International Journal of Digital Earth,
Год журнала:
2024,
Номер
17(1)
Опубликована: Ноя. 27, 2024
Urban
land
use
information
can
be
effectively
extracted
from
high-resolution
satellite
images
for
many
urban
applications.
A
significant
challenge
remains
the
accurate
partition
of
fine-grained
land-use
units
these
images.
This
paper
presents
a
novel
method
deriving
based
on
unsupervised
graph
learning
techniques
using
and
open
street
boundaries.
Our
constructs
to
represent
spatial
relations
between
cover
objects
as
nodes
within
block.
These
are
characterized
by
composition
structure
features
their
surrounding
neighborhood.
We
then
apply
into
subgraphs,
which
communities
spatially
bounded
boundaries
correspond
units.
Next,
neural
network
is
used
extract
deep
structural
classification.
Experiments
were
conducted
cities
Fuzhou
Quanzhou,
China.
Results
showed
that
our
surpassed
traditional
grid
block
techniques,
improving
classification
accuracy
24%
9%,
respectively.
Furthermore,
it
achieved
results
comparable
those
reference
units,
with
an
overall
0.87
versus
0.89.
Frontiers in Environmental Science,
Год журнала:
2023,
Номер
10
Опубликована: Янв. 10, 2023
As
a
primary
concern
in
the
ecosystem,
understanding
impact
of
spatial
heterogeneity
ecological
networks
on
development
environmental
sustainability
has
overarching
significance.
The
Tibetan
Plateau’s
edge
is
vital
contribution
to
study
plateau’s
network.
However,
there
are
few
studies
and
explorations
county-level
network
arid
region.
This
aimed
evaluate
patterns
Tianzhu
County
establish
an
security
evaluation
index
system.
We
used
minimum
cumulative
resistance
(MCR)
model
built
surface
from
exploratory
data
analysis
(ESDA)
method.
Then,
by
identifying
corridors
nodes
gravity
model,
we
analyzed
pattern
proposed
specific
plans
for
optimizing
situation.
results
showed
that
1)
county
overall
been
lower,
its
values
each
direction,
2)
Z-Score
was
70.1893,
which
shows
vulnerability
region
significant
autocorrelation.
identified
156
112
nodes,
formed
“one
belt
three
zones.”
Our
analytical
framework
offers
valuable
tool
constructing
selecting
“sources”
at
regional
scale,
can
be
applied
landscapes
geographical
contexts
sustainable
regions.
Land,
Год журнала:
2024,
Номер
13(10), С. 1695 - 1695
Опубликована: Окт. 17, 2024
With
the
acceleration
of
urbanization,
high
density
and
intensity
urban
construction
expansion
have
led
to
an
exacerbation
heat
island
(UHI)
effect,
which,
in
turn,
contributes
global
climate
warming
severely
impacts
ecological
environments
human
health.
This
study
takes
Wanjiang
agglomeration
as
a
case
study.
Using
land
surface
temperature
data
from
2010,
2016,
2022,
employs
Morphological
Spatial
Pattern
Analysis
(MSPA)
model
quantitatively
identify
types
spatiotemporal
distribution
characteristics
patches
agglomeration.
Based
on
this
analysis,
constructed
thermal
environment
sources
corridors,
applied
circuit
theory
(CIRCUIT)
spatial
network
The
results
show
that
(1)
2010
seven
belt
were
identified
by
consensus,
mainly
distributed
northwest
southeast,
their
areas
increased
significantly.
dominant
type
changed
core
2022.
(2)
From
number
area
increased.
According
source
theory,
corridors
pinch
points
indicating
ecosystem
connectivity
had
improved
during
period.
barrier
2022
are
identified.
(3)
During
2010–2022,
α,
β,
γ
with
time,
overall
was
enhanced,
transmission
efficiency
between
gradually
improved,
threat
degree
rural
residents
rise.
provides
identification
assessment
agglomeration,
offering
valuable
insights
for
understanding
pattern
mitigating
effect
region.
