Remote Sensing,
Год журнала:
2024,
Номер
16(21), С. 4091 - 4091
Опубликована: Ноя. 1, 2024
Under
the
interference
of
climate
warming
and
human
engineering
activities,
degradation
permafrost
causes
frequent
occurrence
geological
disasters
such
as
uneven
foundation
settlement
landslides,
which
brings
great
challenges
to
construction
operational
safety
road
projects.
In
this
paper,
spatial
temporal
evolution
surface
deformations
along
Beihei
Highway
was
investigated
by
combining
SBAS-InSAR
technique
frost
number
model
after
considering
vegetation
factor
with
multi-source
remote
sensing
observation
data.
After
comprehensively
factors
change,
degradation,
anthropogenic
disturbance,
landslide
processes
were
analyzed
in
conjunction
site
surveys
ground
The
results
show
that
average
deformation
rate
is
approximately
−16
mm/a
over
22
km
section
study
area.
on
pavement
related
topography,
subsidence
more
pronounced
areas
high
topographic
relief
a
sunny
aspect.
Permafrost
roads
area
showed
an
insignificant
trend,
at
landslides
large
deformation,
significant
trend.
Meteorological
monitoring
data
indicate
annual
minimum
mean
temperature
increasing
rapidly
1.266
°C/10a
during
last
40
years.
associated
precipitation
freeze–thaw
cycles.
There
are
interactions
between
important
influences
settlement.
Focusing
process
zone
can
help
deeply
understand
mechanism
change
impact
hazards
zone.
Ecological Informatics,
Год журнала:
2024,
Номер
81, С. 102622 - 102622
Опубликована: Май 1, 2024
Chlorophyll
content
is
an
important
index
for
evaluating
the
health
and
productivity
of
crops,
environmental
stress
on
them.
The
real-time,
rapid,
accurate
acquisition
chlorophyll
plays
a
key
role
in
crop
growth
monitoring.
Remote
sensing
can
quickly
obtain
regional
global
scale,
but
how
to
eliminate
interference
soil
background
estimation
major
challenge.
statistical
analysis
method
based
empirical/semi-empirical
model
simpler,
faster
easier
implement
than
that
radiative
transfer
mechanism
model.
influence
by
looking
Vegetation
(VI)
sensitive
not
certain
extent.
However,
accuracy
this
low
fields
with
different
degrees
coverage.
Additionally,
special
characteristics
rice
make
doubtful
tool
estimate
To
improve
leaf
(LCC)
model,
we
here
propose
new
We
analyzed
remote
images
Sentinel-2
over
rice-planting
areas
Qian
Gorlos
County
Jilin
Province
China.
divided
study
area
into
three
regions
high-,
medium-,
low-rice
canopy
Rice
LCC
each
region
was
estimated
identifying
vegetation
indices
are
coverages.
Compared
results
without
considering
coverage,
our
achieves
higher
accuracy.
In
addition,
applied
Northeast
China
2023
verify
its
strong
generalisability
robustness.
Our
provides
reference
rapidly
non-destructively
obtaining
images.
applicability
other
crops
will
be
verified
future.
Ecological Informatics,
Год журнала:
2024,
Номер
80, С. 102505 - 102505
Опубликована: Янв. 30, 2024
Studying
the
spatiotemporal
evolutionary
characteristics
of
vegetation
and
effect
precipitation
changes
is
necessary
for
understanding
regional
ecological
environment.
We
used
trend
analysis,
partial
correlation
significance
tests,
residual
analysis
to
analyze
evolution
driving
factors
fractional
cover
(FVC)
in
Jinghe
River
Basin
(JRB)
from
1998
2019.
The
results
showed
that
coverage
JRB
significantly
improved
FVC
an
increasing
90.64%
areas
JRB,
overall
annual
change
was
extremely
significant
(p
≤
0.01).
However,
insignificant
trend;
distribution
developed
a
uniform
direction
centroid
tended
move
backward.
area
with
between
concentration
index
accounted
largest
proportion
(18.47%).
Precipitation
generally
favored
recovery;
however,
limited
non-precipitation
dominated
FVC.
Our
study
contributes
more
comprehensive
effects
patterns
on
facilitate
protection.
Ecological Informatics,
Год журнала:
2024,
Номер
82, С. 102768 - 102768
Опубликована: Авг. 10, 2024
Fractional
Vegetation
Cover
(FVC)
serves
as
a
crucial
indicator
in
ecological
sustainability
and
climate
change
monitoring.
While
machine
learning
is
the
primary
method
for
FVC
inversion,
there
are
still
certain
shortcomings
feature
selection,
hyperparameter
tuning,
underlying
surface
heterogeneity,
explainability.
Addressing
these
challenges,
this
study
leveraged
extensive
field
data
from
Qinghai-Tibet
Plateau.
Initially,
selection
algorithm
combining
genetic
algorithms
XGBoost
was
proposed.
This
integrated
with
Optuna
tuning
method,
forming
GA-OP
combination
to
optimize
learning.
Furthermore,
comparative
analyses
of
various
models
inversion
alpine
grassland
were
conducted,
followed
by
an
investigation
into
impact
heterogeneity
on
performance
using
NDVI
Coefficient
Variation
(NDVI-CV).
Lastly,
SHAP
(Shapley
Additive
exPlanations)
employed
both
global
local
interpretations
optimal
model.
The
results
indicated
that:
(1)
exhibited
favorable
terms
computational
cost
accuracy,
demonstrating
significant
potential
tuning.
(2)
Stacking
model
achieved
among
seven
(R2
=
0.867,
RMSE
0.12,
RPD
2.552,
BIAS
−0.0005,
VAR
0.014),
ranking
follows:
>
CatBoost
LightGBM
RFR
KNN
SVR.
(3)
NDVI-CV
enhanced
result
reliability
excluding
highly
heterogeneous
regions
that
tended
be
either
overestimated
or
underestimated.
(4)
revealed
decision-making
processes
perspectives.
allowed
deeper
exploration
causality
between
features
targets.
developed
high-precision
scheme,
successfully
achieving
accurate
proposed
approach
provides
valuable
references
other
parameter
inversions.
Ecological Informatics,
Год журнала:
2024,
Номер
81, С. 102551 - 102551
Опубликована: Март 7, 2024
The
World
Cup
stands
as
the
most
momentous
global
sporting
event,
and
significantly
impacts
urban
green
space
(UGS)
of
host
cities.
However,
impacts,
processes,
pattern
characteristic
on
UGS
have
not
yet
been
fully
understood.
To
fill
this
gap,
we
employ
time-series
satellite
imagery
compute
normalized
difference
vegetation
index
(NDVI)
across
detailed
maps
in
Qatar
from
2000
to
2022.
In
our
quantitative
assessment,
investigate
coverage,
landscape
patterns,
exposure
both
before
after
Cup.
Additionally,
compile
seven
instances
greening
Qatar,
compare
them
with
processes
three
cities
located
neighboring
countries.
This
contextual
analysis
aims
unravel
nuanced
impact
Qatar.
Our
results
demonstrate:
(1)
emerges
a
significant
contributor
growth,
expansion
accounting
for
94.3%
overall
increase
built-up
area
during
tournament.
surge
growth
is
equivalent
an
additional
38
Manhattan
Central
Parks.
(2)
induces
transformation
landscapes,
rendering
more
complex
fragmented.
degree
change
within
35
times
greater
than
those
changes
observed
pre-World
period.
(3)
brings
about
enhancement
minimum
level
citizens,
marking
8.7-fold
increase.
event
has
proven
be
instrumental
propelling
towards
multifaceted
greening,
establishing
country
leading
model
regional
processes.
study
thus
confirms
Cup's
role
promoting
reshaping
offering
fresh
insights
into
its
contribution
sustainable
development.
Hydrological Processes,
Год журнала:
2025,
Номер
39(1)
Опубликована: Янв. 1, 2025
ABSTRACT
Monitoring
river
connectivity
across
large
regions
is
essential
for
understanding
hydrological
processes
and
environmental
management.
However,
comprehensive
assessments
of
are
often
hindered
by
inaccurate
dam
databases,
which
biased
towards
larger
dams
while
overlooking
smaller
or
low‐head
dams.
To
enhance
the
accuracy
assessments,
we
developed
three
advanced
convolutional
neural
networks
(CNNs;
YOLOv5,
Advance‐You
Only
Look
Once
[YOLO],
Faster
R‐CNN)
to
accurately
classify
evaluate
using
high‐resolution
(1
m)
remote
sensing
imagery.
The
evaluation
results
showed
that
Advance‐YOLO
performs
best
with
an
average
mean
precision
(mAP)
86.6%,
R‐CNN
mediocrely
mAP
77.9%.
Applying
well‐trained
model
in
Tarim
River
Basin
(China),
one
largest
inland
basins
around
globe,
found
there
currently
135
total
on
its
sources.
Conversely,
existing
public
database
underestimates
85.9%
Notably,
a
14.3%
decline
over
past
decade,
current
density
four
source
rivers
1.12
per
10
000
km
2
.
overestimated
83.9%.
here
enhances
assessment
areas
long
period,
thereby
fostering
more
research
effective
water
resource
Remote Sensing,
Год журнала:
2025,
Номер
17(5), С. 921 - 921
Опубликована: Март 5, 2025
Studying
the
spatiotemporal
trends
and
influencing
factors
of
vegetation
coverage
is
essential
for
assessing
ecological
quality
monitoring
regional
ecosystem
dynamics.
The
existing
research
on
variations
their
driving
predominantly
focused
inland
ecologically
vulnerable
regions,
while
coastal
areas
received
relatively
little
attention.
However,
with
unique
geographical,
ecological,
anthropogenic
activity
characteristics,
may
exhibit
distinct
distribution
patterns
mechanisms.
To
address
this
gap,
we
selected
Shandong
Province
(SDP),
a
representative
province
in
China
significant
natural
socioeconomic
heterogeneity,
as
our
study
area.
investigate
coastal–inland
differentiation
dynamics
its
underlying
mechanisms,
SDP
was
stratified
into
four
geographic
sub-regions:
coastal,
eastern,
central,
western.
Fractional
cover
(FVC)
derived
from
MOD13A3
v061
NDVI
data
served
key
indicator,
integrated
multi-source
datasets
(2000–2023)
encompassing
climatic,
topographic,
variables.
We
analyzed
characteristics
dominant
across
these
sub-regions.
results
indicated
that
(1)
FVC
displayed
complex
notable
gradient
where
decreased
towards
coast.
(2)
influence
various
significantly
varied
sub-regions,
dominating
an
east–west
polarity,
i.e.,
explanatory
power
intensified
westward
resurging
zones.
(3)
intricate
interaction
multiple
influenced
spatial
FVC,
particularly
dual-factor
synergies
interactions
between
other
were
crucial
determining
coverage.
Notably,
zone
exhibited
high
sensitivity
to
drivers,
highlighting
exceptional
ecosystems
human
activities.
This
provides
insights
different
geographical
zones
well
factors.
These
findings
can
help
understand
challenges
faced
protecting
vegetation,
facilitating
deeper
insight
responses
enabling
formulation
effective
tailored
strategies
promote
sustainable
development
areas.
Drones,
Год журнала:
2025,
Номер
9(4), С. 235 - 235
Опубликована: Март 23, 2025
Salt
marsh
ecosystems
play
a
critical
role
in
coastal
protection,
carbon
sequestration,
and
biodiversity
preservation.
However,
they
are
increasingly
threatened
by
climate
change
anthropogenic
activities,
necessitating
precise
vegetation
mapping
for
effective
conservation.
This
study
investigated
the
effectiveness
of
spectral
features
machine
learning
models
separating
typical
salt
types
Yellow
River
Delta
using
uncrewed
aerial
vehicle
(UAV)-derived
multispectral
imagery.
The
results
revealed
that
Normalized
Difference
Vegetation
Index
(NDVI),
Green
(GNDVI),
Optimized
Soil
Adjusted
(OSAVI)
were
pivotal
differentiating
types,
compared
with
reflectance
at
individual
bands.
Among
evaluated
models,
U-Net
achieved
highest
overall
accuracy
(94.05%),
followed
SegNet
(93.26%).
model
produced
overly
distinct
abrupt
boundaries
between
lacking
natural
transitions
found
real
distributions.
In
contrast,
excelled
boundary
handling,
better
capturing
types.
Both
deep
outperformed
Random
Forest
(83.74%)
Extreme
Gradient
Boosting
(83.34%).
highlights
advantages
their
potential
ecological
monitoring
conservation
efforts.