Remote Sensing,
Journal Year:
2024,
Volume and Issue:
16(12), P. 2204 - 2204
Published: June 17, 2024
In
the
context
of
continuous
degradation
global
environment,
ecological
restoration
has
become
a
primary
task
in
environmental
governance.
this
process,
remote
sensing
technology,
as
an
advanced
monitoring
and
analysis
tool,
plays
key
role
restoration.
This
article
reviews
application
technology
monitoring.
Based
on
comprehensive
literature
field
sensing,
it
systematically
summarizes
major
in-orbit
spaceborne
airborne
sensors
their
related
products.
further
proposes
series
evaluation
indicators
for
from
four
aspects:
forests,
soil,
water,
atmosphere,
elaborates
calculation
methods
these
indicators.
addition,
paper
also
evaluating
effectiveness
restoration,
including
subjective
evaluation,
objective
methods.
Finally,
we
analyze
challenges
faced
by
effectiveness,
such
issues
with
precision
extraction,
limitations
spatial
resolution,
diversity
review
looks
forward
to
future
technologies,
potential
applications
integrated
aerospace
terrestrial
multi-data
fusion,
machine
learning
technologies.
study
reveals
monitoring,
aiming
provide
efficient
tools
innovative
strategies
assessment
Sensors,
Journal Year:
2025,
Volume and Issue:
25(3), P. 684 - 684
Published: Jan. 23, 2025
Hyperspectral
technology
has
become
increasingly
important
in
monitoring
soil
heavy
metal
pollution,
yet
hyperspectral
data
often
contain
substantial
band
redundancy,
and
selection
methods
are
typically
limited
to
single
algorithms
or
simple
combinations.
Multi-algorithm
combinations
for
remain
underutilized.
To
address
this
gap,
study,
conducted
Gejiu,
Yunnan
Province,
China,
proposes
a
multi-algorithm
method
enable
the
rapid
prediction
of
lead
(Pb)
contamination
levels
soil.
construct
preliminary
Pb
content
model,
initial
spectral
bands
utilized
including
CARS
(Competitive
Adaptive
Reweighted
Sampling),
GA
(Genetic
Algorithm),
MI
(mutual
information),
SPA
(Successive
Projections
WOA
(Whale
Optimization
Algorithm).
The
results
indicated
that
achieved
highest
modeling
accuracy.
Building
on
this,
combined
WOA-based
was
developed,
such
as
WOA-CARS,
WOA-GA,
WOA-MI,
WOA-SPA,
with
multi-level
optimization
further
refined
by
(e.g.,
WOA-GA-MI,
WOA-CARS-MI,
WOA-SPA-MI).
showed
WOA-GA-MI
model
exhibited
optimal
performance,
achieving
an
average
R2
0.75,
improvements
0.32,
0.11,
0.02
over
full-spectrum
WOA-selected
WOA-GA
respectively.
Additionally,
response
analysis
identified
22
common
essential
inversion.
proposed
not
only
significantly
enhances
accuracy
but
also
provides
new
insights
into
optimizing
selection,
serving
valuable
scientific
foundation
assessing
contamination.
Remote Sensing,
Journal Year:
2025,
Volume and Issue:
17(7), P. 1164 - 1164
Published: March 25, 2025
Soil
vanadium
contamination
poses
a
significant
threat
to
ecosystems.
Hyperspectral
remote
sensing
plays
critical
role
in
extracting
spectral
features
of
heavy
metal
contamination,
mapping
its
spatial
distribution,
and
monitoring
trends
over
time.
This
study
targets
vanadium-contaminated
area
Panzhihua
City,
Sichuan
Province.
sampling
measurements
occurred
the
laboratory.
(Gaofen-5,
GF-5)
multispectral
(Gaofen-2,
GF-2;
Sentinel-2)
images
were
acquired
preprocessed,
feature
bands
extracted
by
combining
laboratory
data.
A
dual-branch
convolutional
neural
network
(DB-CNN)
fused
hyperspectral
confirmed
fusion’s
effectiveness.
Six
prevalent
machine
learning
models
adopted,
unified
framework
leveraged
Random
Forest
(RF)
as
second-layer
model
enhance
predictive
performance
these
base
models.
Both
ensemble
evaluated
based
on
accuracy.
The
fusion
process
enhanced
models,
improving
R2
values
for
(V)
pentavalent
(V5+)
from
0.54
0.3
0.58
0.39,
respectively,
at
4
m
resolution.
Further
optimization
using
RF
refine
Extreme
Trees
(ETs)
significantly
increased
0.83
0.75
V
V5+,
this
scale.
934
nm
464
wavelengths
identified
most
predicting
soil
contamination.
integrated
approach
robustly
delineates
distribution
characteristics
V5+
soils,
facilitating
precise
ecological
risk
assessments
through
comparative
analysis
accuracy
across
diverse
Agriculture,
Journal Year:
2024,
Volume and Issue:
14(7), P. 1200 - 1200
Published: July 21, 2024
Hyperspectral
technology
is
widely
recognized
as
an
effective
method
for
monitoring
soil
salinity.
However,
the
traditional
sieved
samples
often
cannot
reflect
true
condition
of
surface.
In
particular,
there
a
lack
research
on
spectral
response
cracked
salt-affected
soils
despite
common
occurrence
cohesive
saline
shrinkage
and
cracking
during
water
evaporation.
To
address
this
research,
laboratory
was
designed
to
simulate
desiccation
progress
57
soda
saline–alkali
with
different
salinity
levels
in
Songnen
Plain
China.
After
completion
drying
process,
spectroscopic
analysis
conducted
surface
all
samples.
Moreover,
study
aimed
evaluate
predictive
ability
multiple
linear
regression
models
(MLR)
four
main
salt
parameters.
The
hyperspectral
reflectance
data
analyzed
using
three
band
screening
methods,
namely
random
forest
(RF),
principal
component
(PCA),
Pearson
correlation
(R).
findings
revealed
significant
between
salinity,
suggesting
that
primary
factor
influencing
Plain.
results
modeling
also
indicated
that,
regardless
dimensionality
reduction
employed,
exhibited
highest
prediction
accuracy
followed
by
electrical
conductivity
(EC)
sodium
(Na+),
while
pH
model
weakest
performance.
addition,
usage
RF
selection
has
best
effect
compared
PCA
which
allows
information
be
predicted
precisely.
