Multiple Environmental Variables as Covariates to Improve the Accuracy of Spatial Prediction Models for SOM on Karst Aera
Land Degradation and Development,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Jan. 12, 2025
ABSTRACT
Aims
accurately
predicting
the
spatial
distribution
of
soil
organic
matter
(SOM)
is
essential
for
environmental
management
and
carbon
storage
estimation.
However,
diversity
sources
variables
poses
a
challenge
in
studying
SOM.
Methods
order
to
address
this
issue,
we
propose
leveraging
multiple
employing
machine
learning
models,
specifically
Lightweight
gradient
boosting
(LightGBM)
random
forest
(RF),
SOM
distribution.
128
samples
were
collected
from
Caohai
National
Nature
Reserve,
their
content
was
measured.
Results
study
found
that
average
36.75
g/kg.
Compared
traditional
linear
regression
models
such
as
ordinary
kriging
(OK),
least
squares
(OLS),
geographically
weighted
(GWR),
based
on
nonlinear
regression,
LightGBM
RF,
demonstrated
higher
cross‐validated
coefficients
determination
(
R
2
)
0.62
0.60,
respectively,
outperforming
other
models.
Additionally,
RF
exhibited
lower
mean
absolute
error
(MAE)
root
square
(RMSE),
indicating
stability
generalization
capability.
The
among
showed
consistency,
with
observed
southern
near‐Caohai
Lake
regions
northern
farther
Lake.
Shapley
additive
explanations
(SHAP)
model
highlighted
agricultural
land
(AL),
pH,
Elevation
(ELV)
primary
covariates
influencing
Conclusions
provides
valuable
insights
support
estimation
karst
plateau
region.
Language: Английский
Mapping Soil Organic Matter in Black Soil Cropland Areas Using Remote Sensing and Environmental Covariates
Agriculture,
Journal Year:
2025,
Volume and Issue:
15(3), P. 339 - 339
Published: Feb. 4, 2025
The
accurate
prediction
of
soil
organic
matter
(SOM)
content
is
important
for
sustainable
agriculture
and
effective
management.
This
task
particularly
challenging
due
to
the
variability
in
factors
influencing
SOM
distribution
across
different
cultivated
land
types,
as
well
site-specific
responses
remote
sensing
data
environmental
covariates,
especially
black
region
northeastern
China,
where
exhibits
significant
spatial
variability.
study
evaluated
variations
on
importance
imagery
covariates
zones.
A
total
180
samples
(0–20
cm)
were
collected
from
Youyi
County,
Heilongjiang
Province,
multi-year
synthetic
bare
images
2014
2022
(focusing
April
May)
acquired
using
Google
Earth
Engine.
Combining
three
types
such
drainage,
climate
topography,
area
was
categorized
into
dry
field
paddy
field.
Then,
model
constructed
random
forest
regression
method
accuracy
strategies
by
10-fold
cross-validation.
findings
indicated
that,
(1)
overall
analysis,
combining
drainage
variables
May
could
attain
highest
accuracy,
ranked
follows:
(RS)
>
(CLI)
(DN)
Topography
(TP).
(2)
Zonal
analysis
conducted
with
a
high
degree
precision,
evidenced
an
R2
0.72
impressively
low
RMSE
0.73%.
time
window
monitoring
More
specifically,
optimal
frames
dryland
identified
May,
while
those
fields
concentrated
May.
(3)
In
addition,
diverse
observed
vary
types.
regions
characterized
intricate
fields,
contributions
assumed
heightened
importance.
Conversely,
featuring
flat
terrain,
roles
played
more
substantial
role
outcomes.
These
underscore
selecting
appropriate
inputs
improving
accuracy.
Language: Английский
Enhancing crop yield and carbon sequestration and greenhouse gas emission mitigation through different organic matter input in the Bohai Rim region: An estimation based on the DNDC-RF framework
Field Crops Research,
Journal Year:
2024,
Volume and Issue:
319, P. 109624 - 109624
Published: Nov. 6, 2024
Language: Английский