Sustainability,
Год журнала:
2024,
Номер
16(19), С. 8324 - 8324
Опубликована: Сен. 25, 2024
Carbon
trading
has
garnered
considerable
attention
as
a
pivotal
policy
instrument
for
advancing
carbon
peaking
and
neutrality,
which
are
essential
components
of
sustainable
development.
The
capacity
to
precisely
anticipate
the
cost
significant
implications
optimal
deployment
market
mechanisms,
economic
advancement
technological
innovations
in
corporate
emissions
reduction,
facilitation
international
energy
adjustments.
To
this
end,
paper
proposes
novel
price
prediction
tool
that
employs
four-step
process:
decomposition,
reconstruction,
prediction,
integration.
This
innovative
approach
first
utilizes
Improved
Complete
Ensemble
Empirical
Mode
Decomposition
with
Adaptive
Noise
(ICEEMDAN),
then
reconstructs
decomposition
set
using
multi-scale
entropy
(MSE),
finally
uses
Long
Short-Term
Memory
neural
network
model
(LSTM)
enhanced
by
Grey
Wolf
Optimizer
(GWO)
predict
emission
price.
experimental
results
demonstrate
achieves
high
accuracy
both
EU
series
China’s
seven
major
markets,
rates
99.10%
99.60%
Hubei
respectively.
represents
an
improvement
approximately
3.1%
over
ICEEMDAN-LSTM
0.91%
ICEEMDAN-MSE-LSTM
model,
thereby
contributing
more
efficient
practices.
Water Resources Research,
Год журнала:
2023,
Номер
59(9)
Опубликована: Сен. 1, 2023
Abstract
Accurate
runoff
forecasting
plays
a
vital
role
in
issuing
timely
flood
warnings.
Whereas,
previous
research
has
primarily
focused
on
historical
and
precipitation
variability
while
disregarding
other
factors'
influence.
Additionally,
the
prediction
process
of
most
machine
learning
models
is
opaque,
resulting
low
interpretability
model
predictions.
Hence,
this
study
develops
an
ensemble
deep
to
forecast
from
three
hydrological
stations.
Initially,
time‐varying
filtered
based
empirical
mode
decomposition
employed
decompose
series
into
several
internal
functions
(IMFs).
Subsequently,
complexity
each
IMF
component
evaluated
by
multi‐scale
permutation
entropy,
IMFs
are
classified
high‐
low‐frequency
portions
entropy
values.
Considering
high‐frequency
still
exhibit
great
volatility,
robust
local
mean
adopted
perform
secondary
portions.
Then,
meteorological
variables
processed
Relief
algorithm
variance
inflation
factor
features
as
inputs,
individual
subsequences
preliminary
outputs
bidirectional
gated
recurrent
unit
extreme
models.
Random
forests
(RF)
introduced
nonlinear
predicted
sub‐models
obtain
final
results.
The
proposed
outperforms
various
evaluation
metrics.
Meanwhile,
due
opaque
nature
models,
shapley
assess
contribution
selected
variable
long‐term
trend
runoff.
could
serve
essential
reference
for
precise
warning.
Energy Science & Engineering,
Год журнала:
2022,
Номер
11(1), С. 79 - 96
Опубликована: Сен. 18, 2022
Abstract
Global
carbon
dioxide
emissions
have
become
a
great
threat
to
economic
sustainability
and
human
health.
The
market
is
recognized
as
the
most
promising
mean
curb
emissions,
furthermore,
price
forecasting
will
promote
role
of
in
reduction
achieve
targets
at
lower
costs
for
emission
entities.
However,
there
are
still
some
technical
problems
prediction,
such
mode
mixing
larger
reconstruction
error
traditional
empirical
decomposition‐type
models.
Therefore,
innovation
this
paper
constructing
novel
prediction
model
complete
ensemble
decomposition
with
adaptive
noise
(CEEMDAN)‐long
short‐term
memory
(LSTM),
that
combines
advantages
CEEMDAN
decomposing
multiscale
time‐frequency
signals
LSTM
fitting
financial
signals.
results
show
proposed
CEEMDAN‐LSTM
has
significant
accuracy
predicting
complex
expectation
indicators
root
square
error,
absolute
percentage
direction
0.638342,
0.448695,
0.015666,
0.687631,
respectively,
which
better
than
other
benchmark
Further
evidence
convince
performance
superior
long‐term
medium‐term
performance.
That
concludes
reliable
method
reveal
price‐driving
mechanism
from
point
characteristics.
Particularly,
more
accurate
can
provide
valuable
reference
entities
green
companies
judge
situation
formulate
quantitative
transactions.
