Remote Sensing,
Год журнала:
2022,
Номер
14(21), С. 5461 - 5461
Опубликована: Окт. 30, 2022
The
ocean
chlorophyll-a
(Chl-a)
concentration
is
an
important
variable
in
the
marine
environment,
abnormal
distribution
of
which
closely
related
to
hazards
red
tides.
Thus,
accurate
prediction
its
East
China
Sea
(ECS)
greatly
for
preventing
water
eutrophication
and
protecting
coastal
ecological
environment.
Processed
by
two
different
pre-processing
methods,
10-year
(2011–2020)
satellite-observed
data
logarithmic
were
used
as
long
short-term
memory
(LSTM)
neural
network
training
datasets
this
study.
2021
comparison
results.
past
15
days’
predict
five
following
days.
Results
showed
that
predictions
obtained
both
methods
could
simulate
seasonal
Chl-a
ECS
effectively.
Moreover,
performance
model
driven
original
values
was
better
medium-
low-concentration
regions.
However,
high-concentration
region,
extreme
concentrations
data-driven
LSTM
models
underestimation,
considering
better.
sensitivity
experiments
accuracy
decreased
considerably
when
backward
time
step
increased.
In
study,
only
chlorophyll-a,
whose
forecasted,
effect
other
relevant
elements
on
not
considered,
current
weakness
Toxins,
Год журнала:
2023,
Номер
15(10), С. 608 - 608
Опубликована: Окт. 10, 2023
Harmful
algal
blooms
(HABs)
are
a
serious
threat
to
ecosystems
and
human
health.
The
accurate
prediction
of
HABs
is
crucial
for
their
proactive
preparation
management.
While
mechanism-based
numerical
modeling,
such
as
the
Environmental
Fluid
Dynamics
Code
(EFDC),
has
been
widely
used
in
past,
recent
development
machine
learning
technology
with
data-based
processing
capabilities
opened
up
new
possibilities
prediction.
In
this
study,
we
developed
evaluated
two
types
learning-based
models
prediction:
Gradient
Boosting
(XGBoost,
LightGBM,
CatBoost)
attention-based
CNN-LSTM
models.
We
Bayesian
optimization
techniques
hyperparameter
tuning,
applied
bagging
stacking
ensemble
obtain
final
results.
result
was
derived
by
applying
optimal
techniques,
applicability
evaluated.
When
predicting
an
technique,
it
judged
that
overall
performance
can
be
improved
complementing
advantages
each
model
averaging
errors
overfitting
individual
Our
study
highlights
potential
emphasizes
need
incorporate
latest
into
important
field.
Annual Review of Environment and Resources,
Год журнала:
2023,
Номер
48(1), С. 123 - 147
Опубликована: Сен. 8, 2023
Harmful
cyanobacterial
blooms
(CyanoHABs)
impact
lakes,
estuaries,
and
freshwater
reservoirs
worldwide.
The
duration,
severity,
spread
of
CyanoHABs
have
markedly
increased
over
the
past
decades
will
likely
continue
to
increase.
This
article
addresses
universal
phenomena
occurring
in
many
ecosystems
Based
on
analysis
ecophysiological
traits
bloom-forming
cyanobacteria
their
interactions
with
environmental
processes,
we
summarize
decipher
driving
forces
leading
initiation,
outbreak,
persistence
blooms.
Due
coupling
effects
eutrophication,
rising
CO
2
levels
global
warming,
a
multidisciplinary
joint
research
approach
is
critical
for
better
understanding
CyanoHAB
phenomenon
its
prediction,
remediation,
prevention.
There
an
urgent
need
evaluate
guide
proper
use
bloom
control
techniques
at
large
scales,
using
science-based
environmentally
friendly
approaches.
Water Research X,
Год журнала:
2023,
Номер
21, С. 100207 - 100207
Опубликована: Ноя. 16, 2023
Water
quality
is
substantially
influenced
by
a
multitude
of
dynamic
and
interrelated
variables,
including
climate
conditions,
landuse
seasonal
changes.
Deep
learning
models
have
demonstrated
predictive
power
water
due
to
the
superior
ability
automatically
learn
complex
patterns
relationships
from
variables.
Long
short-term
memory
(LSTM),
one
deep
for
prediction,
type
recurrent
neural
network
that
can
account
longer-term
traits
time-dependent
data.
It
most
widely
applied
used
predict
time
series
First,
we
reviewed
applications
standalone
LSTM
discussed
its
calculation
time,
prediction
accuracy,
good
robustness
with
process-driven
numerical
other
machine
learning.
This
review
was
expanded
into
model
data
pre-processing
techniques,
Complete
Ensemble
Empirical
Mode
Decomposition
Adaptive
Noise
method
Synchrosqueezed
Wavelet
Transform.
The
then
focused
on
coupling
convolutional
network,
attention
transfer
coupled
networks
their
performance
over
model.
We
also
emphasized
influence
static
variables
in
transformation
dataset.
Outlook
further
challenges
were
addressed.
outlook
research
application
hydrology
concludes
review.
