Wild,
Journal Year:
2025,
Volume and Issue:
2(1), P. 7 - 7
Published: March 11, 2025
Multi-source
remote
sensing
fusion
and
machine
learning
are
effective
tools
for
forest
monitoring.
This
study
aimed
to
analyze
various
techniques,
their
application
with
algorithms,
assessment
in
estimating
type
aboveground
biomass
(AGB).
A
keyword
search
across
Web
of
Science,
Science
Direct,
Google
Scholar
yielded
920
articles.
After
rigorous
screening,
72
relevant
articles
were
analyzed.
Results
showed
a
growing
trend
optical
radar
fusion,
notable
use
hyperspectral
images,
LiDAR,
field
measurements
fusion-based
Machine
particularly
Random
Forest
(RF),
Support
Vector
(SVM),
K-Nearest
Neighbor
(KNN),
leverage
features
from
fused
sources,
proper
variable
selection
enhancing
accuracy.
Standard
evaluation
metrics
include
Mean
Absolute
Error
(MAE),
Root
Squared
(RMSE),
Overall
Accuracy
(OA),
User’s
(UA),
Producer’s
(PA),
confusion
matrix,
Kappa
coefficient.
review
provides
comprehensive
overview
prevalent
data
by
synthesizing
current
research
highlighting
fusion’s
potential
improve
monitoring
The
underscores
the
importance
spectral,
topographic,
textural,
environmental
variables,
sensor
frequency,
key
gaps
standardized
protocols
exploration
multi-temporal
dynamic
change
Environmental Monitoring and Assessment,
Journal Year:
2025,
Volume and Issue:
197(2)
Published: Jan. 6, 2025
Abstract
The
grassland
ecosystem
forms
a
critical
part
of
the
natural
ecosystem,
covering
up
to
15–26%
Earth’s
land
surface.
Grassland
significantly
impacts
carbon
cycle
and
climate
regulation
by
storing
dioxide.
organic
matter
found
in
biomass,
which
acts
as
source,
greatly
expands
stock
terrestrial
ecosystems.
Correct
estimation
above
ground
biomass
(AGB)
its
spatial
temporal
changes
is
vital
for
determining
grassland.
Datasets
from
multiple
sources
were
fused
accomplish
objective
study.
Sentinel-2
sensor
band,
vegetation
index
(NDVI),
Shuttle
Radar
Topography
Mission
(SRTM)
DEM
products
used
predictor
variables,
while
Global
Ecosystem
Dynamics
Investigations
(GEDI)
mean
above-ground
density
(AGBD)
data
was
train
model.
Random
forest
(RF)
gradient
boosting
estimate
AGB
biome.
We
also
identified
correlation
between
Sentinel-2-derived
indices
ground-based
measurements
leaf
area
(LAI).
processing
duration,
parameter
requirements,
human
intervention
are
reduced
with
RF
algorithms.
Due
fundamental
concept,
ensemble
algorithms
effectively
handled
multi-modal
automatically
conducted
spectral
selection.
findings
show
variations
study
area’s
concentration
throughout
five
years.
According
results,
models
outperformed
both
achieved
highest
R
2
value
0.5755
Mg/ha,
0.7298
Mg/ha.
VI
vs
LAI
results
that
NDVI
best-performing
model
an
0.6396
m
−2
RMSE
0.159893
,
followed
OSAVI,
NDRE,
MSAVI.
This
result
shows
field
biophysical
can
map
ecosystem’s
biomass.
Forests,
Journal Year:
2025,
Volume and Issue:
16(2), P. 347 - 347
Published: Feb. 15, 2025
Aboveground
biomass
(AGB)
serves
as
an
important
indicator
for
assessing
the
productivity
of
forest
ecosystems
and
exploring
global
carbon
cycle.
However,
accurate
estimation
AGB
remains
a
significant
challenge,
especially
when
integrating
multi-source
remote
sensing
data,
effects
different
feature
combinations
results
are
unclear.
In
this
study,
we
proposed
method
estimating
by
combining
Gao
Fen
7
(GF-7)
stereo
imagery
with
data
from
Sentinel-1
(S1),
Sentinel-2
(S2),
Advanced
Land
Observing
Satellite
digital
elevation
model
(ALOS
DEM),
field
survey
data.
The
continuous
tree
height
(TH)
was
derived
using
GF-7
ALOS
DEM.
Spectral
features
were
extracted
S1
S2,
topographic
Using
these
features,
15
constructed.
recursive
elimination
(RFE)
used
to
optimize
each
combination,
which
then
input
into
extreme
gradient
boosting
(XGBoost)
estimation.
Different
estimate
compared.
best
selected
mapping
distribution
at
30
m
resolution.
outcomes
showed
that
composed
13
including
TH,
topographic,
spectral
S2
This
achieved
prediction
performance,
determination
coefficient
(R2)
0.71
root
mean
square
error
(RMSE)
18.11
Mg/ha.
TH
found
be
most
predictive
feature,
followed
optical
radar
features.
Wild,
Journal Year:
2025,
Volume and Issue:
2(1), P. 7 - 7
Published: March 11, 2025
Multi-source
remote
sensing
fusion
and
machine
learning
are
effective
tools
for
forest
monitoring.
This
study
aimed
to
analyze
various
techniques,
their
application
with
algorithms,
assessment
in
estimating
type
aboveground
biomass
(AGB).
A
keyword
search
across
Web
of
Science,
Science
Direct,
Google
Scholar
yielded
920
articles.
After
rigorous
screening,
72
relevant
articles
were
analyzed.
Results
showed
a
growing
trend
optical
radar
fusion,
notable
use
hyperspectral
images,
LiDAR,
field
measurements
fusion-based
Machine
particularly
Random
Forest
(RF),
Support
Vector
(SVM),
K-Nearest
Neighbor
(KNN),
leverage
features
from
fused
sources,
proper
variable
selection
enhancing
accuracy.
Standard
evaluation
metrics
include
Mean
Absolute
Error
(MAE),
Root
Squared
(RMSE),
Overall
Accuracy
(OA),
User’s
(UA),
Producer’s
(PA),
confusion
matrix,
Kappa
coefficient.
review
provides
comprehensive
overview
prevalent
data
by
synthesizing
current
research
highlighting
fusion’s
potential
improve
monitoring
The
underscores
the
importance
spectral,
topographic,
textural,
environmental
variables,
sensor
frequency,
key
gaps
standardized
protocols
exploration
multi-temporal
dynamic
change
