A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy
Jiangtao Qi,
No information about this author
Peng Cheng,
No information about this author
Junbo Zhou
No information about this author
et al.
Land,
Journal Year:
2025,
Volume and Issue:
14(2), P. 329 - 329
Published: Feb. 6, 2025
Soil
organic
matter
(SOM)
and
total
nitrogen
(TN)
are
critical
indicators
for
assessing
soil
fertility.
Although
laboratory
chemical
analysis
methods
can
accurately
measure
their
contents,
these
techniques
time-consuming
labor-intensive.
Spectral
technology,
characterized
by
its
high
sensitivity
convenience,
has
been
increasingly
integrated
with
machine
learning
algorithms
nutrient
monitoring.
However,
the
process
of
spectral
data
remains
complex
requires
further
optimization
simplicity
efficiency
to
improve
prediction
accuracy.
This
study
proposes
a
novel
model
enhance
accuracy
SOM
TN
predictions
in
northeast
China’s
black
soil.
Visible/Shortwave
Near-Infrared
Spectroscopy
(Vis/SW-NIRS)
within
350–1070
nm
range
were
collected,
preprocessed,
dimensionality-reduced.
The
scores
first
nine
principal
components
after
partial
least
squares
(PLS)
dimensionality
reduction
selected
as
inputs,
measured
contents
used
outputs
build
back-propagation
neural
network
(BPNN)
model.
results
show
that
processed
combination
standard
normal
variate
(SNV)
multiple
scattering
correction
(MSC)
have
best
modeling
performance.
To
stability
this
model,
three
named
random
search
(RS),
grid
(GS),
Bayesian
(BO)
introduced.
demonstrate
Vis/SW-NIRS
provides
reliable
PLS-RS-BPNN
achieving
performance
(R2
=
0.980
0.972,
RMSE
1.004
0.006
TN,
respectively).
Compared
traditional
models
such
forests
(RF),
one-dimensional
convolutional
networks
(1D-CNNs),
extreme
gradient
boosting
(XGBoost),
proposed
improves
R2
0.164–0.344
predicting
0.257–0.314
respectively.
These
findings
confirm
potential
technology
effective
tools
prediction,
offering
valuable
insights
application
sensing
information.
Language: Английский
Research on Soil Erosion Based on Remote Sensing Technology: A Review
Agriculture,
Journal Year:
2024,
Volume and Issue:
15(1), P. 18 - 18
Published: Dec. 25, 2024
Monitoring
and
assessing
soil
erosion
is
essential
for
reducing
land
degradation
ensuring
food
security.
It
provides
critical
scientific
insights
developing
effective
policies
implementing
targeted
preventive
measures.
The
emergence
of
remote
sensing
technology
has
significantly
bolstered
research,
empowering
researchers
to
comprehensively
accurately
understand
address
erosion-related
challenges.
Consequently,
become
pivotal
in
research
methodologies.
In
recent
years,
significant
progress
been
made
on
erosion.
This
study
aims
encapsulate
the
current
status
advancements
applications
research.
catalogs
commonly
used
data
sources
introduces
innovative
methodologies
detecting
soil-erosion-related
information
utilizing
technology.
Furthermore,
it
delves
into
analysis
acquisition
methods
factors
influencing
examines
crucial
role
prevalent
simulation
prediction
models.
Additionally,
this
identifies
existing
challenges
outlines
prospects
developmental
directions
emphasizing
its
potential
contribute
sustainable
management
practices
environmental
conservation
efforts.
Language: Английский
Multi-spectral evaluation of total nitrogen, phosphorus and potassium content in soil using Vis-NIR spectroscopy based on a modified support vector machine with whale optimization algorithm
Mochen Liu,
No information about this author
Yang Kuankuan,
No information about this author
Yinfa Yan
No information about this author
et al.
Soil and Tillage Research,
Journal Year:
2025,
Volume and Issue:
252, P. 106567 - 106567
Published: April 19, 2025
Language: Английский
Potential of EnMAP Hyperspectral Imagery for Regional-Scale Soil Organic Matter Mapping
Remote Sensing,
Journal Year:
2025,
Volume and Issue:
17(9), P. 1600 - 1600
Published: April 30, 2025
The
emergence
of
new-generation
hyperspectral
satellites
offers
more
potential
for
mapping
soil
properties.
This
study
presents
the
first
assessment
EnMAP
(Environmental
Mapping
and
Analysis
Program)
imagery
organic
matter
(SOM)
prediction
using
actual
spectral
data
from
282
samples.
Different
preprocessing
techniques,
including
Savitzky–Golay
(SG)
smoothing,
second
derivative
SG,
Standard
Normal
Variate
(SNV)
transformation,
were
evaluated
in
combination
with
embedded
feature
selection
to
identify
most
relevant
wavelengths
SOM
prediction.
Partial
Least
Squares
Regression
(PLSR)
models
developed
under
different
pre-treatment
scenarios.
best
performance
was
obtained
SNV
top
30
bands
(wavelengths)
selected,
giving
R2
=
0.68,
RMSE
0.34%,
RPIQ
1.75.
successfully
identified
significant
prediction,
particularly
around
550
nm
Vis–NIR
region,
1570–1630
nm,
1600
2200
SWIR
region.
resulting
predictions
exhibited
spatially
consistent
patterns
that
corresponded
known
soil–landscape
relationships,
highlighting
properties
despite
its
limited
geographical
availability.
While
these
results
are
promising,
this
limitations
ability
PLSR
extrapolate
beyond
sampled
areas,
suggesting
need
explore
non-linear
modeling
approaches.
Future
research
should
focus
on
evaluating
EnMAP’s
advanced
machine
learning
techniques
comparing
it
other
available
products
establish
robust
protocols
satellite-based
monitoring.
Language: Английский
Is the estimation of soil organic carbon using the colour space model, based on visible spectroscopy range, a reliable approach?
Soil Use and Management,
Journal Year:
2024,
Volume and Issue:
40(4)
Published: Oct. 1, 2024
Abstract
Traditionally,
soil
colour
attributes
have
been
determined
using
the
Munsell
Colour
Chart
(MCC).
However,
lack
of
standardization
with
this
method
has
made
it
more
difficult
to
assess
properties,
particularly
organic
carbon
(SOC).
In
contrast,
reflectance
spectroscopy
(RS)
across
visible
(Vis,
400–800
nm),
near‐infrared
(NIR,
800–2500
nm)
and
Vis–NIR
(350–2500
spectral
regions
recognized
as
a
reliable
approach
for
predicting
SOC.
As
result,
scientists
increasingly
adopted
RS
obtain
parameters,
addressing
limitations
MCC.
because
techniques
analysis
is
typically
limited
VIS
range,
key
information
from
NIR
are
often
neglected
or
eliminated.
This
study
examined
effectiveness
VIS‐based
in
estimating
SOC
compared
VIS,
ranges.
Fifteen
parameters
were
derived
spectrum,
12
indices
calculated
these
parameters.
Three
multivariate
models
such
random
forest
(RF),
Cubist
support
vector
machine
regression
(SVMR)
used
prediction,
along
various
preprocessing
algorithms
remove
artefacts.
The
results
indicated
that,
(
R
2
=
.54)
.45),
pre‐processed
data
produced
most
accurate
.72).
suggests
that
range
alone
lacks
adequate
information,
likely
affecting
accuracy
dataset,
solely
region.
Although
introduction
slightly
improved
.47),
still
less
than
those
obtained
both
ranges
even
.54).
findings
highlight
need
caution
when
methods
estimation,
high
levels
not
necessarily
restricted
Language: Английский