A Blockchain-based Landslide Mitigation Recommendation System for Decision-Making
Engineering Technology & Applied Science Research,
Journal Year:
2025,
Volume and Issue:
15(1), P. 20452 - 20460
Published: Feb. 2, 2025
Landslides
are
catastrophic
natural
disasters
that
could
threaten
the
structural
integrity
of
a
building,
imposing
hazards
to
engineering
and
human
life.
This
study
proposes
TOPSIS
landslide
disaster
mitigation
recommendation
system
integrated
with
blockchain.
New
approaches
data
provenance,
transparency,
informed
decision-making
explored
in
context
geospatial
The
process
is
carried
out
using
multicriteria
evaluation
method,
which
considers
soil
stability,
rainfall,
vegetation
density,
proximity
rivers,
slope.
results
yielded
promising
precision,
recall,
accuracy,
F1
scores
(91%,
93%,
95%,
respectively),
suggesting
model
make
accurate
impartial
prioritization
predictions.
Blockchain
ensures
immutability,
security,
ranks
strategies
from
worst
best
determine
better
solution.
proposed
approach
essential
predict
regions
prone
landslides
enables
appropriate
management
relaxation
measures.
application
blockchain
technology
can
provide
trust,
reliability,
speed
while
reducing
landslides.
Language: Английский
Exploring U-Net Deep Learning Model for Landslide Detection Using Optical Imagery, Geo-indices, and SAR Data in a Data Scarce Tropical Mountain Region
PFG – Journal of Photogrammetry Remote Sensing and Geoinformation Science,
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 11, 2025
Language: Английский
Evaluation of Geological Hazards Susceptibility along the Hefei-Fuzhou High- Speed Railway Based on Machine Learning Algorithms
Research Square (Research Square),
Journal Year:
2025,
Volume and Issue:
unknown
Published: May 6, 2025
Abstract
Geological
hazards
pose
significant
risks
during
the
construction
and
operation
of
railways,
demanding
effective
prevention
control
measures
to
ensure
operational
safety.
The
Hefei-Fuzhou
High-Speed
Railway,
a
critical
transportation
artery,
traverses
complex
geological
terrain
diverse
landforms,
leading
prominent
risk
along
its
route.
This
study
focuses
on
Huangshan-Fuzhou
section
this
railway,
evaluating
landslide
susceptibility
within
railway
corridor
using
Random
Forest
(RF)
algorithm.
Furthermore,
we
analyze
spatial
variations
in
primary
influencing
factors
by
comparing
two
distinct
sub-regions.
main
findings
are
as
follows:
(1)
A
model
developed
historical
inventory
RF
algorithm
demonstrated
strong
predictive
performance,
achieving
an
Area
Under
Curve
(AUC)
value
0.86.
(2)
Application
produced
zonation
map,
which
revealed
that
approximately
30%
area
is
classified
high
(16.92%)
very
(13.22%)
zones.
(3)
Analysis
feature
importance
identified
Slope
(0.28),
Relief
(0.18),
Topographic
Wetness
Index
(TWI,
0.11)
most
influential
governing
across
entire
area.
(4)
Comparative
analysis
factor
between
northern
southern
sub-regions
patterns:
north
were
(0.115),
TWI
(0.051),
(0.050),
whereas
south,
they
(0.149),
Rainfall
(0.043),
Curvature
(0.041).
These
results
highlight
dominant
influence
topography
at
regional
scale,
while
underscoring
enhanced
role
precipitation
key
contributing
region.
research
provides
scientific
basis
for
targeted
Railway
offers
valuable
methodological
approach
infrastructure
planning
management
similar
environments.
Language: Английский
Enhanced Landslide Spatial Prediction Using Hybrid Deep Learning Model and SHAP Analysis: A Case Study of the Tuyen Quang-Ha Giang Expressway, Vietnam
Dam Duc Nguyen,
No information about this author
Manh Duc Nguyen,
No information about this author
Nguyen Tuan Hung
No information about this author
et al.
Journal of the Indian Society of Remote Sensing,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 3, 2024
Language: Английский