Extreme
urban
temperatures
have
emerged
as
crucial
threats
to
ecosystems
and
sustainable
development.
Against
this
background,
we
developed
a
Random
Forest
(RF)
model
by
means
of
eXplainable
Artificial
Intelligence
(XAI)
examine
the
contributions
various
impact
features
in
regulating
land
surface
temperature
(LST)
study
area
Beijing,
China.
Multiple
data
sources
were
investigated,
including
LST,
Normalized
Difference
Vegetation
Index
(NDVI),
cover,
elevation,
tree
height,
building
height.
A
grid
(inner
outer
cities),
composed
3416
boxes,
3x3
km,
was
used
extract
mean
values
features.
RF
outperformed
Linear
Regression
(R2
0.89
vs
0.83)
predicting
demonstrating
complex
non-linear
relationships
between
LST
By
applying
method,
our
results
suggest
that
major
Beijing
elevation
(44.19%),
compactness
impervious
(17.27%),
NDVI
(11.12%),
proportion
(8.04%),
height
(3.83%).
The
relationship
highlights
need
for
systematic
planning
landscapes.
This
provides
state-of-the-art
technology
gain
novel
insights
into
managing
green
spaces,
development
mitigate
hot
environments.
Environmental Science & Technology,
Journal Year:
2024,
Volume and Issue:
58(13), P. 5811 - 5820
Published: March 19, 2024
Enhancing
the
cooling
effectiveness
of
green
spaces
(GSs)
is
crucial
for
improving
urban
thermal
environments
in
context
global
warming.
Increasing
GS
coverage
and
optimizing
its
spatial
distribution
individually
proved
to
be
effective
measures.
However,
their
comparative
potential
interaction
remain
unclear.
Here,
using
moving
window
approach
random
forest
algorithm,
we
established
a
robust
model
(R2
=
0.89
±
0.01)
explore
relationship
between
land
surface
temperature
(LST)
Chinese
megacity
Guangzhou.
Subsequently,
response
LST
varying
was
simulated,
both
combination.
The
results
indicate
that
with
higher
more
equitable
conducive
heat
mitigation.
found
lower
city's
average
by
up
4.73
°C,
while
led
decrease
1.06
°C.
Meanwhile,
synergistic
effect
observed
when
combining
measures,
resulting
additional
benefits
(0.034–0.341
°C).
These
findings
provide
valuable
insights
into
guidance
planning
aimed
at
mitigation
cities.
City and Environment Interactions,
Journal Year:
2023,
Volume and Issue:
21, P. 100136 - 100136
Published: Dec. 19, 2023
Green
spaces
such
as
forests,
grasslands,
and
croplands
(including
gardens)
can
be
found
in
urban
environments.
Although
they
benefit
human
animal
well-being,
have
become
threatened
due
to
rapid
growth
unplanned
development.
Yet,
little
attention
has
been
given
studying
the
dynamics
of
green
sub-Saharan
Africa.
In
this
study,
we
examined
land
use
cover
(LULC)
change
fragmentation
(especially,
spaces)
within
second
fastest
urbanising
city
Ghana,
Tamale.
particular,
focused
our
analyses
on
its
core
(∼5
km
radius
around
centre)
relevance
economy
society.
Landsat
data
was
used
estimate
metrics
past
future
LULC
changes
study
area
from
1990
2052.
We
clear
patterns
space
decline
core:
i.e.,
became
patchy
over
time
pattern
expected
continue
future.
Additionally,
built-up
class
benefited
with
latter
being
significantly
negatively
correlated
population
size.
Our
investigation
reveals
that
protected
forests
tree
plantations
contributed
a
significant
proportion
available
core.
However,
these
areas
were
becoming
increasingly
by
forest
reserve
downsizing,
indiscriminate
activities
(e.g.,
logging
encroachment),
sale
public
lands
private
developers,
practices
commonly
associated
growth.
Hence,
enforcement
relevant
local
legislations
2016
Land
Use
Spatial
Planning
Act
[Act
925])
coupled
integration
initiatives
policies
encourage
are
needed
ensure
sustainability
ecosystems
for
well-being
humans
environment.
Urban Climate,
Journal Year:
2024,
Volume and Issue:
56, P. 102045 - 102045
Published: June 28, 2024
High
land
surface
temperatures
(LST)
have
emerged
as
crucial
threats
to
urban
ecosystems
and
sustainable
development.
To
better
understand
mitigate
their
impacts,
it
is
essential
analyze
the
contributing
features.
Against
this
background,
we
developed
a
random
forest
model
enhanced
by
Explainable
Artificial
Intelligence
(XAI)
impact
features
of
LST
in
Beijing,
China.
By
applying
XAI
method,
our
results
suggest
that
major
Beijing
are
elevation
(44.19%),
compactness
impervious
(17.27%),
Normalized
Difference
Vegetation
Index
(11.12%),
proportion
area
(8.04%),
tree
height
(3.83%).
Compactness
exhibited
an
overall
cooling
effect,
which
became
weaker
at
high
values.
increased
with
building
height,
trend
reached
5
m.
The
most
important
impacting
inner
city
buildings,
whereas
outer
these
surfaces.
study
applies
explain
non-linear
interactions
between
features,
offering
innovative
insights
policy-makers
develop
planning
strategies.
Our
findings
increasing
green
spaces
water
bodies
well
controlling
density
can
effectively
heat
dense
areas
enhance
effects.
