Agronomy,
Journal Year:
2024,
Volume and Issue:
14(12), P. 3039 - 3039
Published: Dec. 19, 2024
The
accurate
prediction
of
the
spatial
variability
for
soil
water
content
(SWC)
in
farmland
is
essential
resource
management
and
sustainable
agricultural
development.
However,
natural
factors
introduce
uncertainty
result
poor
alignment
when
predicting
SWC,
leading
to
low
accuracy.
To
address
this,
this
study
introduced
a
novel
indicator:
landscape
indices.
These
indices
include
largest
patch
index
(LPI),
edge
density
(ED),
aggregation
(AI),
cohesion
(COH),
contagion
(CON),
division
(DIV),
percentage
like
adjacencies
(PLA),
Shannon
evenness
(SHEI),
diversity
(SHDI).
A
Bayesian
optimization–deep
forest
(BO–DF)
model
was
developed
leverage
these
SWC.
Statistical
analysis
revealed
that
exhibited
skewed
distributions
weak
linear
correlations
with
SWC
(r
<
0.2).
Despite
incorporating
variables
into
BO–DF
significantly
improved
accuracy,
R2
increasing
by
35.85%.
This
demonstrated
robust
nonlinear
fitting
capability
Spatial
mapping
using
indicated
high-value
areas
were
predominantly
located
eastern
southern
regions
Yellow
River
Delta
China.
Furthermore,
SHapley
additive
explanation
(SHAP)
highlighted
key
drivers
findings
underscore
potential
as
valuable
prediction,
supporting
regional
strategies
Soil Systems,
Journal Year:
2025,
Volume and Issue:
9(1), P. 20 - 20
Published: March 4, 2025
The
relationships
between
soil
aggregates,
aggregate-associated
carbon
(C),
and
compaction
indices
in
pomegranate
orchards
of
varying
ages
(0–30
years)
Assiut,
Egypt,
were
investigated.
Soil
bulk
density
(Bd)
organic
(OC)
content
increased
with
orchard
age
both
the
surface
(0.00–0.20
m)
subsurface
(0.20–0.40
layers
0.20–0.40
m).
percentage
macroaggregates
(R0.25)
their
OC
aggregate
fraction
>
0.250
mm
as
layer
Older
show
improved
structure,
indicated
by
higher
mean
weight
diameter
(MWD)
geometric
(GMD),
alongside
reduced
fractal
dimension
(D)
erodibility
(K).
As
increased,
maximum
(BMax)
decreased
due
to
an
increase
OC,
while
degree
compactness
(DC)
reaching
a
at
for
30
Y
orchards.
C
significantly
influenced
BMax,
which
led
reducing
risk.
Multivariate
analyses
identified
>2
most
critical
factor
influencing
DC,
compaction,
K
aggregates
negatively
correlated
but
was
positively
associated
MWD
GMD.
Moreover,
DC
Bd
proportions
whereas
2–0.250
aggregation.
These
findings
highlight
role
size
fractions
enhancing
structure
stability,
mitigating
erosion
risks
Remote Sensing,
Journal Year:
2025,
Volume and Issue:
17(7), P. 1131 - 1131
Published: March 22, 2025
As
one
of
the
foundational
datasets
in
geographical
information
science,
land
use
and
cover
(LULC)
data
plays
a
crucial
role
study
human–environment
interaction
mechanisms,
urban
sustainable
development,
other
related
issues.
Although
existing
research
has
explored
type
recognition
from
remote
sensing
imagery,
interpretation
algorithms,
perspectives,
significant
spatial
discrepancies
exist
between
these
products.
Therefore,
we
introduced
multi-source
LULC
integration
approach
that
incorporates
dependencies,
employing
fully
connected
neural
network
alongside
environmental
variables
to
enhance
accuracy
data.
The
Yangtze
River
Delta
was
chosen
as
case
area
for
method
evaluation
validation.
Our
results
show
proposed
significantly
improves
classification
accuracy.
A
comparative
analysis
both
global
category-specific
perspectives
revealed
product
obtained
exhibited
notably
higher
overall
accuracy,
Kappa
coefficient,
intersection
over
union
compared
China
dataset,
30
m
fine
dynamic
monitoring
multi-period
dataset.
Additionally,
quantity
allocation
disagreements
fused
were
improved.
fusion
its
products
can
provide
support
services
construction,
resource
management,
protection,
demonstrating
value
importance.
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: April 24, 2025
Water
quality
early
warning
is
crucial
for
protecting
ecological
security
and
controlling
pollution
in
lakes
reservoirs.
However,
the
traditional
level
may
not
provide
accurate
data
a
specific
area.
Therefore,
it
necessary
to
design
an
adaptive
threshold
identification
system
that
conforms
actual
operating
environment.
This
study
monitored
nine
water
parameters-water
temperature
(WT),
pH,
dissolved
oxygen
(DO),
permanganate
index
(CODMn),
chemical
demand
(COD),
five-day
biochemical
(BOD5),
total
nitrogen
(TN),
phosphorus
(TP),
ammonia
(NH3-N)-monthly
from
11
sampling
sites
Danjiangkou
Reservoir,
i.e.,
largest
artificial
lake
Asia,
2017
2022.
The
reservoir
was
divided
into
three
sub-areas
by
cluster
analysis:
Danku,
Hanku,
intake.
Quality
Index
(WQI)
used
comprehensive
spatiotemporal
evaluation,
minimum
WQI
(WQImin)
model
developed
using
multiple
linear
regression.
Finally,
risk
early-warning
proposed
based
on
frequency
analysis,
categorizing
six
levels.
findings
reveal
each
area
maintains
at
"good"
or
"excellent"
levels
during
period.
average
values,
lowest
highest,
are
Hanku
(75.44),
Danku
(78.78),
intake
(79.07).
result
shows
of
Reservoir
has
been
maintained
good
due
control
management
Chinese
government
after
operation
Middle
Route
South-to-North
Diversion
Project
China.
WQImin
models
have
different
key
parameters:
WT,
DO,
TN,
TP,
COD
common
all
areas,
whereas
NH3-N
included
both
models.
BOD5
pH
were
unique
models,
respectively.
TN
TP
identified
as
parameters
affecting
safety
Reservoir.
thresholds
significantly
higher
than
those
intake,
indicating
worst.
These
dynamically
revised
through
new
became
available.
assessment
framework
provides
robust
tool
offers
scientific
reliable
reference
administrative
departments
implement
effective
environment
prevention
strategies.
