Remote Sensing,
Год журнала:
2025,
Номер
17(2), С. 273 - 273
Опубликована: Янв. 14, 2025
The
intensification
of
climate
change
and
the
implementation
territorial
spatial
planning
policies
have
jointly
increased
complexity
future
carbon
storage
changes.
However,
impact
on
under
remains
unclear.
Therefore,
this
study
aims
to
reveal
potential
impacts
sequestration,
providing
decision
support
for
addressing
optimizing
planning.
We
employed
FLUS
model,
InVEST
variance
partitioning
analysis
(VPA)
method
simulate
15
different
scenarios
that
combine
Xiamen
in
2035,
quantify
individual
combined
ecosystem
sequestration.
results
showed
(1)
by
Xiamen’s
capacity
is
expected
range
from
32.66
×
106
Mg
33.00
various
scenarios,
reflecting
a
decrease
2020
levels;
(2)
conducive
preserving
storage,
with
urban
development
boundary
proving
be
most
effective;
(3)
greatly
affected
change,
RCP
4.5
more
effective
than
8.5
maintaining
higher
levels
storage;
(4)
influence
sequestration
consistently
exceeds
particularly
high-emission
where
regulatory
effect
especially
significant.
Remote Sensing,
Год журнала:
2022,
Номер
14(21), С. 5546 - 5546
Опубликована: Ноя. 3, 2022
Forest
fires
may
have
devastating
consequences
for
the
environment
and
human
lives.
The
prediction
of
forest
is
vital
preventing
their
occurrence.
Currently,
there
are
fewer
studies
on
over
longer
time
scales
in
China.
This
due
to
difficulty
forecasting
fires.
There
many
factors
that
an
impact
occurrence
specific
contribution
each
factor
not
clear
when
using
conventional
analyses.
In
this
study,
we
leveraged
excellent
performance
artificial
intelligence
algorithms
fusing
data
from
multiple
sources
(e.g.,
fire
hotspots,
meteorological
conditions,
terrain,
vegetation,
socioeconomic
collected
2003
2016).
We
tested
several
and,
finally,
four
were
selected
formal
processing.
neural
network,
a
radial
basis
function
support-vector
machine,
random
identify
thirteen
major
drivers
models
evaluated
five
indicators
accuracy,
precision,
recall,
f1
value,
area
under
curve.
obtained
probability
province
China
optimal
model.
Moreover,
spatial
distribution
high-to-low
fire-prone
areas
was
mapped.
results
showed
accuracies
between
75.8%
89.2%,
curve
(AUC)
values
0.840
0.960.
model
had
highest
accuracy
(89.2%)
AUC
value
(0.96).
It
determined
as
best
study.
indicate
with
high
incidences
mainly
concentrated
north-eastern
(Heilongjiang
Province
northern
Inner
Mongolia
Autonomous
Region)
south-eastern
(including
Fujian
Jiangxi
Province).
at
risk
fire,
management
departments
should
improve
prevention
control
by
establishing
watch
towers
other
monitoring
equipment.
study
helped
understanding
main
period
2016,
maps
produced
order
depict
comprehensive
views
China’s
risks
province.
They
expected
form
scientific
helping
decision-making
authorities.
Remote Sensing,
Год журнала:
2022,
Номер
14(14), С. 3259 - 3259
Опубликована: Июль 6, 2022
After
the
“5·12”
Wenchuan
earthquake
in
2008,
collapses
and
landslides
have
occurred
continuously,
resulting
accumulation
of
a
large
quantity
loose
sediment
on
slopes
or
gullies,
providing
rich
material
source
reserves
for
occurrence
debris
flow
flash
flood
disasters.
Therefore,
it
is
great
significance
to
build
collapse
landslide
susceptibility
evaluation
model
County
local
disaster
prevention
mitigation.
Taking
as
research
object
according
data
1081
historical
points,
well
natural
environment,
this
paper
first
selects
six
categories
environmental
factors
(13
total)
including
topography
(slope,
aspect,
curvature,
terrain
relief,
TWI),
geological
structure
(lithology,
soil
type,
distance
fault),
meteorology
hydrology
(rainfall,
river),
seismic
impact
(PGA),
ecological
(NDVI),
human
activity
(land
use).
It
then
builds
three
single
models
(LR,
SVM,
RF)
CF-based
hybrid
(CF-LR,
CF-SVM,
CF-RF),
makes
comparative
analysis
accuracy
reliability
models,
thereby
obtaining
optimal
area.
Finally,
study
discusses
contribution
prediction
model.
The
results
show
that
(1)
areas
prone
extremely
high
predicted
by
CF-LR,
RF
CF-RF)
an
area
730.595
km2,
377.521
361.772
372.979
318.631
306.51
respectively,
frequency
ratio
precision
0.916,
0.938,
0.955,
0.956,
0.972,
0.984,
respectively;
(2)
ranking
comprehensive
index
based
confusion
matrix
CF-RF>RF>CF-SVM>CF-LR>SVM>LR
AUC
value
CF-RF>RF>CF-SVM>CF-LR>SVM>LR.
To
certain
extent,
coupling
can
improve
more
over
models.
CF-RF
ranks
highest
all
indexes,
with
POA
257.046
0.946;
(3)
rainfall,
river
are
most
important
factors,
accounting
24.216%,
22.309%,
11.41%,
respectively.
necessary
strengthen
monitoring
mountains
rock
masses
close
rivers
case
rainstorms
county
other
similar
post-earthquake
landslides.
