Water Science & Technology Water Supply,
Journal Year:
2023,
Volume and Issue:
23(8), P. 3359 - 3376
Published: July 31, 2023
Abstract
Highly
accurate
rainfall
prediction
can
provide
a
reliable
scientific
basis
for
human
production
and
life.
For
the
characteristics
of
occasional
sudden
changes
in
coastal
hilly
areas,
this
article
chooses
four
cities
eastern
Zhejiang
province
as
object
study
establishes
model
based
on
variational
mode
decomposition
(VMD),
reptile
search
algorithm
(RSA),
differentiable
neural
computer
(DNC).
The
VMD
reduces
complexity
sequence
data;
RSA
is
used
to
find
best-fit
function;
DNC
combines
advantages
recurrent
network
computational
processing
improve
problem
memory
forgetting
long
short-term
memory.
To
verify
accuracy
model,
results
are
compared
with
other
three
models,
show
that
VMD–RSA–DNC
has
best
maximum
minimum
relative
errors
9.62
0.17%,
respectively,
average
root-mean-square
error
5.43,
mean
absolute
percentage
3.59%,
Nash–Sutcliffe
efficiency
0.95
predicting
area.
This
provides
new
reference
method
construction
models.
Ecological Informatics,
Journal Year:
2024,
Volume and Issue:
82, P. 102755 - 102755
Published: Aug. 3, 2024
Streamflow
simulation
is
crucial
for
flood
mitigation,
ecological
protection,
and
water
resource
planning.
Process-based
hydrological
models
machine
learning
algorithms
are
the
mainstream
tools
streamflow
simulation.
However,
their
inherent
limitations,
such
as
time-consuming
large
data
requirements,
make
achieving
high-precision
simulations
challenging.
This
study
developed
a
hybrid
approach
to
simultaneously
improve
accuracy
computational
efficiency
of
simulation,
which
integrates
Block-wise
use
TOPMODEL
(BTOP)
model
into
eXtreme
Gradient
Boosting
(XGBoost),
i.e.,
BTOP_XGB.
In
this
approach,
BTOP
generates
simulated
using
Latin
hypercube
sampling
algorithm
instead
calibration
reduce
costs.
Then,
XGBoost
combines
with
multi-source
errors.
which,
serval
input
variable
selection
employed
choose
relevant
inputs
remove
redundant
information
model.
The
validated
compared
standalone
at
three
stations
in
Jialing
River
basin,
China.
results
show
that
performance
BTOP_XGB
significantly
better
than
models.
NSE
Beibei,
Xiaoheba,
Luoduxi
increases
by
54%,
21%,
83%,
respectively.
Meanwhile,
time
saved
>90%
original
calibrated
BTOP.
less
affected
parameter
sample
sizes
amounts,
demonstrating
robustness
simplifies
complexity
enhances
stability
learning,
jointly
improving
reliability
provides
potential
shortcut
over
basins
areas
or
limited
observed
data.
Ecological Informatics,
Journal Year:
2023,
Volume and Issue:
79, P. 102452 - 102452
Published: Dec. 28, 2023
In
recent
years,
the
application
of
Data-Driven
Models
(DDMs)
in
ecological
studies
has
garnered
significant
attention
due
to
their
capacity
accurately
simulate
complex
hydrological
processes.
These
models
have
proven
invaluable
comprehending
and
predicting
natural
phenomena.
However,
achieve
improved
outcomes,
certain
additive
components
such
as
signal
analysis
(SAM)
input
variable
selections
(IVS)
are
necessary.
SAMs
unveil
hidden
characteristics
within
time
series
data,
while
IVS
prevents
utilization
inappropriate
data.
realm
research,
understanding
these
patterns
is
pivotal
for
grasping
implications
streamflow
dynamics
guiding
effective
management
decisions.
Addressing
need
more
precise
forecasting,
this
study
proposes
a
novel
SAM
called
"Maximum
Energy
Entropy
(MEE)"
forecast
monthly
Ajichai
basin,
located
northwestern
Iran.
A
comparative
was
conducted,
pitting
MEE
against
well-known
methods
Discreet
Wavelet
(DW)
Wavelet-Entropy
(DWE),
ultimately
demonstrating
superiority
MEE.
The
results
showcased
superior
performance
our
proposed
method,
with
an
NSE
value
0.72,
compared
DW
(NSE
0.68)
DWE
0.68).
Furthermore,
exhibited
greater
reliability,
boasting
lower
Standard
Deviation
0.13
(0.26)
(0.19).
equips
researchers
decision-makers
accurate
predictions,
facilitating
well-informed
water
resource
planning.
To
further
evaluate
MEE's
accuracy
using
various
DDMs,
we
integrated
Artificial
Neural
Network
(ANN)
Genetic
Programming
(GP).
Additionally,
GP
served
method
selecting
appropriate
variables.
Ultimately,
combination
ANN
forecasting
model
(MEE-GP-ANN)
yielded
most
favorable
results.
Water Cycle,
Journal Year:
2024,
Volume and Issue:
5, P. 266 - 277
Published: Jan. 1, 2024
Long-term
river
streamflow
prediction
and
modeling
are
essential
for
water
resource
management
decision-making
related
to
resources.
This
research
paper
considers
the
importance
of
these
predictions
proposes
a
model
address
scarcity
scenarios
support
in
allocation,
flood
management,
drought
scenarios.
Machine
learning
(ML)
techniques
offer
promising
alternatives
improving
long-term
prediction.
However,
most
existing
studies
on
ML
models
have
focused
shorter
time
horizons,
limiting
their
broader
applicability.
Consequently,
there
is
need
dedicated
that
addresses
use
Considering
this
gap,
presents
an
ML-based
approach
learns
replicates
natural
flow
dynamics
river,
allowing
simulation
reduced
(25%
50%
reduction).
capability
allows
simulating
varying
severity,
providing
valuable
insights
service
managers.
study
significantly
contributes
progress
predicting
through
application
machine
models.
Moreover,
offers
recommendations
hydrologists
improve
future
efforts.
