Discrete Dynamics in Nature and Society,
Год журнала:
2023,
Номер
2023, С. 1 - 11
Опубликована: Ноя. 16, 2023
Urban
regional
risk
is
a
complex
nonlinear
problem
that
encounters
insufficient
information,
randomness,
and
uncertainty.
To
accurately
assess
the
overall
urban
risk,
assessment
model
for
public
safety
was
proposed
by
using
information
diffusion
theory.
The
entropy
theory
employed
to
optimize
reduce
A
framework
of
based
on
constructed.
Finally,
case
study
Hangzhou
city
in
China
presented
demonstrate
performance
method.
Results
showed
method
could
successfully
estimate
city.
levels
probabilities
different
hazard
indicators
were
basically
consistent
with
reality.
hazards
respect
industrial
mining
accidents
road
traffic
extremely
serious.
More
than
80
deaths
from
would
occur
almost
every
3
years,
more
400
RTA
2.6
years.
Moreover,
centralized
intervals
level
associated
five
found,
where
risks
likely
happen
had
higher
vulnerability.
It
provide
guidance
government’s
management
policy-making.
International Journal of Applied Earth Observation and Geoinformation,
Год журнала:
2024,
Номер
128, С. 103710 - 103710
Опубликована: Фев. 19, 2024
Maximizing
billboard
coverage
with
limited
resources
and
different
objective
goals
plays
a
vital
role
in
social
activities.
The
Maximal
Coverage
Billboard
Location
Problem
(MCBLP)
is
complex,
especially
for
multi-objective
functions.
A
spatial
optimization
model
was
developed
using
mixed-integer
linear
programming
based
on
MCBLP
to
formulate
the
problem
of
determining
locations.
Combining
distinctive
features
location
problems,
we
have
new
approach
called
ReCovNet
that
utilizes
Deep
Reinforcement
Learning
(DRL)
solve
MCBLP.
We
applied
address
real-world
New
York
City.
To
assess
its
performance,
implemented
various
algorithms
such
as
Gurobi
solver,
Genetic
Algorithm
(GA)
deep
learning
baseline
Attention
Model
(AM).
reports
optimal
solutions,
while
GA
AM
serve
benchmark
algorithms.
Our
proposed
achieves
good
balance
between
efficiency
accuracy
effectively
solves
introduced
our
study
has
potential
improve
advertising
effectiveness,
offers
novel
insights
addressing
GIScience & Remote Sensing,
Год журнала:
2024,
Номер
61(1)
Опубликована: Янв. 15, 2024
Differences
in
human
mobility
reflect
temporal
variations
and
spatial
differences
urban
spaces,
including
regional
functions,
physical
environments,
geographical
sentiments.
Accurately
quantifying
these
is
critical
for
understanding
managing
cities.
However,
existing
measurement
methods
overlook
the
distribution
of
population
movement,
which
limits
ability
to
compare
mobility.
Separate
treatment
distribution,
flux,
distance
movement
increases
complexity
uncertainty
geographic
phenomena.
Therefore,
we
propose
a
flow-based
location
measure,
termed
difference
index
(MDI),
that
fuses
multidimensional
characteristics
quantify
The
method
quantifies
by
calculating
minimum
transformation
cost
between
two
sets
origin-destination
flows
based
on
optimal
transport
theory.
Simulation
experiments
confirmed
advantage
MDI
perceiving
particularly
regarding
distribution.
We
examined
mobile
signaling
positioning
data
from
Wuhan
found
proposed
could
effectively
identify
dependencies
heterogeneous
effects
semantics
Sustainable Cities and Society,
Год журнала:
2024,
Номер
109, С. 105527 - 105527
Опубликована: Май 21, 2024
This
paper
presents
an
original
framework
for
assessing
and
enhancing
urban
resilience
from
the
perspective
of
life
circle
that
emphasizes
daily
activity
spaces
residents,
using
Urumqi,
a
major
city
in
northwest
China's
arid
oasis
region,
as
case
study.
Based
on
multi-source
geographic
big
data,
we
introduce
Gini
coefficient
Lorenz
curve
to
analyze
spatial
matching
relationship
between
pressure
resilience,
divided
priority
planning
intervention
by
index.
Our
findings
study
Urumqi
reveal
strong
"center-periphery"
structure
pressures.
findings,
proposed
targeted
interventions
prioritized
index
considers
address
disparities
improve
resilience.
advocates
focus
circle,
aiming
develop
multi-center
cluster-type
resilient
foster
"people-oriented"
city.
Rapidly
acquiring
three-dimensional
(3D)
building
data,
including
geometric
attributes
like
rooftop,
height
and
orientations,
as
well
indicative
function,
quality,
age,
is
essential
for
accurate
urban
analysis,
simulations,
policy
updates.
Current
datasets
suffer
from
incomplete
coverage
of
multi-attributes.
This
paper
presents
the
first
national-scale
Multi-Attribute
Building
dataset
(CMAB)
with
artificial
intelligence,
covering
3,667
spatial
cities,
31
million
buildings,
23.6
billion
m²
rooftops
an
F1-Score
89.93%
in
OCRNet-based
extraction,
totaling
363
m³
stock.
We
trained
bootstrap
aggregated
XGBoost
models
city
administrative
classifications,
incorporating
morphology,
location,
function
features.
Using
multi-source
billions
remote
sensing
images
60
street
view
(SVIs),
we
generated
height,
structure,
style,
quality
each
machine
learning
large
multimodal
models.
Accuracy
was
validated
through
model
benchmarks,
existing
similar
products,
manual
SVI
validation,
mostly
above
80%.
Our
results
are
crucial
global
SDGs
planning.
