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.
Remote Sensing,
Год журнала:
2024,
Номер
16(7), С. 1258 - 1258
Опубликована: Апрель 2, 2024
As
a
crucial
component
of
the
ecological
security
pattern,
source
(ES)
plays
vital
role
in
providing
ecosystem
service
value
(ESV)
and
conserving
biodiversity.
Previous
studies
have
mostly
considered
ES
only
from
either
landscape
change
pattern
or
function
perspectives,
ignored
their
integration
spatio-temporal
evolutionary
modeling.
In
this
study,
we
proposed
multi-perspective
framework
for
characteristics
by
ESV
incorporating
aesthetics,
carbon
sink
characteristics,
quality,
kernel
NDVI
(kNDVI).
By
integrating
revised
normalized
difference
vegetation
index
as
foundation,
employed
spatial
priority
model
to
identify
ES.
This
improvement
aims
yield
more
practical
specific
result.
Applying
Three-River
Headwaters
Region
(TRHR),
significant
sources
has
been
observed
2000
2020.
performance
provided
reference
conservation
TRHR.
The
results
indicate
that
identification
reliable
accuracy
efficiency
compared
with
existing
NRs
method
could
reveal
precise
distributions
ES,
enhancing
integrity
technical
modeling
support
developing
cross-scale
planning
management
strategies
nature
reserve
boundaries.
our
research
serve
building
networks
other
ecologically
fragile
areas.
Remote Sensing,
Год журнала:
2024,
Номер
16(10), С. 1735 - 1735
Опубликована: Май 14, 2024
In
the
context
of
global
climate
change
and
increase
in
drought
frequency,
monitoring
accurately
assessing
impact
hydrological
process
limitations
on
vegetation
growth
is
paramount
importance.
Our
study
undertakes
a
comprehensive
evaluation
efficacy
satellite
remote
sensing
indices—Normalized
Difference
Vegetation
Index
(MODIS
NDVI
product),
kernel
(kNDVI),
Solar-Induced
chlorophyll
Fluorescence
(GOSIF
product)
this
regard.
Initially,
we
applied
LightGBM-Shapley
additive
explanation
framework
to
assess
influencing
factors
three
indices.
We
found
that
Vapor
Pressure
Deficit
(VPD)
primary
factor
affecting
southern
China
(18°–30°N).
Subsequently,
using
Gross
Primary
Productivity
(GPP)
estimates
from
flux
tower
sites
as
performance
benchmark,
evaluated
ability
these
indices
reflect
GPP
changes
during
conditions.
findings
indicate
SIF
serves
most
effective
surrogate
for
GPP,
capturing
variability
periods
with
minimal
time
lag.
Additionally,
our
reveals
kNDVI
significantly
varies
depending
estimation
different
parameters.
The
application
time-heuristic
method
could
potentially
enhance
kNDVI’s
capacity
capture
dynamics
more
effectively
periods.
Overall,
demonstrates
satellite-based
data
are
adept
at
responses
water
stress
tracking
anomalies
caused
by
droughts.
These
not
only
provide
critical
insights
into
selection
optimization
product
but
also
offer
valuable
future
research
aimed
improving
understanding
status
under
climatic
changes.
Remote Sensing,
Год журнала:
2025,
Номер
17(1), С. 169 - 169
Опубликована: Янв. 6, 2025
The
northern
permafrost
regions
are
increasingly
experiencing
frequent
and
intense
extreme
events,
with
a
rise
in
the
occurrence
of
compound
events.
Many
climate-related
hazards
these
areas
driven
by
such
significantly
affecting
stability
functionality
vegetation
ecosystems.
However,
cumulative
lagged
effects
events
on
remain
unclear,
which
may
lead
to
an
underestimation
their
actual
impacts.
This
study
provides
comprehensive
analysis
spatiotemporal
variations
response
from
1982
2022.
primary
focus
this
is
examining
climate
Kernel
Normalized
Difference
Vegetation
Index
(kNDVI)
during
growing
seasons.
results
indicate
that
high-latitude
regions,
frequency
high
temperature–precipitation
temperature–drought
have
increased
58.0%
67.0%
areas,
respectively.
Conversely,
low
has
decreased
70.6%
57.2%
showing
fastest
increase.
temporal
kNDVI
vary
type;
they
produce
more
compared
single
high-temperature
fewer
precipitation
forest
grassland
Notably,
exhibit
strongest
vegetation,
while
influence
wetland
shrubland
within
same
month.
underscores
importance
multivariable
perspective
understanding
dynamics
regions.
Forests,
Год журнала:
2025,
Номер
16(2), С. 307 - 307
Опубликована: Фев. 10, 2025
In
the
context
of
climate
change,
southern
slope
Qilian
Mountains
stands
as
a
pivotal
region
for
China’s
ecological
security,
holding
immense
significance
sustaining
sustainable
development.
This
study
aims
to
precisely
monitor
and
predict
dynamic
changes
in
vegetation
cover
within
this
region,
along
with
their
time-lagged
effects
on
thereby
providing
scientific
basis
management.
By
calculating
kNDVI
from
2001
2020
Google
Earth
Engine
(GEE)
platform,
integrating
Sen’s
trend
analysis,
Hurst
exponent,
partial
correlation
we
have
conducted
an
in-depth
exploration
long-term
spatiotemporal
variations
its
delayed
responses
factors.
The
primary
research
findings
can
be
summarized
follows:
exhibits
overall
positive
trend,
notable
geographical
spatial
distribution.
proportion
areas
showing
improvement
is
high
84%,
while
degraded
account
only
17%.
Furthermore,
there
average
lag
response
1.6
months
precipitation
0.6
temperature
region.
speed
positively
correlates
coefficient
between
Notably,
more
sensitive
area
Mountains.
not
fills
gap
monitoring
but
also
offers
support
governance
green
development
initiatives
Additionally,
it
showcases
innovative
application
advanced
remote
sensing
technologies
statistical
analysis
methods
research,
fresh
perspectives
future
management
strategies.
These
hold
profound
implications
promoting
conservation
area.
Abstract
Satellite-observed
solar-induced
chlorophyll
fluorescence
(SIF)
is
a
powerful
proxy
for
the
photosynthetic
characteristics
of
terrestrial
ecosystems.
Direct
SIF
observations
are
primarily
limited
to
recent
decade,
impeding
their
application
in
detecting
long-term
dynamics
ecosystem
function.
In
this
study,
we
leverage
two
surface
reflectance
bands
available
both
from
Advanced
Very
High-Resolution
Radiometer
(AVHRR,
1982–2023)
and
MODerate-resolution
Imaging
Spectroradiometer
(MODIS,
2001–2023).
Importantly,
calibrate
orbit-correct
AVHRR
against
MODIS
counterparts
during
overlapping
period.
Using
bias-corrected
data
MODIS,
neural
network
trained
produce
Long-term
Continuous
SIF-informed
Photosynthesis
Proxy
(LCSPP)
by
emulating
Orbiting
Carbon
Observatory-2
SIF,
mapping
it
globally
over
1982–2023
Compared
with
previous
photosynthesis
proxies,
LCSPP
has
similar
skill
but
can
be
advantageously
extended
Further
comparison
three
widely
used
vegetation
indices
(NDVI,
kNDVI,
NIRv)
shows
higher
or
comparable
correlation
satellite
site-level
GPP
estimates
across
types,
ensuring
greater
capacity
representing
activity.
Sustainability,
Год журнала:
2025,
Номер
17(6), С. 2348 - 2348
Опубликована: Март 7, 2025
Examining
the
effects
of
climate
change
(CC)
and
anthropogenic
activities
(AAs)
on
vegetation
dynamics
is
essential
for
ecosystem
management.
However,
time
lag
accumulation
plant
growth
are
often
overlooked,
resulting
in
an
underestimation
CC
impacts.
Combined
with
kernel
normalized
difference
index
(kNDVI),
data
during
growing
season
from
2000
to
2023
Three
Rivers
Source
Region
(TRSR)
trend
correlation
analyses
were
employed
assess
kNDVI
dynamics.
Furthermore,
effect
upgraded
residual
analysis
applied
explore
how
climatic
human
drivers
jointly
influence
vegetation.
The
results
show
following:
(1)
showed
a
fluctuating
but
overall
increasing
trend,
indicating
improvement
growth.
Although
future
likely
continue
improving,
certain
areas—such
as
east
western
Yangtze
River
basin,
south
Yellow
parts
Lancang
basin—will
remain
at
risk
deterioration.
(2)
Overall,
both
precipitation
temperature
positively
correlated
kNDVI,
acting
dominant
factor
affecting
predominant
temporal
0-month
1-month
accumulation,
while
primarily
2–3-month
0–1-month
accumulation.
main
category
(PA_TL),
which
accounted
70.93%
TRSR.
(3)
Together,
AA
drove
dynamics,
contributions
35.73%
64.27%,
respectively,
that
played
role.
incorporating
combined
enhanced
explanatory
ability
factors