Journal of Water Supply Research and Technology—AQUA,
Journal Year:
2019,
Volume and Issue:
68(7), P. 547 - 561
Published: Oct. 22, 2019
Abstract
In
this
research,
general
regression
neural
network
(GRNN),
Hammerstein-wiener
(HW)
and
non-linear
autoregressive
with
exogenous
(NARX)
network,
least
square
support
vector
machine
(LSSVM)
models
were
employed
for
multi-parametric
(Hardness
(mg/L),
turbidity
(Turb)
(μs/cm),
pH
suspended
solid
(SS)
(mg/L))
modeling
of
Tamburawa
water
treatment
plant
(TWTP)
at
Kano,
Nigeria.
The
weekly
data
from
the
TWTP
used
predictive
evaluated
based
on
several
numerical
indicators.
Four
different
ensemble
techniques
(GRNN-E,
HW-E,
NARX-E,
LSSVM-E)
subsequently
employed.
comparison
results
showed
that
HW
served
as
best
model
simulation
Hardness,
Turb,
SS
while
NARX
demonstrated
high
capability
in
predicting
pH.
Yet,
system
identification
attained
overall
performance
among
four
approaches.
offers,
therefore,
a
reliable
intelligent
approach
treated
should
be
explored
tool
TWTP.
Among
models,
GRNN-E
proved
merit
increased
accuracy
single
significantly
up
to
30%
Hardness
34%
pH,
37%
regards
models.
Applied Sciences,
Journal Year:
2020,
Volume and Issue:
10(17), P. 5776 - 5776
Published: Aug. 20, 2020
Water
quality
prediction
plays
an
important
role
in
environmental
monitoring,
ecosystem
sustainability,
and
aquaculture.
Traditional
methods
cannot
capture
the
nonlinear
non-stationarity
of
water
well.
In
recent
years,
rapid
development
artificial
neural
networks
(ANNs)
has
made
them
a
hotspot
prediction.
We
have
conducted
extensive
investigation
analysis
on
ANN-based
from
three
aspects,
namely
feedforward,
recurrent,
hybrid
architectures.
Based
151
papers
published
2008
to
2019,
23
types
variables
were
highlighted.
The
primarily
collected
by
sensor,
followed
specialist
experimental
equipment,
such
as
UV-visible
photometer,
there
is
no
mature
sensor
for
measurement
at
present.
Five
different
output
strategies,
Univariate-Input-Itself-Output,
Univariate-Input-Other-Output,
Multivariate-Input-Other(multi),
Multivariate-Input-Itself-Other-Output,
Multivariate-Input-Itself-Other
(multi)-Output,
are
summarized.
From
results
review,
it
can
be
concluded
that
ANN
models
capable
dealing
with
modeling
problems
rivers,
lakes,
reservoirs,
wastewater
treatment
plants
(WWTPs),
groundwater,
ponds,
streams.
many
review
articles
useful
researchers
similar
fields.
Several
new
architectures
presented
study,
recurrent
structures,
able
improve
future
development.
Hydrology and earth system sciences,
Journal Year:
2021,
Volume and Issue:
25(5), P. 2951 - 2977
Published: May 31, 2021
Abstract.
Water
temperature
in
rivers
is
a
crucial
environmental
factor
with
the
ability
to
alter
hydro-ecological
as
well
socio-economic
conditions
within
catchment.
The
development
of
modelling
concepts
for
predicting
river
water
and
will
be
essential
effective
integrated
management
adaptation
strategies
future
global
changes
(e.g.
climate
change).
This
study
tests
performance
six
different
machine-learning
models:
step-wise
linear
regression,
random
forest,
eXtreme
Gradient
Boosting
(XGBoost),
feed-forward
neural
networks
(FNNs),
two
types
recurrent
(RNNs).
All
models
are
applied
using
data
inputs
daily
prediction
10
Austrian
catchments
ranging
from
200
96
000
km2
exhibiting
wide
range
physiographic
characteristics.
evaluated
input
sets
include
combinations
means
air
temperature,
runoff,
precipitation
radiation.
Bayesian
optimization
optimize
hyperparameters
all
models.
To
make
results
comparable
previous
studies,
widely
used
benchmark
additionally:
regression
air2stream.
With
mean
root
squared
error
(RMSE)
0.55
∘C,
tested
could
significantly
improve
compared
(1.55
∘C)
air2stream
(0.98
∘C).
In
general,
show
very
similar
models,
median
RMSE
difference
0.08
∘C
between
From
both
FNNs
XGBoost
performed
best
4
catchments.
RNNs
best-performing
largest
catchment,
indicating
that
mainly
perform
when
processes
long-term
dependencies
important.
Furthermore,
was
observed
hyperparameter
showing
importance
optimization.
Especially
FNN
model
showed
an
extremely
large
standard
deviation
1.60
due
chosen
hyperparameters.
evaluates
variables,
training
characteristics
stream
prediction,
acting
basis
regional
multi-catchment
preprocessing
steps
implemented
open-source
R
package
wateRtemp
provide
easy
access
these
approaches
facilitate
further
research.
