This
work
aimed
to
study
the
modeling
of
organic
pollution
waters
Déganobo
Lake
system
by
three
models:
Multiple
Linear
Regression
model
(MLR
model),
Mutilayer
Perceptron
(MLP
model)
and
Regression/
hybrid
(MLR/MLP
model).In
its
implementation,
chemical
oxygen
demand
(COD)
these
waters,
obtained
from
August
2021
July
2022,
was
used.Two
approaches
were
done
in
case
their
COD
MLP
MLR/MLP
model:
static
dynamic
modeling.The
results
have
highlighted
low
predictions
MLR
(36.2
%)
models
(6-8-1
for
7-3-1
modeling,
both
predicting
less
than
35%
experimental
values
with
high
error
(RMSE
upper
1.30
relative
0.750).However,
(MLR/6-3-1
MLR/7-3-1
modeling)
well
predicted
around
99%
very
errors
0.0001
0.006
cases).So,
most
efficient
predict
waters.The
accuracy
this
ecological
again
provided
during
study.
RSC Advances,
Год журнала:
2024,
Номер
14(13), С. 9003 - 9019
Опубликована: Янв. 1, 2024
The
waste
management
industry
uses
an
increasing
number
of
mathematical
prediction
models
to
accurately
forecast
the
behavior
organic
pollutants
during
catalytic
degradation.
The Science of The Total Environment,
Год журнала:
2024,
Номер
951, С. 175424 - 175424
Опубликована: Авг. 12, 2024
Hypoxia
is
one
of
the
fundamental
threats
to
water
quality
globally,
particularly
for
partially
enclosed
basins
with
limited
renewal,
such
as
coastal
lagoons.
This
work
proposes
combined
use
a
machine
learning
technique,
field
observations,
and
data
derived
from
hydrodynamic
heat
exchange
numerical
model
predict,
forecast
up
10
days
in
advance,
occurrence
hypoxia
eutrophic
lagoon.
The
random
forest
algorithm
used,
training
validating
set
models
classify
dissolved
oxygen
levels
Orbetello
lagoon,
central
Mediterranean
Sea
(Italy),
has
provided
test
case
assessing
reliability
proposed
methodology.
Results
proved
that
methodology
effective
providing
reliable
short-term
evaluation
DO
levels,
high
resolution
both
time
space
throughout
an
entire
An
overall
classification
accuracy
91
%
was
found
models,
score
identifying
severe
-
i.e.
hourly
lower
than
2
mg/l
86
%.
predictors
extracted
allows
us
overcome
intrinsic
limitation
modelling
approaches
which
rely
on
input
relatively
few,
local
measurements,
inability
capture
spatial
heterogeneity
distributions,
unless
several
measuring
points
are
available.
methodological
approach
application
similar
environments.
Ecological Informatics,
Год журнала:
2024,
Номер
82, С. 102695 - 102695
Опубликована: Июнь 20, 2024
Accurate
and
efficient
long-term
prediction
of
marine
dissolved
oxygen
(DO)
is
crucial
for
the
sustainable
development
aquaculture.
However,
multidimensional
time
dependency
lag
effects
chemical
variables
present
significant
challenges
when
handling
multiple
inputs
in
univariate
tasks.
To
address
these
issues,
we
designed
a
multivariate
time-series
model
(LMFormer)
based
on
Transformer
architecture.
The
proposed
decomposition
strategy
effectively
leverages
feature
information
at
different
scales,
thereby
reducing
loss
critical
information.
Additionally,
dynamic
variable
selection
gating
mechanism
was
to
optimize
collinearity
problem
data
extraction
process.
Finally,
an
two-stage
attention
architecture
capture
long-range
dependencies
between
features.
This
study
conducted
high-precision
7-day
advance
DO
predictions
two
case
studies,
environmentally
stable
Shandong
Peninsula
China
San
Juan
Islands
United
States,
which
are
affected
by
extreme
conditions
such
as
ocean
currents.
experimental
results
demonstrate
superior
performance
generalizability
model.
In
case,
mean
absolute
error
(MAE),
root
square
(RMSE),
coefficient
determination
(R2),
Kling–Gupta
efficiency
(KGE)
reached
0.0159,
0.126,
0.9743,
0.9625,
respectively.
MAE
reduced
average
42.34%
compared
that
baseline
model,
RMSE
24.57%,
R2
increased
22.54%,
KGE
improved
12.04%.
Overall,
achieves
data,
providing
valuable
references
management
decision-making
Applied Sciences,
Год журнала:
2025,
Номер
15(3), С. 1471 - 1471
Опубликована: Янв. 31, 2025
Dissolved
oxygen
(DO)
is
a
vital
water
quality
index
influencing
biological
processes
in
aquatic
environments.
Accurate
modeling
of
DO
levels
crucial
for
maintaining
ecosystem
health
and
managing
freshwater
resources.
To
this
end,
the
present
study
contributes
Bayesian-optimized
explainable
machine
learning
(ML)
model
to
reveal
dynamics
predict
concentrations.
Three
ML
models,
support
vector
regression
(SVR),
tree
(RT),
boosting
ensemble,
coupled
with
Bayesian
optimization
(BO),
are
employed
estimate
Mississippi
River.
It
concluded
that
BO-SVR
outperforms
others,
achieving
coefficient
determination
(CD)
0.97
minimal
error
metrics
(root
mean
square
=
0.395
mg/L,
absolute
0.303
mg/L).
Shapley
Additive
Explanation
(SHAP)
analysis
identifies
temperature,
discharge,
gage
height
as
most
dominant
factors
affecting
levels.
Sensitivity
confirms
robustness
models
under
varying
input
conditions.
With
perturbations
from
5%
30%,
temperature
sensitivity
ranges
1.0%
6.1%,
discharge
0.9%
5.2%,
0.8%
5.0%.
Although
experience
reduced
accuracy
extended
prediction
horizons,
they
still
achieve
satisfactory
results
(CD
>
0.75)
forecasting
periods
up
30
days.
The
established
also
exhibit
higher
than
many
prior
approaches.
This
highlights
potential
BO-optimized
reliable
forecasting,
offering
valuable
insights
resource
management.
