Remote Sensing,
Год журнала:
2024,
Номер
16(10), С. 1678 - 1678
Опубликована: Май 9, 2024
With
climate
change
and
urbanization
expansion,
wetlands,
which
are
some
of
the
largest
carbon
stocks
in
world,
facing
threats
such
as
shrinking
areas
declining
sequestration
capacities.
Wetland
at
risk
being
transformed
into
sources,
especially
those
wetlands
with
strong
land
use–natural
resource
conservation
conflict.
Moreover,
there
is
a
lack
well-established
indicators
for
evaluating
health
wetland
stocks.
To
address
this
issue,
we
proposed
novel
framework
safety
assessment
using
Super
Slack-Based
Measure
(Super-SBM),
then
conducted
an
empirical
study
on
Quanzhou
Bay
Estuary
(QBEW).
This
integrates
unexpected
output
indicator
(i.e.,
emissions),
expected
indicators,
including
GDP
per
capita
stock
estimates
calculated
via
machine
learning
(ML)-based
remote
sensing
inversion,
input
environmental
governance
investigations,
conditions,
socio-economic
activities,
utilization.
The
results
show
that
annual
average
pools
QBEW
was
meager
0.29
2015,
signaling
very
poor
state,
likely
due
to
inadequate
inputs
or
excessive
outputs.
However,
has
been
substantial
improvement
since
then,
evidenced
by
fact
all
assessments
have
exceeded
threshold
1
from
2018
onwards,
reflecting
transition
“weakly
effective”
status
within
safe
acceptable
range.
our
investigation
employing
Super-SBM
model
calculate
“slack
variables”
yielded
valuable
insights
optimization
strategies.
research
advances
field
establishing
measurement
leverages
efficiency
methods,
thereby
offering
quantitative
safeguard
mechanism
supports
achievement
“3060”
dual-carbon
target.
Forests,
Год журнала:
2025,
Номер
16(3), С. 449 - 449
Опубликована: Март 2, 2025
Forests
play
a
key
role
in
carbon
sequestration
and
oxygen
production.
They
significantly
contribute
to
peaking
neutrality
goals.
Accurate
estimation
of
forest
stocks
is
essential
for
precise
understanding
the
capacity
ecosystems.
Remote
sensing
technology,
with
its
wide
observational
coverage,
strong
timeliness,
low
cost,
stock
research.
However,
challenges
data
acquisition
processing
include
variability,
signal
saturation
dense
forests,
environmental
limitations.
These
factors
hinder
accurate
estimation.
This
review
summarizes
current
state
research
on
from
two
aspects,
namely
remote
methods,
highlighting
both
advantages
limitations
various
sources
models.
It
also
explores
technological
innovations
cutting-edge
field,
focusing
deep
learning
techniques,
optical
vegetation
thickness
impact
forest–climate
interactions
Finally,
discusses
including
issues
related
quality,
model
adaptability,
stand
complexity,
uncertainties
process.
Based
these
challenges,
paper
looks
ahead
future
trends,
proposing
potential
breakthroughs
pathways.
The
aim
this
study
provide
theoretical
support
methodological
guidance
researchers
fields.
Ecological Informatics,
Год журнала:
2024,
Номер
82, С. 102768 - 102768
Опубликована: Авг. 10, 2024
Fractional
Vegetation
Cover
(FVC)
serves
as
a
crucial
indicator
in
ecological
sustainability
and
climate
change
monitoring.
While
machine
learning
is
the
primary
method
for
FVC
inversion,
there
are
still
certain
shortcomings
feature
selection,
hyperparameter
tuning,
underlying
surface
heterogeneity,
explainability.
Addressing
these
challenges,
this
study
leveraged
extensive
field
data
from
Qinghai-Tibet
Plateau.
Initially,
selection
algorithm
combining
genetic
algorithms
XGBoost
was
proposed.
This
integrated
with
Optuna
tuning
method,
forming
GA-OP
combination
to
optimize
learning.
Furthermore,
comparative
analyses
of
various
models
inversion
alpine
grassland
were
conducted,
followed
by
an
investigation
into
impact
heterogeneity
on
performance
using
NDVI
Coefficient
Variation
(NDVI-CV).
Lastly,
SHAP
(Shapley
Additive
exPlanations)
employed
both
global
local
interpretations
optimal
model.
The
results
indicated
that:
(1)
exhibited
favorable
terms
computational
cost
accuracy,
demonstrating
significant
potential
tuning.
(2)
Stacking
model
achieved
among
seven
(R2
=
0.867,
RMSE
0.12,
RPD
2.552,
BIAS
−0.0005,
VAR
0.014),
ranking
follows:
>
CatBoost
LightGBM
RFR
KNN
SVR.
(3)
NDVI-CV
enhanced
result
reliability
excluding
highly
heterogeneous
regions
that
tended
be
either
overestimated
or
underestimated.
(4)
revealed
decision-making
processes
perspectives.
allowed
deeper
exploration
causality
between
features
targets.
developed
high-precision
scheme,
successfully
achieving
accurate
proposed
approach
provides
valuable
references
other
parameter
inversions.
Ecological Informatics,
Год журнала:
2024,
Номер
82, С. 102750 - 102750
Опубликована: Авг. 3, 2024
Sustainable
development
in
cities
requires
advanced
technologies
for
monitoring
and
estimating
air
pollution
emissions,
which
directly
affect
the
health
of
local
inhabitants
residents
neighborhoods.
For
this,
low-cost
sensors
information
are
increasingly
used
to
provide
accurate
quality
forecasts.
They
are,
however,
subject
data
constraints.
This
paper
presents
new
techniques
accurate,
reliable
forecasting
at
various
scales
using
from
IoT-enabled
along
with
state-run
air-quality
stations.
Here,
we
develop
an
extended
deep-learning
model
based
on
neural
networks
algorithms
optimization
hyperparameters
network
dropout
rates.
These
can
yield
a
significant
improvement
over
31%
prediction
accuracy
while
maintaining
coverage
approximately
80%
air-particle
levels
24-h
period.
The
advantages
effectiveness
our
validated
verified
two
real-world
scenarios,
suburban
construction
site
civil
infrastructure
project.
Comparison
analysis
is
conducted
indicate
outperformance
proposed
method
recent
probabilistic
time
series
estimation
regular
days
extreme
events.
