Environmental Research Letters,
Год журнала:
2024,
Номер
19(9), С. 094002 - 094002
Опубликована: Июль 24, 2024
Abstract
Storm
surges
caused
by
tropical
cyclones
(TCs)
have
long
ranked
first
among
all
types
of
marine
disasters
in
casualties
and
economic
losses,
can
lead
to
further
regional
exacerbation
consequences
stemming
from
these
losses
along
different
coastlines.
Understanding
the
spatial
footprints
storm
is
thus
highly
important
for
developing
effective
risk
management
protection
plans.
To
this
end,
we
designed
an
ideal
surge
model
based
on
Finite
Volume
Community
Ocean
Model
explore
relationship
between
TC
intensity
footprint
surges,
its
intrinsic
mechanism.
The
both
positive
negative
were
positively
correlated
with
intensity;
however,
latter
was
more
sensitive
when
weaker
than
CAT3
TC’s.
average
CAT1
574
km,
CAT5
increasing
6%
25%,
respectively,
compared
CAT1.
1407
18%
29%,
decomposition
mechanism
analysis
show
that
main
contributing
component
total
at
south
end
storm’s
landfall
during
time
forerunner
Ekman
surge,
whereas
contribution
normal
north
resurgence
dominant.
In
addition,
not
components
increased
intensity,
as
did,
similar
surge.
These
quantitative
analyses
mechanisms
provide
a
theoretical
basis
predicting
evaluating
risks.
Geomatics Natural Hazards and Risk,
Год журнала:
2024,
Номер
15(1)
Опубликована: Фев. 8, 2024
In
recent
years,
urban
flooding
disasters
have
occurred
frequently.
Conducting
research
on
flood
susceptibility
assessment
is
critical
for
prevention
and
renewal
planning.
However,
determining
how
to
effectively
improve
the
accuracy
of
remains
a
challenging
topic.
Combining
machine
learning
algorithms
SHapely
Additive
exPlanations
(SHAP)
method,
this
study
proposes
an
effective
technical
framework
assessment.
Firstly,
in
terms
data
selection,
three
types
sources
were
considered
comprehensively.
Then,
based
above
sources,
five
different
experimental
scenarios
constructed
feature
preferences
performed
using
SHAP.
Finally,
performance
differences
commonly
used
advanced
are
compared.
The
results
show
that
it
feasible
use
importance
information
provided
by
SHAP
optimization.
Compared
with
scenario
without
optimization,
optimization
greatly
improves
model.
XGboost
works
best
when
paired
optimal
combination,
its
AUC
value
reaches
maximum.
indicate
studies,
selection
algorithm
combination
features
important
reliability
Water,
Год журнала:
2025,
Номер
17(10), С. 1477 - 1477
Опубликована: Май 14, 2025
Urban
flood
risk
assessments
play
a
crucial
role
in
urban
resilience
and
disaster
management.
This
paper
proposes
comprehensive
method
for
assessment
prediction
that
is
based
on
environmental
attributes
the
operational
characteristics
of
pipe
networks.
Using
central
area
Zhengzhou
as
case
study,
an
integrated
evaluation
index
system
was
developed,
entropy
weight
applied
to
quantify
indicators.
A
loosely
coupled
RF-XGBoost
model
constructed
predict
different
rainfall
scenarios.
The
results
indicate
(1)
overall
study
exhibits
increasing
trend
from
northeast
southwest,
with
medium-
high-risk
zones
being
predominant;
(2)
spatial
distribution
pattern
closely
aligns
but
shows
slight
variations
under
influence
network
risks;
(3)
demonstrates
superior
predictive
accuracy
multi-factor
coupling
When
characteristics,
attributes,
risks
are
comprehensively
considered,
Nash–Sutcliffe
Efficiency
(NSE)
predictions
improves
0.85
(when
using
only
characteristics)
0.94.
provides
valuable
insights
technical
support
mitigating
risks.
