A novel machine learning-based framework for the water quality parameters prediction using hybrid long short-term memory and locally weighted scatterplot smoothing methods
Journal of Hydroinformatics,
Год журнала:
2024,
Номер
26(5), С. 1059 - 1079
Опубликована: Апрель 12, 2024
ABSTRACT
Water
quality
prediction
is
crucial
for
effective
river
stream
management.
Dissolved
oxygen,
conductivity
and
chemical
oxygen
demand
are
vital
parameters
water
quality.
Development
of
machine
learning
(ML)
deep
(DL)
methods
made
them
widely
used
in
this
domain.
Sophisticated
DL
techniques,
especially
long
short-term
memory
(LSTM)
networks,
required
accurate,
real-time
multistep
prediction.
LSTM
networks
predicting
due
to
their
ability
handle
long-term
dependencies
sequential
data.
We
propose
a
novel
hybrid
approach
combining
with
data
smoothing
method.
The
Sava
at
the
Jamena
hydrological
station
serves
as
case
study.
Our
workflow
uses
alongside
LOcally
WEighted
Scatterplot
Smoothing
(LOWESS)
technique
filtering.
For
comparison,
Support
Vector
Regressor
(SVR)
baseline
Performance
evaluated
using
Root
Mean
Squared
Error
(RMSE)
Coefficient
Determination
R2
metrics.
Results
demonstrate
that
outperforms
method,
an
up
0.9998
RMSE
0.0230
on
test
set
dissolved
oxygen.
Over
5-day
period,
our
achieves
0.9912
0.1610
confirming
it
reliable
method
Язык: Английский
A water quality prediction approach for the Downstream and Delta of Dongjiang River Basin under the joint effects of water intakes, pollution sources, and climate change
Journal of Hydrology,
Год журнала:
2024,
Номер
640, С. 131686 - 131686
Опубликована: Июль 16, 2024
Язык: Английский
Interpretable Ai-Enhanced Reliable River Water Quality Prediction with Multi Remote Sensing Data Sources: Insights from Meteorological & Spatial-Temporal Variables
Опубликована: Янв. 1, 2025
Язык: Английский
Ensemble machine learning using hydrometeorological information to improve modeling of quality parameter of raw water supplying treatment plants
Journal of Environmental Management,
Год журнала:
2024,
Номер
362, С. 121378 - 121378
Опубликована: Июнь 1, 2024
Source
and
raw
water
quality
may
deteriorate
due
to
rainfall
river
flow
events
that
occur
in
watersheds.
The
effects
on
are
normally
detected
drinking
treatment
plants
(DWTPs)
with
a
time-lag
after
these
the
Early
warning
systems
(EWSs)
DWTPs
require
models
high
accuracy
order
anticipate
changes
parameters.
Ensemble
machine
learning
(EML)
techniques
have
recently
been
used
for
modeling
improve
decrease
variance
outcomes.
We
three
decision-tree-based
EML
(random
forest
[RF],
gradient
boosting
[GB],
eXtreme
Gradient
Boosting
[XGB])
predict
two
critical
parameters
DWTPs,
Turbidity
UV
absorbance
(UV254),
using
time
series
as
predictors.
When
turbidity,
(rRF−Tu2=0.87,
rGB−Tu2=0.80
rXGB−Tu2=0.81)
showed
very
good
performance
metrics.
For
UV254,
(rRF−UV2=0.89,
rGB−UV2=0.85
rXGB−UV2=0.88)
again
Results
from
this
study
suggest
approaches
could
be
EWSs
of
enhance
decision-making
DWTPs.
Язык: Английский