A
B
S
T
R
C
TIn
the
context
of
using
aircraft
as
a
pivotal
tool
for
detecting
radioactive
hotspots,
acquisition
radioactivity
data
was
conducted
through
CeBr3
scintillation
crystal
detector
mounted
on
helicopter.
However,
challenges
arose,
including
managing
extensive
volumes,
computationally
demanding
tasks,
and
susceptibility
to
local
optima
issues.
To
address
these
leverage
benefits
Sparrow
Search
Algorithm
(SSA)
in
global
optimization
convergence
speed,
an
improved
SSA
devised.
This
version
integrated
principles
with
intricacies
searching
hotspots.
The
algorithm
employed
matrix
segmentation
method
process
matrices
derived
from
measured
data,
aiming
enhance
efficiency
accuracy.
An
empirical
analysis
conducted,
performing
100
iterations
experimental
scrutinize
impact
segmentation.
Computation
times
results
were
compared
across
different
levels,
confirming
favorable
algorithmic
outcomes
method.
practical
viability
stability
further
assessed
genuine
segmented
generated
evaluation.
Remarkably,
comparison
between
computational
manually
identified
reaffirmed
algorithm's
reliability
effectively
Agricultural Water Management,
Journal Year:
2024,
Volume and Issue:
294, P. 108718 - 108718
Published: Feb. 15, 2024
Soil
moisture
is
a
significant
variable
in
agricultural
study
and
precision
irrigation
decision-making.
It
determines
the
soil
water
availability
for
plants,
directly
influencing
plant
growth,
yield
quality.
Owing
to
variations
regional
microclimate,
landform
difference,
type
vegetation
coverage,
has
strong
spatial-temporal
heterogeneity
on
large
scale.
Micro-wave
remote
sensing
can
be
used
invert
based
dielectric
constant
under
different
weather
conditions,
while
optical
utilizes
spectral
characteristics
estimate
physiological
ecological
information
of
vegetation.
In
this
study,
two
new
hybrid
models
(ACO-RF
SSA-RF)
were
structured
by
optimizing
standalone
random
forest
(RF)
ant
colony
optimization
algorithm
(ACO)
sparrow
search
(SSA),
six
input
combinations
multi-temporal
Sentinel-1
Landsat-8
data
from
sensors
(optical,
thermal
radar
sensors)
used.
The
RF,
ACO-RF,
SSA-RF
with
inputs
employed
predict
at
depths
(5
cm,
10
20
40
cm)
large-scale
drip-irrigated
citrus
orchard.
results
showed
that
ACO-RF
outperformed
RF
model
terms
prediction
accuracy
depth
0–40
R2
0.800–0.921
0.504–0.798,
RRMSE
7.214–16.284%
11.124–22.214%,
respectively.
model,
had
better
than
0.805–0.921
0.800–0.911,
7.214–13.244%
8.274–16.284%,
At
5
cm
inversion
microwave
was
higher
multispectral
inputs,
0.556–0.888
0.541–0.886,
9.015–19.544%
9.124–22.214%,
However,
0.532–0.841
0.508–0.831,
9.124–21.021%
9.142–21.214%,
multispectral,
thermal,
exhibited
highest
predicting
moisture,
0.635–0.921,
7.214−18.564%,
Therefore,
multisource
recommended
This
approach
provide
support
making
intelligent
decisions
grid
land
lots.
Environmental Engineering Research,
Journal Year:
2024,
Volume and Issue:
30(4), P. 240339 - 0
Published: Dec. 2, 2024
Coal,
oil,
and
natural
gas
are
the
main
three
fossil
energy
that
produce
carbon.
Among
them,
which
is
contributor
to
carbon
emissions
rarely
studied.
In
this
work,
average
contribution
rate
of
predicted
based
on
an
innovative
two-stage
model
combining
optimal
layers
wavelet’s
orders
with
long
short-term
memory
optimized
by
improved
sparrow
search
algorithm.
The
experimental
results
demonstrate
using
wavelet
for
preprocessing
can
achieve
better
prediction
results,
compared
some
other
methods,
one-step
than
those
multi-step
prediction.
addition,
six
error
indicators
used
in
study
reasonable,
evaluation
indicator
more
reasonable.
conclusion
be
reached
order
from
high
low
gas,
petroleum,
coal
their
proportion
46.62%,
34.90%,
18.48%,
therefore,
short
future,
will
source
US.
