Frontiers in Forests and Global Change,
Год журнала:
2025,
Номер
8
Опубликована: Апрель 28, 2025
Land
cover
change
information
is
needed
to
support
decision-making
in
land-based
natural
resource
management,
especially
coastal
areas
and
mangrove
ecosystems.
This
study
aims
assess
the
drivers
detect
forest
over
last
30
years
Kubu
Raya
District,
Indonesia,
using
satellite
imagery
data
from
United
States
Geological
Survey
(USGS)
Earth
Explorer.
Maximum
Likelihood
Classification
was
used
analyze
images
four
different
recording
digitally:
1993
(Landsat
5),
2003
7),
2013
2023
8).
Getis-Ord
Gi*
analysis
also
observe
fragmentation
distribution
patterns
determine
with
hot
spots
or
cold
Reticular
Fragmentation
Index
(RFI)
value
as
a
consideration.
Binary
Logistic
Regression
(BLR)
of
social
variables,
including
population
density,
education,
accessibility,
soil
type,
rainfall,
temperature,
slope,
elevation.
The
results
showed
significant
decrease
cover,
1,011.37
km
2
1993–964.37
2023,
an
average
loss
3.25
per
year,
mangroves,
open
areas,
ponds,
water
bodies,
agricultural
settlements.
pattern
that
occurs
some
northern
part,
there
are
insignificant
points
then
turn
into
2023.
Meanwhile,
were
shifted
spread
central
part
area.
In
addition,
variables
provide
values
directly
inversely
proportional
driving
factors.
Social
factors,
land
access,
have
relationship
change.
Regulations
made
by
government
presence
educated
community
main
for
ecosystem
conservation;
existing
access
not
exploitation
but
only
daily
activities.
Natural
such
alluvial
types,
high
concentration
nutrients,
making
them
ideal
sustainable
agriculture
ponds.
Rainfall
intensity
contributes
higher
production
stable
pond
water.
Conservation
efforts
must
consider
these
changes
spatial
dynamics
effectively
protect
ecosystems
future.
Ecological Informatics,
Год журнала:
2024,
Номер
82, С. 102732 - 102732
Опубликована: Июль 22, 2024
Accurately
estimating
aboveground
biomass
(AGB)
in
forest
ecosystems
facilitates
efficient
resource
management,
carbon
accounting,
and
conservation
efforts.
This
study
examines
the
relationship
between
predictors
from
Landsat-9
remote
sensing
data
several
topographical
features.
While
provides
reliable
crucial
for
long-term
monitoring,
it
is
part
of
a
broader
suite
available
technologies.
We
employ
machine
learning
algorithms
such
as
Extreme
Gradient
Boosting
(XGBoost),
Support
Vector
Regression
(SVR),
Random
Forest
(RF),
alongside
linear
regression
techniques
like
Multiple
Linear
(MLR).
The
primary
objectives
this
encompass
two
key
aspects.
Firstly,
research
methodically
selects
optimal
predictor
combinations
four
distinct
variable
groups:
(L1)
data,
fusion
Vegetation-based
indices
(L2),
integration
with
Shuttle
Radar
Topography
Mission
Digital
Elevation
Model
(SRTM
DEM)
(L3)
combination
best
(L4)
derived
L1,
L2,
L3.
Secondly,
systematically
assesses
effectiveness
different
to
identify
most
precise
method
establishing
any
potential
field-measured
AGB
variables.
Our
revealed
that
(RF)
model
was
utilizing
OLI
SRTM
DEM
predictors,
achieving
remarkable
accuracy.
conclusion
reached
by
assessing
its
outstanding
performance
when
compared
an
independent
validation
dataset.
RF
exhibited
accuracy,
presenting
relative
mean
absolute
error
(RMAE),
root
square
(RRMSE),
R2
values
14.33%,
22.23%,
0.81,
respectively.
XGBoost
subsequent
choice
RMAE,
RRMSE,
15.54%,
23.85%,
0.77,
further
highlights
significance
specific
spectral
bands,
notably
B4
B5
Landsat
9
capturing
spatial
distribution
patterns.
Integration
vegetation-based
indices,
including
TNDVI,
NDVI,
RVI,
GNDVI,
refines
mapping
precision.
Elevation,
slope,
Topographic
Wetness
Index
(TWI)
are
proxies
representing
biophysical
biological
mechanisms
impacting
AGB.
Through
utilization
openly
accessible
fine-resolution
employing
algorithm,
demonstrated
promising
outcomes
identification
predictor-algorithm
mapping.
comprehensive
approach
offers
valuable
avenue
informed
decision-making
assessment,
ecological
monitoring
initiatives.
Ecology and Evolution,
Год журнала:
2025,
Номер
15(2)
Опубликована: Фев. 1, 2025
ABSTRACT
This
study
evaluates
the
Billion
Tree
Afforestation
Project
(BTAP)
in
Pakistan's
Khyber
Pakhtunkhwa
(KPK)
province
using
remote
sensing
and
machine
learning.
Applying
Random
Forest
(RF)
classification
to
Sentinel‐2
imagery,
we
observed
an
increase
tree
cover
from
25.02%
2015
29.99%
2023
a
decrease
barren
land
20.64%
16.81%,
with
accuracy
above
85%.
Hotspot
spatial
clustering
analyses
revealed
significant
vegetation
recovery,
high‐confidence
hotspots
rising
36.76%
42.56%.
A
predictive
model
for
Normalized
Difference
Vegetation
Index
(NDVI),
supported
by
SHAP
analysis,
identified
soil
moisture
precipitation
as
primary
drivers
of
growth,
ANN
achieving
R
2
0.8556
RMSE
0.0607
on
testing
dataset.
These
results
demonstrate
effectiveness
integrating
learning
framework
support
data‐driven
afforestation
efforts
inform
sustainable
environmental
management
practices.
Scottish Geographical Journal,
Год журнала:
2025,
Номер
unknown, С. 1 - 20
Опубликована: Янв. 1, 2025
Forest
degradation
poses
a
greater
ecological
threat
than
deforestation,
with
forest
fragmentation
being
key
concern.
Fragmentation
breaks
vast
tracts
into
smaller,
isolated
patches,
jeopardizing
biodiversity.
A
study
in
Haryana's
sub-Himalayan
region
analysed
using
satellite
data
from
Landsat-7
ETM+
(2001)
and
Landsat-8
OLI
(2021).
Geospatial
methods,
employing
tools
like
QGIS,
ArcGIS,
FRAGSTAT,
evaluated
landscape
metrics
dynamics.
Over
20
years,
area
significantly
declined,
particularly
large
core
regions.
Paradoxically,
while
the
largest
patch
index
mean
increased,
overall
decreased.
This
trend
reflects
loss
of
smaller
patches
to
non-forest
land
uses
rather
recovery,
resulting
more
uniform
sizes.
The
reveals
growing
posed
by
shrinking
areas
expanding
scrubland,
endangering
local
These
findings
emphasize
need
for
conservation
policies
addressing
land-use
transitions
protection.
By
integrating
land-cover
analysis,
research
sheds
light
on
complex
dynamics
fragmentation,
offering
valuable
insights
conservation.
International Multidisciplinary Scientific GeoConference SGEM ...,
Год журнала:
2025,
Номер
24, С. 255 - 262
Опубликована: Фев. 15, 2025
Remote
sensing
(RS)
imagery
is
widely
used
to
assess
and
detect
environmental
changes
in
various
areas
the
numerous
methods
resulting
from
natural
human
activities.
To
understand
landscape
change,
including
role
of
windbreaks
agricultural
regions,
RS
datasets
are
essential.
Detected
by
CORINE
Land
Cover
(CLC)
project,
landscapes
have
undergone
such
as
an
increase
complex
cropping
patterns
164.19%
pastures
15.3%,
but
a
decrease
coniferous
forest
10.19%
land
mainly
occupied
agriculture
with
significant
vegetation
10.17%
between
1990
2018.
These
trends
highlight
changing
dynamics
cover,
which
critical
for
assessing
economic
value
soil
conservation
structures.
Monitoring
these
helps
effectiveness
reducing
degradation.
By
utilizing
data
remote
sensing,
this
paper
analyses
use
spatial
distribution
windbreaks,
correlating
their
presence
reductions
tracking
cover
over
time,
provides
valuable
insights
into
measures
combat
degradation
landscapes.
