Unlocking time-quantile impact of energy vulnerability, financial development, and political globalization on environmental sustainability in Turkey: Evidence from different pollution indicators
Journal of Environmental Management,
Год журнала:
2024,
Номер
365, С. 121499 - 121499
Опубликована: Июль 2, 2024
Язык: Английский
A multi-stage forecasting system for daily ocean tidal energy based on secondary decomposition, optimized gate recurrent unit and error correction
Journal of Cleaner Production,
Год журнала:
2024,
Номер
449, С. 141303 - 141303
Опубликована: Март 12, 2024
Язык: Английский
An Optimized Extreme Learning Machine Composite Framework for Point, Probabilistic, and Quantile Regression Forecasting of Carbon Price
Process Safety and Environmental Protection,
Год журнала:
2025,
Номер
unknown, С. 106772 - 106772
Опубликована: Янв. 1, 2025
Язык: Английский
A hybrid model for carbon price forecasting based on SSA-NSTransformer: Considering the role of multi-stage carbon reduction targets
Journal of Environmental Management,
Год журнала:
2025,
Номер
375, С. 124237 - 124237
Опубликована: Янв. 29, 2025
Язык: Английский
Evaluation of the planting performance for planting substrate using the SQI-CRITIC combination model based on the least squares method
Frontiers in Environmental Science,
Год журнала:
2025,
Номер
13
Опубликована: Фев. 6, 2025
Background
To
improve
the
scientificity
of
evaluation
results
planting
performance
Yellow
River
sediment
based
on
substrate.
Methods
This
study
replaced
natural
soil
with
sediment,
used
cement
as
cementing
material,
added
different
proportions
organic
matter
and
amendment
habitat
material
to
prepare
substrate
carried
out
experiments
by
using
oats
proposed
a
combined
SQI-CRITIC
weighting
calculation
method
least
square
for
its
evaluation.
Results
The
showed
that
(1)
led
significant
variations
in
sediment:
among
5#
mix
ratio,
plant
height
(12.5
cm)
biomass
(3.06
g)
reached
extreme
values.
Photosynthetic
rate
(1.97
μmol∙m−2∙s−1
)
transpiration
(0.25
id="m2">mmol∙m−2∙s−1
were
significantly
higher
than
other
fitness
ratio
components
(
P
<
0.05
),
while
stomatal
width
(87.03
μm)
was
largest
density
(19.6%)
lowest
).
(2)
calculated
combination
model
are
scientific
effective,
more
accurate
line
actual
situation.
(3)
comprehensive
analysis
recommended
use
quality
(mixture
matter,
=
100:3:12:4)
ecological
restoration
achieve
best
growth
effect.
Conclusion
experimental
can
be
extended
areas
need
sandy
restoration,
view
providing
theoretical
basis
evaluation,
water
conservation
control,
construction
Basin.
Язык: Английский
Supply and demand behaviors in the Chinese emission allowances pledge credit market under different value type: An evolutionary game analysis
Journal of Cleaner Production,
Год журнала:
2024,
Номер
455, С. 142374 - 142374
Опубликована: Апрель 27, 2024
Язык: Английский
An optimal weight heterogeneous integrated carbon price prediction model based on temporal information extraction and specific comprehensive feature selection
Energy,
Год журнала:
2024,
Номер
312, С. 133654 - 133654
Опубликована: Ноя. 1, 2024
Язык: Английский
Carbon Price Point–Interval Forecasting Based on Two-Layer Decomposition and Deep Learning Combined Model Using Weight Assignment
Journal of Cleaner Production,
Год журнала:
2024,
Номер
unknown, С. 144124 - 144124
Опубликована: Окт. 1, 2024
Язык: Английский
Carbon emission price forecasting in China using a novel secondary decomposition hybrid model of CEEMD-SE-VMD-LSTM
Systems Science & Control Engineering,
Год журнала:
2023,
Номер
12(1)
Опубликована: Дек. 18, 2023
Effective
forecasting
of
carbon
prices
helps
investors
to
judge
market
conditions
and
promotes
the
environment
economic
sustainability.
The
contribution
this
paper
is
constructing
a
novel
secondary
decomposition
hybrid
price
model,
namely
CEEMD-SE-VMD-LSTM.
It
noteworthy
that
sample
entropy
introduced
identify
highly
complex
signals
rather
than
empirically
determined
in
previous
studies.
Specifically,
complementary
ensemble
empirical
mode
(CEEMD)
model
used
decompose
original
signals.
(SE)
variational
(VMD)
are
conducted
recognize
components,
while
long
short-term
memory
(LSTM)
employed
forecast
by
summing
up
predicted
intrinsic
function
(IMF)
components.
conclusion
shows
proposed
has
smallest
errors
with
values
RMSE,
MAE
MAPE
0.2640,
0.1984
0.0044,
respectively,
models
better
other
primary
performances
LSTM-type
those
GRU-type
models.
Further
evidence
convinces
us
accuracy
superior
long-term
forecasting.
Those
conclusions
innovation
can
provide
valuable
reference
for
make
trading
decisions.
Язык: Английский
A carbon price ensemble prediction model based on secondary decomposition strategies and bidirectional long short‐term memory neural network by an improved particle swarm optimization
Energy Science & Engineering,
Год журнала:
2024,
Номер
12(6), С. 2568 - 2590
Опубликована: Май 13, 2024
Abstract
To
further
enhance
the
precision
of
carbon
trading
price
forecasting,
this
research
proposes
a
combined
forecasting
model,
CEEMDAN–VMD–IPSO–BiLSTM,
considering
unsatisfactory
high‐frequency
sequence
decomposition
and
reliance
on
unidirectional
neural
networks
in
current
price‐prediction
models.
First
all,
original
prices
is
decomposed
into
multiple
independent
subsequences
through
completely
ensemble
empirical
mode
with
adaptive
noise
(CEEMDAN)
technique.
The
sample
entropy
values
each
subsequence
are
calculated
to
reconstruct
them
as
high‐frequency,
low‐frequency,
trend
sequences.
Second,
we
employ
variational
(VMD)
approach
decompose
series.
obtained
subsequences,
along
low‐frequency
sequences,
separately
input
an
improved
particle
swarm
optimization
(IPSO)
optimized
bidirectional
long
short‐term
memory
network
(BiLSTM)
model
for
forecasting.
Finally,
IPSO–BiLSTM
used
integrate
outcomes
from
previous
step,
yielding
ultimate
results
predicting
prices.
case
studies
reveal
that
compared
benchmark
exhibits
superior
predictive
universality.
It
offers
theoretical
support
optimizing
market
operations
fostering
low‐carbon
economic
growth,
holding
practical
importance.
Язык: Английский