Quality control of the GNSS-IR sea level measurements by using K-means clustering
Survey Review,
Год журнала:
2025,
Номер
unknown, С. 1 - 14
Опубликована: Янв. 26, 2025
Quality
control
is
a
crucial
step
in
GNSS-IR
data
processing
and
performed
this
study
using
two
methods:
the
peak-to-noise
ratio
K-means
clustering.
Both
quality
methods
are
applied
to
SNR
at
MERS,
TRBZ,
SNOP
sites.
clustering
shows
better
performance
for
MERS
GPS
L1,
Galileo
L2,
while
TRBZ
L1.
The
correlation
coefficient
between
sea
levels
from
L1
signal
tide
gauge
greater
than
85%.
These
results
demonstrate
that
promising
control.
Язык: Английский
Improving Soil Moisture Prediction Using Gaussian Process Regression
Smart Agricultural Technology,
Год журнала:
2025,
Номер
unknown, С. 100905 - 100905
Опубликована: Март 1, 2025
Язык: Английский
A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers
Yiying Yao,
Jixuan Yan,
Guang Li
и другие.
Agriculture,
Год журнала:
2025,
Номер
15(8), С. 837 - 837
Опубликована: Апрель 13, 2025
The
Global
Navigation
Satellite
System
Interferometric
Reflectometry
(GNSS-IR)
has
demonstrated
significant
potential
for
soil
moisture
content
(SMC)
monitoring
due
to
its
high
spatiotemporal
resolution.
However,
GNSS-IR
inversion
experiments
are
notably
influenced
by
vegetation
and
meteorological
factors.
To
address
these
challenges,
this
study
proposes
a
multi-factor
SMC
method.
Six
GNSS
stations
from
the
Plate
Boundary
Observatory
(PBO)
were
selected
as
sites.
A
low-order
polynomial
was
applied
separate
reflected
signals,
extracting
parameters
such
phase,
frequency,
amplitude,
effective
reflector
height.
Auxiliary
variables,
including
Normalized
Microwave
Reflection
Index
(NMRI),
cumulative
rainfall,
daily
average
evaporation,
used
further
improve
accuracy.
dataset
constructed,
three
machine
learning
models
develop
prediction
model:
Support
Vector
Regression
(SVR),
suitable
small
medium-sized
regression
tasks;
Convolutional
Neural
Networks
(CNN),
with
robust
feature
extraction
capabilities;
NRBO-XGBoost,
which
supports
automatic
optimization.
method
achieved
remarkable
results.
For
instance,
at
P038
station,
model
attained
an
R2
of
0.98,
RMSE
0.0074
MAE
0.0038.
Experimental
results
indicate
that
significantly
outperformed
traditional
univariate
model,
whose
(RMSE,
MAE)
only
0.88
(0.0179,
0.0136).
Further
analysis
revealed
NRBO-XGBoost
surpassed
other
models,
outperforming
SVR
0.11
CNN
0.03.
Additionally,
different
surface
types
showed
higher
accuracy
in
grassland
open
shrubland
areas,
all
reaching
values
above
0.9.
Therefore,
validated,
supporting
practical
application
technology
inversion.
Язык: Английский
GNSS-IR Soil Moisture Retrieval Using Multi-Satellite Data Fusion Based on Random Forest
Remote Sensing,
Год журнала:
2024,
Номер
16(18), С. 3428 - 3428
Опубликована: Сен. 15, 2024
The
accuracy
and
reliability
of
soil
moisture
retrieval
based
on
Global
Positioning
System
(GPS)
single-star
Signal-to-Noise
Ratio
(SNR)
data
is
low
due
to
the
influence
spatial
temporal
differences
different
satellites.
Therefore,
this
paper
proposes
a
Random
Forest
(RF)-based
multi-satellite
fusion
Navigation
Satellite
Interferometric
Reflectometry
(GNSS-IR)
method,
which
utilizes
RF
Model’s
Mean
Decrease
Impurity
(MDI)
algorithm
adaptively
assign
arc
weights
fuse
all
available
satellite
obtain
accurate
results.
Subsequently,
effectiveness
proposed
method
was
validated
using
GPS
from
Plate
Boundary
Observatory
(PBO)
network
sites
P041
P037,
as
well
collected
in
Lamasquere,
France.
A
Support
Vector
Machine
model
(SVM),
Radial
Basis
Function
(RBF)
neural
model,
Convolutional
Neural
Network
(CNN)
are
introduced
for
comparison
accuracy.
results
indicated
that
had
best
performance,
with
Root
Square
Error
(RMSE)
values
0.032,
0.028,
0.003
cm3/cm3,
Absolute
(MAE)
0.025,
0.022,
0.002
correlation
coefficients
(R)
0.94,
0.95,
0.98,
respectively,
at
three
sites.
demonstrates
strong
robustness
generalization
capabilities,
providing
reference
achieving
high-precision,
real-time
monitoring
moisture.
Язык: Английский
Retrieval of significant wave height based on multi-channel fusion using shipborne GPS/BDS reflectometry
Measurement,
Год журнала:
2024,
Номер
243, С. 116416 - 116416
Опубликована: Дек. 9, 2024
Язык: Английский
Quality control and improvement of GNSS-IR soil moisture robust inversion model
Advances in Space Research,
Год журнала:
2024,
Номер
unknown
Опубликована: Июль 1, 2024
Язык: Английский
Soil moisture inversion based on multiple drought indices and RBFNN: A case study of northern Hebei Province
Heliyon,
Год журнала:
2024,
Номер
10(17), С. e37426 - e37426
Опубликована: Сен. 1, 2024
Drought
has
a
significant
impact
on
crop
growth
and
productivity,
highlighting
the
critical
need
for
precise
timely
soil
moisture
estimation
to
mitigate
agricultural
losses.
This
study
focuses
retrieval
in
northern
Hebei
Province
during
July
2012,
utilizing
eight
widely
employed
remote
sensing
drought
indices
derived
from
MODIS
satellite
data.
These
were
cross-referenced
with
measured
levels
analysis.
Based
their
correlation
coefficients,
composite
index
set
comprising
six
was
identified.
Furthermore,
radial
basis
function
neural
network
(RBFNN)
estimate
relative
humidity.
The
accuracy
evaluation
of
model,
which
integrates
multiple
RBFNN,
demonstrated
clear
superiority
over
models
relying
single
indices.
model
achieved
an
average
87.54
%
humidity
at
depth
10
cm
(SM10)
87.36
20
(SM20).
root
mean
square
errors
(RMSE)
test
sets
0.093
0.092,
respectively.
Validation
results
2013
indicated
that
inversion
accurately
reflected
actual
conditions,
effectively
capturing
dynamic
changes.
fully
verify
reliability
practicability
model.
findings
introduce
novel
approach
local
estimation,
implications
enhancing
water
resource
management
decision-making
processes.
Язык: Английский
Key Technologies in Intelligent Seeding Machinery for Cereals: Recent Advances and Future Perspectives
Agriculture,
Год журнала:
2024,
Номер
15(1), С. 8 - 8
Опубликована: Дек. 24, 2024
The
operational
performance
of
cereal
seeding
machinery
influences
the
yield
and
quality
cereals.
In
this
article,
we
review
existing
literature
on
intelligent
technologies
for
machinery,
encompassing
active
controllable
actuators,
rate
control,
seed
position
control
systems.
manuscript,
(1)
characteristics
innovative
structures
motor-driven
seed-metering
devices
ground
surface
profiling
mechanisms
are
expounded;
(2)
state-of-the-art
detection
principles
applications
soil
property
sensors
described
based
different
properties;
(3)
optimal
decision
approaches
properties
summarized;
(4)
research
state
measuring
is
expounded
in
detail;
(5)
trajectory
methods
depth
systems
measurement
principles;
(6)
present
state,
limitations,
future
development
directions
described.
future,
more
advanced
multi-algorithm
multi-sensor
fusion
detection,
decisions,
rates,
likely
to
evolve.
This
not
only
expounds
latest
studies
actuating,
sensing,
but
also
discusses
shortcomings
developing
trends
detail.
review,
therefore,
offers
a
reference
domain
Язык: Английский