Deformation Slope Extraction and Influencing Factor Analysis Using LT-1 Satellite Data: A Case Study of Chongqing and Surrounding Areas, China
Remote Sensing,
Год журнала:
2025,
Номер
17(1), С. 156 - 156
Опубликована: Янв. 5, 2025
The
use
of
satellite
imagery
for
surface
deformation
monitoring
has
been
steadily
increasing.
However,
the
study
extracting
slopes
from
data
requires
further
advancement.
This
limitation
not
only
poses
challenges
subsequent
studies
but
also
restricts
potential
deeper
exploration
and
utilization
data.
LT-1
satellite,
China’s
largest
L-band
synthetic
aperture
radar
offers
a
new
perspective
monitoring.
In
this
study,
we
extracted
in
Chongqing
its
surrounding
areas
China
based
on
generated
by
LT-1.
Twelve
factors
were
selected
to
analyze
their
influence
slope
deformation,
including
elevation,
topographic
position,
slope,
landcover,
soil,
lithology,
relief,
average
rainfall
intensity,
distances
rivers,
roads,
railways,
active
faults.
A
total
5863
identified,
covering
an
area
140
km2,
mainly
concentrated
central
part
area,
with
highest
density
reaching
0.22%.
Among
these
factors,
intensity
was
found
have
greatest
impact
slope.
These
findings
provide
valuable
information
geological
disaster
early
warning
management
areas,
while
demonstrating
practical
value
Язык: Английский
A hierarchical graph-based hybrid neural networks with a self-screening strategy for landslide susceptibility prediction in the spatial–frequency domain
Bulletin of Engineering Geology and the Environment,
Год журнала:
2025,
Номер
84(3)
Опубликована: Фев. 12, 2025
Язык: Английский
Deciphering the Social Vulnerability of Landslides Using the Coefficient of Variation-Kullback-Leibler-TOPSIS at an Administrative Village Scale
Remote Sensing,
Год журнала:
2025,
Номер
17(4), С. 714 - 714
Опубликована: Фев. 19, 2025
Yu’nan
County
is
located
in
the
Pacific
Rim
geological
disaster-prone
area.
Frequent
landslides
are
an
important
cause
of
population,
property,
and
infrastructure
losses,
which
directly
threaten
sustainable
development
regional
social
economy.
Based
on
field
survey
data,
this
paper
employs
coefficient
variation
method
(CV)
improved
TOPSIS
model
(Kullback-Leibler-Technique
for
Order
Preference
by
Similarity
to
Ideal
Solution)
assess
vulnerability
landslide
disasters
182
administrative
villages
County.
Also,
it
conducts
a
ranking
comprehensive
analysis
their
levels.
Finally,
accuracy
evaluation
results
validated
applying
losses
incurred
from
per
unit
area
within
same
year.
The
indicate
significant
spatial
variability
across
County,
with
68
out
exhibiting
moderate
levels
or
higher.
This
suggests
high
risk
widespread
damage
potential
disasters.
Among
these,
Xincheng
village
has
highest
score,
while
Chongtai
lowest,
0.979
difference
vulnerabilities.
By
comparing
actual
landslides,
found
that
predicted
CV-KL-TOPSIS
more
consistent
results.
Furthermore,
among
ten
sub-factors,
population
density,
building
value,
road
value
contribute
most
significantly
overall
weight
0.269,
0.152,
0.105,
respectively,
suggesting
mountainous
areas
where
relatively
concentrated,
hazards
reflection
characteristics
local
economic
level.
framework
indicators
proposed
can
systematically
accurately
evaluate
landslide-prone
areas,
provide
reference
urban
planning
management
areas.
Язык: Английский
Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks
International Journal of Digital Earth,
Год журнала:
2025,
Номер
18(1)
Опубликована: Фев. 19, 2025
Язык: Английский
Evolution of landslide susceptibility in the Three Gorges Reservoir area over the three decades from 1991 to 2020
Geomatics Natural Hazards and Risk,
Год журнала:
2025,
Номер
16(1)
Опубликована: Фев. 25, 2025
Язык: Английский
Assessment of Landslide Susceptibility Based on the Two-Layer Stacking Model—A Case Study of Jiacha County, China
Remote Sensing,
Год журнала:
2025,
Номер
17(7), С. 1177 - 1177
Опубликована: Март 26, 2025
The
challenge
of
obtaining
landslide
susceptibility
zoning
in
Tibet
is
compounded
by
the
high
altitude,
extensive
range,
and
difficult
exploration
region.
To
address
this
issue,
a
novel
evaluation
approach
based
on
Stacking
ensemble
machine
learning
proposed.
This
study
focuses
Jiacha
County,
adopts
slope
unit
as
unit,
picks
up
14
factors
that
symbolize
topography
geomorphology,
environmental
hydrological
features,
basic
geological
features.
These
conditioning
were
integrated
into
total
4660
models,
randomly
combined
10
base-algorithms,
including
AdaBoost,
Decision
Tree
(DT),
Gradient
Boosting
(GBDT),
k-Nearest
Neighbors
(kNNs),
LightGBM,
Multilayer
Perceptron
(MLP),
Random
Forest
(RF),
Ridge
Regression,
Support
Vector
Machine
(SVM),
XGBoost.
All
models
trained,
using
natural
discontinuity
method
to
classify
susceptibility,
AUC
value,
area
under
ROC
curve,
was
taken
evaluate
model.
results
show
maximum
values
9
performing
better
reach
0.78
0.99
over
test
set
train
set.
Most
areas
identified
above
consistency
with
interpretation
existing
field
data.
Thus,
applicable
situation
Tibet,
can
provide
theoretical
support
for
disaster
prevention
mitigation
work
Qinghai–Tibet
Plateau
area.
Язык: Английский
Effects of different division methods of landslide susceptibility levels on regional landslide susceptibility mapping
Bulletin of Engineering Geology and the Environment,
Год журнала:
2025,
Номер
84(6)
Опубликована: Май 6, 2025
Язык: Английский
DS Net: A Dual-Coded Segmentation Network Leveraging Large Model Prior Knowledge for Intelligent Landslide Extraction
Remote Sensing,
Год журнала:
2025,
Номер
17(11), С. 1912 - 1912
Опубликована: Май 31, 2025
Landslides
are
characterized
by
their
suddenness
and
destructive
power,
making
rapid
accurate
identification
crucial
for
emergency
rescue
disaster
assessment
in
affected
areas.
To
address
the
challenges
of
limited
landslide
samples
data
complexity,
a
sample
library
was
constructed
using
high-resolution
remote
sensing
imagery
combined
with
field
validation.
An
innovative
Dual-Coded
Segmentation
Network
(DS
Net),
which
realizes
dynamic
alignment
deep
fusion
local
details
global
context,
image
features
domain
knowledge
through
multi-attention
mechanism
Prior
Knowledge
Integration
(PKI)
module
Cross-Feature
Aggregation
(CFA)
module,
significantly
improves
detection
accuracy
reliability.
objectively
evaluate
performance
DS
Net
model,
four
efficient
semantic
segmentation
models—SegFormer,
SegNeXt,
FeedFormer,
U-MixFormer—were
selected
comparison.
The
results
demonstrate
that
achieves
superior
(overall
=
0.926,
precision
0.884,
recall
0.879,
F1-score
0.882),
metrics
3.5–7.1%
higher
than
other
models.
These
findings
confirm
effectively
efficiency
identification,
providing
critical
scientific
basis
prevention
mitigation.
Язык: Английский
Design and construction of tunnels and tunnelling: Understanding the importance of geological conditions, landslide susceptibility and risk assessment
Geological Journal,
Год журнала:
2024,
Номер
59(9), С. 2365 - 2370
Опубликована: Авг. 14, 2024
Tunnel
engineering
is
a
complex
and
multidisciplinary
field
that
requires
the
integration
of
geological
expertise,
advanced
modeling
techniques,
practical
solutions.
The
research
compiled
in
Special
Issue
"Tunnels
Tunneling"
makes
significant
contributions
to
by
addressing
diverse
conditions
intricate
challenges
inherent
tunnel
construction.
These
insights
are
crucial
for
enhancing
safety,
efficiency,
sustainability
projects
worldwide.
studies
this
provide
comprehensive
understanding
various
innovative
solutions
engineering.
They
offer
valuable
guidelines
designing,
constructing,
maintaining
safe
stable
structures
across
different
settings.
In
addition,
specific
regions,
such
as
Three
Gorges
Reservoir
area,
Hengduan
Mountains,
Tibetan
Plateau,
require
tailored
approaches.
A
key
theme
many
comparative
importance
accurate
risk
assessment
ensure
safety.
regions
prone
hazards,
landslide
susceptibility
mapping
critical.
Innovative
approaches,
machine
learning
models,
highlighted
their
potential
predict
manage
risks
effectively.
Язык: Английский