Remote Sensing Applications Society and Environment,
Journal Year:
2024,
Volume and Issue:
36, P. 101335 - 101335
Published: Aug. 28, 2024
Forests
are
crucial
in
delivering
ecosystem
services
that
underpin
human
well-being
and
biodiversity
conservation.
However,
these
vital
ecosystems
threatened
by
forest
degradation
rapid
urbanisation.
This
study
addresses
this
challenge
proposing
a
comprehensive
framework
for
mapping
natural
forests
at
the
municipal
scale.
The
integrates
remote
sensing
techniques
with
machine
learning
algorithms
to
provide
valuable
insights
into
extent
of
within
eThekwini
Municipality.
utilised
Landsat
7,
8,
9
satellite
imagery
analyse
map
historical
current
distribution
forests.
Five
spectral
indices,
namely,
Normalized
Differential
Vegetation
Index
(NDVI),
Green
Difference
(GNDVI),
Chlorophyll
(CIG),
Enhanced
(EVI),
Index-2
(EVI-2),
which
were
calculated
from
bands,
employed
analysis.
Light
Gradient
Boosting
Machine
(LightGBM),
Categorical
(CatBoost),
Extreme
(XGBoost)
used
model
distribution.
Accuracy
was
assessed
through
confusion
matrices,
Receiver
Operating
Characteristic
(ROC)
Curves,
area
under
ROC
curve
(AUC),
F1
scores.
LightGBM
achieved
highest
overall
accuracy
(90.76%),
followed
CatBoost
(89.56%)
XGBoost
(84.34%).
also
obtained
best
score
(90.76%).
These
findings
highlight
LightGBM's
effectiveness
classifying
forests,
making
it
preferred
classifications
based
on
7
significantly
underestimated
area,
whereas
8
data
revealed
an
increase
2015
2023.
will
guide
effective
targeted
rehabilitation
restoration
efforts,
ensuring
preservation
enhancement
services.
Sensors,
Journal Year:
2025,
Volume and Issue:
25(4), P. 1169 - 1169
Published: Feb. 14, 2025
This
study
introduces
an
innovative
machine
learning
method
to
model
the
spatial
variation
of
land
surface
temperature
(LST)
with
a
focus
on
urban
center
Da
Nang,
Vietnam.
Light
Gradient
Boosting
Machine
(LightGBM),
support
vector
machine,
random
forest,
and
Deep
Neural
Network
are
employed
establish
functional
relationships
between
LST
its
influencing
factors.
The
approaches
trained
validated
using
remote
sensing
data
from
2014,
2019,
2024.
Various
explanatory
variables
representing
topographical
characteristics,
as
well
landscapes,
used.
Experimental
results
show
that
LightGBM
outperforms
other
benchmark
methods.
In
addition,
Shapley
Additive
Explanations
utilized
clarify
impact
factors
affecting
LST.
analysis
outcomes
indicate
while
importance
these
changes
over
time,
density
greenspace
consistently
emerge
most
influential
attained
R2
values
0.85,
0.92,
0.91
for
years
2024,
respectively.
findings
this
work
can
be
helpful
deeper
understanding
heat
stress
dynamics
facilitate
planning.
Forests,
Journal Year:
2024,
Volume and Issue:
15(9), P. 1615 - 1615
Published: Sept. 13, 2024
Forests
play
a
vital
role
in
atmospheric
CO2
sequestration
among
terrestrial
ecosystems,
mitigating
the
greenhouse
effect
induced
by
human
activity
changing
climate.
The
LUE
(light
use
efficiency)
model
is
popular
algorithm
for
calculating
GPP
(gross
primary
production)
based
on
physiological
mechanisms
and
easy
to
implement.
Different
versions
have
been
applied
many
years
simulate
of
different
ecosystem
types
at
regional
or
global
scales.
For
estimating
forest
using
approaches,
we
implemented
five
models
(EC-LUE,
VPM,
GOL-PEM,
CASA,
C-Fix)
forests
type
DBF,
EBF,
ENF,
MF,
FLUXNET2015
dataset,
remote
sensing
observations,
Köppen–Geiger
climate
zones.
We
then
fused
these
additionally
improve
ability
estimation
an
RF
(random
forest)
SVM
(support
vector
machine).
Our
results
indicated
that
under
unified
parameterization
scheme,
EC-LUE
VPM
yielded
best
performance
simulating
variations,
followed
GLO-PEM,
C-fix,
while
MODIS
also
demonstrated
reliable
ability.
fusion
across
flux
net
sites
could
capture
more
variation
magnitudes
with
higher
R2
lower
RMSE
than
SVM.
Both
were
validated
cross-validation
all
sites,
showing
accuracy
simulation
be
improved
28%
27%.
