Agriculture,
Год журнала:
2024,
Номер
14(12), С. 2326 - 2326
Опубликована: Дек. 19, 2024
This
study
accurately
inverts
key
growth
parameters
of
rice,
including
Leaf
Area
Index
(LAI),
chlorophyll
content
(SPAD)
value,
and
height,
by
integrating
multisource
remote
sensing
data
(including
MODIS
ERA5
imagery)
deep
learning
models.
Dehui
City
in
Jilin
Province,
China,
was
selected
as
the
case
area,
where
multidimensional
vegetation
indices,
ecological
function
parameters,
environmental
variables
were
collected,
covering
seven
stages
rice.
Data
analysis
parameter
prediction
conducted
using
a
variety
machine
models
Partial
Least
Squares
(PLSs),
Support
Vector
Machine
(SVM),
Random
Forest
(RF),
Long
Short-Term
Memory
Networks
(LSTM),
among
which
LSTM
model
demonstrated
superior
performance,
particularly
at
multiple
critical
time
points.
The
results
show
that
performed
best
inverting
three
with
LAI
inversion
accuracy
on
21
August
reaching
coefficient
determination
(R2)
0.72,
root
mean
square
error
(RMSE)
0.34,
absolute
(MAE)
0.27.
SPAD
same
date
achieved
an
R2
0.69,
RMSE
1.45,
MAE
1.16.
height
25
July
reached
0.74,
2.30,
2.08.
not
only
verifies
effectiveness
combining
advanced
algorithms
but
also
provides
scientific
basis
for
precision
management
decision-making
rice
cultivation.
Heliyon,
Год журнала:
2024,
Номер
10(8), С. e29837 - e29837
Опубликована: Апрель 1, 2024
Unmanned
aerial
vehicle
(UAV)
granular
fertilizer
spreading
technology
has
been
gradually
applied
in
agricultural
production.
However,
the
process
of
operation,
actual
influence
effect
each
factor
field
operation
is
still
unclear.
Based
on
self-developed
UAV
system,
this
paper
explores
effects
three
factors,
baffle
retraction
(B),
disc
speed
(D),
and
flight
altitude
(H),
scenarios
through
orthogonal
test
taking
coefficient
variation
(Cv)
relative
error
application
rate
(λ)
as
evaluation
indexes.
The
results
showed
that
optimal
level
combination
Cv
was
11.23
%
for
BbDbHa
(the
6
%,
600r/min,
height
1.5
m)
at
2
m/s.
best
λ
BbDbHb
7.99
m).
In
addition,
by
analysing
weather
vortex
rice
canopy
effect,
it
found
less
while
caused
airflow
rotor
a
certain
which
also
relatively
easy
to
ignore
operations.
study
can
be
used
explore
operational
UAVs
field,
will
help
promote
development
provide
reference
precision
aviation.
Agronomy,
Год журнала:
2024,
Номер
14(6), С. 1324 - 1324
Опубликована: Июнь 19, 2024
For
agricultural
production,
improving
the
rice
harvest
index
(HI)
through
management
practices
is
a
major
means
to
enhance
water
and
N
utilization
efficiency
yield.
Both
irrigation
regimes
nitrogen
(N)
rates
are
important
aspects
of
practices.
However,
it
unclear
how
HI
affected
by
N.
This
study
aimed
clarify
mechanism
underlying
response
N,
explore
most
suitable
water-saving
reduction
ensure
A
two-year
(2021~2022)
field
experiment
was
conducted
on
Mollisols
in
Northeast
China.
In
this
experiment,
nine
treatments
were
performed,
involving
three
(flooded
irrigation,
controlled
“thin-shallow-wet-dry”
irrigation)
(110,
99,
88
kg/ha).
The
agronomic
traits
transfer
photoassimilates
under
different
observed
studied;
HI,
WUE,
NUE
calculated
analyzed.
highest
achieved
with
99
kg/ha
rate,
at
values
0.622
0.621
2021
2022,
respectively.
Controlled
(CI)
an
appropriate
rate
increased
proportion
productive
tillers,
dry
matter
non-structural
carbohydrates
(NSCs),
sugar–spikelet
ratio,
grain–leaf
leaf
area
(LAI)
during
heading–flowering
stage.
subsequent
analysis
indicated
that
main
reason
for
increase
ratio
high
yield
increasing
thousand-grain
weight.
present
suggested
not
only
led
fertilizer
resource
savings
but
also
improved
characteristics
growth
enhanced
transport
capacity.
Thus,
these
have
enormous
potential
Therefore,
regulating
methods
should
be
considered
strategy
Notulae Botanicae Horti Agrobotanici Cluj-Napoca,
Год журнала:
2024,
Номер
52(2), С. 13728 - 13728
Опубликована: Май 21, 2024
Nitrogen
fertilizer
levels
significantly
affect
crop
growth
and
development,
necessitating
precision
management.
Most
studies
focus
on
nitrogen
nutrient
estimation
using
vegetation
indices
textural
features,
overlooking
the
diagnostic
potential
of
color
features.
Hence,
we
investigated
cotton
nutrition
status
unmanned
aerial
vehicle
(UAV)
image
features
index
(NNI).
Random
frog
algorithm
-
random
forest-screened
feature
sets
correlated
with
NNI,
which
were
substituted
into
four
machine
learning
algorithms
for
NNI
modeling.
The
composite
scores
(F)
optimal
calculated
coefficient
variation
method
comprehensive
diagnosis.
Validation
model
determining
critical
concentration
in
yielded
a
determination
R2
=
0.89,
root
mean
square
error
RMSE
0.50
g
(100
g)-1,
absolute
MAE
0.44,
demonstrating
improved
performance.
Additionally,
our
novel
constructed
based
exhibited
R2c
0.97,
RMSEc
0.02,
MAEc
R2v
0.85,
RMSEv
0.05,
MAEv
0.04.
Polynomial
fitting
indicated
that
was
reliable
following
criterion:
0.48
<
F2
0.67
overapplication,
whereas
or
>
deficiency.
This
study
demonstrates
superior
effectiveness
UAV
RGB
quick,
accurate
diagnosis
levels,
will
help
guide
application.
