
científicos
estudiar
los
cuerpos
de
agua
para
el
desarrollo
humano.
El
objetivo
la
investigación
fue
explorar
características
hidroquímicas
subterránea
cuenca
baja
valle
río
Carrizal
mediante
técnicas
multivariantes
geoespaciales
que
permitan
establecer
este
esta
zona.
trabajo
consistió
tomar
muestras
catorce
pozos
observación,
cada
uno
con
distintos
usos
suelo.
Los
parámetros
se
evaluaron
fueron:
pH,
conductividad
eléctrica,
dureza,
sólidos
totales
disueltos,
relación
absorción
sodio,
además
cationes
aniones.
De
manera
general,
hidroquímicos
muestran
variable
dureza
encuentra
un
nivel
superior
al
permisible
su
uso,
mientras
que:
conductividad,
pH
mostraron
valores
bajos
sin
problemas
uso.
catión
calcio
(Ca2+)
representa
67
%
ion
Bicarbonato
75
siendo
concentraciones
mayoritarias
aniones,
respectivamente.
Profundizando
más
análisis
pudo
evidenciar
existente
entre
parámetro
totales,
calcio,
bicarbonato,
cloruro
sulfato.
determinada
por
mineralización
roca
madre,
esto
traduce
concentración
alta
correlación
aniones
Las
empleadas
exploración
permitieron
conocer
comportamientos
Carrizal.
Journal of Hydroinformatics,
Journal Year:
2024,
Volume and Issue:
26(11), P. 2798 - 2814
Published: Nov. 1, 2024
ABSTRACT
This
study
aims
to
identify
the
best
machine
learning
(ML)
approach
predict
concentrations
of
biochemical
oxygen
demand
(BOD),
nitrate,
and
phosphate.
Four
ML
techniques
including
Decision
tree,
Random
Forest,
Gradient
Boosting
XGBoost
were
compared
estimate
water
quality
parameters
based
on
biophysical
(i.e.,
population,
basin
area,
river
slope,
level,
stream
flow),
physicochemical
properties
conductivity,
turbidity,
pH,
temperature,
dissolved
oxygen)
input
parameters.
The
innovation
lies
in
combination
on-the-spot
variables
with
additional
characteristics
watershed.
model
performances
evaluated
using
coefficient
determination
(R2),
Nash-Sutcliffe
efficiency
(NSE),
Root
Mean
Squared
Error
(RMSE)
Kling-Gupta
Efficiency
(KGE)
coefficient.
robust
five-fold
cross-validation,
along
hyperparameter
tuning,
achieved
R2
values
0.71,
0.66,
0.69
for
phosphate,
BOD;
NSE
0.67,
0.65,
0.62,
KGE
0.64,
0.75,
0.60,
respectively.
yielded
good
results,
showcasing
superior
performance
when
considering
all
analysis
performed,
but
his
was
closely
match
by
other
algorithms.
overall
modeling
design
approach,
which
includes
careful
consideration
data
preprocessing,
dataset
splitting,
statistical
evaluation
metrics,
feature
analysis,
curve
are
just
as
important
algorithm
selection.
Applied Water Science,
Journal Year:
2024,
Volume and Issue:
14(12)
Published: Nov. 29, 2024
The
aims
of
this
study
are
capability
assessment
the
SWAT
model
and
SWAT-CUP
software
in
hydrological
simulation
evaluation
uncertainty
estimating
runoff.
In
modeling
process,
basin
was
divided
into
12
sub-basins
294
units
(HRUs).
Model
calibration
analysis
were
performed
using
sequential
fitting
(SUFI2)
algorithm
for
2000–2006
2007–2010,
respectively.
Based
on
sensitivity
results,
parameters
USLE_P
soil
protection
factor,
wet
density
(SOL_BD),
CN
among
most
important
determining
amount
output
Among
these
factors,
SCS-CN
recognized
as
sensitive
parameter.
coefficients
R2,
bR2,
Nash–Sutcliffe
index
(NS)
0.75,
0.59,
0.67
period
0.46,
0.24,
0.42
validation
period.
results
showed
performance
is
weak
stage
calibration.
This
due
to
lack
accuracy
precision
statistics
available
region,
water
collected
from
upstream
gardens
area,
well
existing
springs.
therefore
recommended
applications
arid
semiarid
catchments
within
Iran
with
similar
data.
Due
limited
availability
data
Iran,
has
not
assessed
compared
related
future
