Comparison of Tree Typologies Mapping Using Random Forest Classifier Algorithm of PRISMA and Sentinel-2 Products in Different Areas of Central Italy
Remote Sensing,
Journal Year:
2025,
Volume and Issue:
17(3), P. 356 - 356
Published: Jan. 22, 2025
The
continuous
development
of
satellite
imagery,
coupled
with
advancements
in
machine
learning
technologies,
allows
detailed
mapping
terrestrial
landscapes.
This
study
evaluates
the
classification
performance
tree
typologies
using
Sentinel-2
and
PRISMA
data,
focusing
on
central
Italy’s
different
areas.
purpose
is
to
assess
role
spectral
spatial
resolution
land
cover
classification,
contributing
forest
management
conservation
efforts.
Random
Forest
Classifier
was
applied
classify
across
two
areas:
Roman
Coastal
region
Lake
Vico
Basin.
Ground
truth
(GT)
collected
from
a
trial
citizen
survey
campaign,
were
used
for
training
validation.
datasets,
particularly
when
processed
PCA,
consistently
outperformed
Sentinel-2.
PCA
dataset
achieved
highest
overall
accuracy
71.09%
87.15%
Basin,
emphasizing
value
resolution.
However,
showed
comparative
strength
spatially
heterogeneous
Tree
more
uniform
distribution,
such
as
hazelnut
chestnut,
higher
compared
mixed-species
forests.
assesses
that
remains
viable
alternative
where
critical
also
considering
limited
images’
availability.
Moreover,
work
explores
potential
combining
satellites
accurate
GT
improved
mapping.
Language: Английский
Semi-Automatic Extraction of Hedgerows from High-Resolution Satellite Imagery
Remote Sensing,
Journal Year:
2025,
Volume and Issue:
17(9), P. 1506 - 1506
Published: April 24, 2025
Small
landscape
elements
are
critical
in
ecological
systems,
encompassing
vegetated
and
non-vegetated
features.
As
elements,
hedgerows
contribute
significantly
to
biodiversity
conservation,
erosion
protection,
wind
speed
reduction
within
agroecosystems.
This
study
focuses
on
the
semi-automatic
extraction
of
by
applying
Object-Based
Image
Analysis
(OBIA)
approach
two
multispectral
satellite
datasets.
Multitemporal
image
data
from
PlanetScope
Copernicus
Sentinel-2
have
been
used
test
applicability
proposed
for
detailed
land
cover
mapping,
with
an
emphasis
extracting
Woody
Elements.
demonstrates
significant
results
classifying
hedgerows,
a
smaller
element,
both
images.
A
good
overall
accuracy
(OA)
was
obtained
using
(OA
=
95%)
85%),
despite
coarser
resolution
latter.
will
undoubtedly
demonstrate
effectiveness
OBIA
leveraging
freely
available
particularly
identifying
thus
supporting
conservation
infrastructure
enhancement.
Language: Английский
Leveraging the Potential of PRISMA Hyperspectral Data for Forest Tree Species Classification: A Case Study in Southern Italy
Remote Sensing,
Journal Year:
2024,
Volume and Issue:
16(24), P. 4788 - 4788
Published: Dec. 22, 2024
Hyperspectral
imagery
and
advanced
classification
techniques
can
significantly
enhance
remote
sensing’s
role
in
forest
monitoring.
Thanks
to
recent
missions,
such
as
the
Italian
Space
Agency’s
PRISMA
(PRecursore
IperSpettrale
della
Missione
Applicativa—Hyperspectral
PRecursor
of
Application
Mission),
hyperspectral
data
narrow
bands
spanning
visible/near
infrared
shortwave
are
now
available.
In
this
study,
from
were
used
with
aim
testing
applicability
different
band
sizes
classify
tree
species
highly
biodiverse
environments.
The
Serre
Regional
Park
southern
Italy
was
a
case
study.
focused
on
category
classes
based
predominant
sample
plots.
Ground
truth
collected
using
global
positioning
system
together
smartphone
application
test
its
contribution
facilitating
field
collection.
final
result,
measured
dataset,
showed
an
F1
greater
than
0.75
for
four
classes:
fir
(0.81),
pine
(0.77),
beech
(0.90),
holm
oak
(0.82).
Beech
forests
highest
accuracy
(0.92),
while
chestnut
(0.68)
mixed
class
hygrophilous
(0.69)
lower
accuracy.
These
results
demonstrate
potential
spaceborne
identifying
trends
spectral
signatures
classification.
Language: Английский