Journal of Physics Conference Series,
Год журнала:
2023,
Номер
2666(1), С. 012006 - 012006
Опубликована: Дек. 1, 2023
Abstract
Transmission
lines
are
directly
exposed
to
the
natural
environment
and
prone
failure
due
meteorological
factors.
A
novel
approach
for
diagnosing
transmission
line
faults
under
various
conditions
has
been
introduced.
This
method,
known
as
SDA-ISSA-XGBoost,
combines
power
of
Stacked
Denoising
Autoencoder
(SDA),
an
improved
Sparrow
Search
Algorithm
(ISSA)
enhanced
with
chaotic
mapping
sequences,
adaptive
weights,
iterative
local
search,
a
random
differential
mutation
strategy,
eXtreme
Gradient
Boosting
(XGBoost).
The
process
begins
SDA,
which
extracts
essential
features
from
initial
data.
Subsequently,
ISSA
is
applied
optimize
parameters
XGBoost
model.
results
in
ISSA-XGBoost
fault
diagnosis
performance
this
model
compared
PSO-XGBoost
SSA-XGBoost.
experimental
findings
demonstrate
that
achieves
impressive
accuracy
94.39%,
surpassing
both
SSA-XGBoost
by
6.54%
3.74%,
respectively.
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Сен. 17, 2024
Abstract
In
an
era
marked
by
growing
global
population
and
climate
variability,
ensuring
food
security
has
become
a
paramount
concern.
Rice,
being
staple
crop
for
billions
of
people,
requires
accurate
timely
yield
prediction
to
ensure
security.
This
study
was
undertaken
across
two
rice
seasons
in
the
Udham
Singh
Nagar
district
Uttarakhand
state
predict
at
45,
60
90
days
after
transplanting
(DAT)
through
machine
learning
(ML)
models,
utilizing
combination
optical
Synthetic
Aperture
Radar
(SAR)
data
conjunction
with
biophysical
parameters.
Results
revealed
that
ML
models
were
able
provide
relatively
early
estimates.
For
summer
rice,
eXtreme
gradient
boosting
(XGB)
best-performing
model
all
three
stages
(45,
60,
DAT),
while
kharif
DAT
XGB,
Neural
network
(NNET),
Cubist,
respectively.
The
combined
ranking
showed
accuracy
improved
as
date
approaches
harvest,
best
observed
both
rice.
Overall
rankings
indicate
top
NNET,
Support
vector
regression,
these
Random
Forest,
findings
this
offer
valuable
insights
into
potential
use
remote
sensing
parameters
using
which
enhances
planning
resource
management
enabling
more
informed
decision-making
stakeholders
such
farmers,
policy
planners
well
researchers.
Agronomy,
Год журнала:
2024,
Номер
14(10), С. 2262 - 2262
Опубликована: Окт. 1, 2024
Timely
and
accurate
prediction
of
winter
wheat
yields,
which
is
crucial
for
optimizing
production
management,
maintaining
supply–demand
balance,
ensuring
food
security,
depends
on
interactions
among
numerous
factors,
such
as
climate,
surface
characteristics,
soil
quality.
Despite
the
extensive
application
deep
learning
models
in
this
field,
few
studies
have
analyzed
effect
large-scale
geospatial
characteristics
neighboring
regions
crop
yields.
Therefore,
we
present
an
attention-based
spatio-temporal
Graph
Neural
Network
(ASTGNN)
model
coupled
with
multi-source
data
improved
accuracy
yield
estimation.
The
datasets
used
study
included
multiple
types
remote
sensing,
meteorological,
soil,
yield,
planting
area
Anhui,
China,
from
2005
to
2020.
results
showed
that
led
higher
performance
than
single-source
data,
enabled
yields
three
months
prior
harvest.
Furthermore,
ASTGNN
provided
better
two
traditional
(R2
=
0.70,
RMSE
0.21
t/ha,
MAE
0.17
t/ha).
enhances
by
incorporating
characteristics.
This
research
has
implications
improving
agricultural
promoting
development
digital
agriculture,
addressing
climate
change
agriculture.
Algorithms,
Год журнала:
2025,
Номер
18(2), С. 84 - 84
Опубликована: Фев. 5, 2025
Many
sciences
exploit
algorithms
in
a
large
variety
of
applications.
In
agronomy,
amounts
agricultural
data
are
handled
by
adopting
procedures
for
optimization,
clustering,
or
automatic
learning.
this
particular
field,
the
number
scientific
papers
has
significantly
increased
recent
years,
triggered
scientists
using
artificial
intelligence,
comprising
deep
learning
and
machine
methods
bots,
to
process
crop,
plant,
leaf
images.
Moreover,
many
other
examples
can
be
found,
with
different
applied
plant
diseases
phenology.
This
paper
reviews
publications
which
have
appeared
past
three
analyzing
used
classifying
agronomic
aims
crops
applied.
Starting
from
broad
selection
6060
papers,
we
subsequently
refined
search,
reducing
358
research
articles
30
comprehensive
reviews.
By
summarizing
advantages
applying
analyses,
propose
guide
farming
practitioners,
agronomists,
researchers,
policymakers
regarding
best
practices,
challenges,
visions
counteract
effects
climate
change,
promoting
transition
towards
more
sustainable,
productive,
cost-effective
encouraging
introduction
smart
technologies.
Proceedings of The International Conference on Data Science and Official Statistics,
Год журнала:
2023,
Номер
2023(1), С. 368 - 381
Опубликована: Дек. 29, 2023
In
the
era
of
modern
agriculture,
satellite
imagery
has
been
widely
used
to
monitor
crops,
one
which
is
paddy.
This
paper
tries
describe
vegetation
indices,
climate,
and
soil
index
features
related
paddy
plants
curates
a
collection
on
Google
Earth
Engine
(GEE).
reveals
how
GEE
can
be
collect
process
multimodal
form
precision
agriculture
dataset.
The
objective
this
study
establish
comprehensive
dataset
by
leveraging
crops.
data
collected
as
originates
from
306
locations
in
Karawang
Regency,
Indonesia,
during
2019-2020
period.
first
step,
we
identify
relevant
essential
for
crop
analysis.
Subsequently,
carefully
select
image
collections
within
based
these
features.
Afterward,
perform
acquisition
necessary
preprocessing
through
Colab
environment.
results
showed
that
Sentinel-2
outperforms
Landsat
8
terms
spatial
temporal
resolution.
Apart
that,
generated
successfully
captures
growth
patterns
plants.
Rice
yield
depends
on
factors
including
variety,
weather,
field
management,
nutrient
and
water
availability.
We
analyzed
important
drivers
variability
at
the
scale,
developed
forecast
models
for
crops
in
temperate
irrigated
rice
growing
region
of
Australia.
fused
a
time-series
Sentinel-1
Sentinel-2
satellite
remote
sensing
imagery,
spatial
weather
data
management
information,
while
phenology
was
predicted
using
previously
reported
models.
Higher
yields
were
associated
with
early
flowering,
higher
indices
indicating
nitrogen
status,
temperatures
around
successive
cropping
same
lower
yield.
which
aggregated
to
phenological
periods
provided
more
accurate
than
aggregating
calendar
periods.
Yield
particularly
depended
reflectances
vegetation
based
red
edge
short
wave
infrared
bands
just
before
minimum
temperature
flowering.
Final
trained
2018-2022
data,
applied
predicting
1580
fields
(43,700
hectares)
from
an
independent
season
challenging
conditions
(2023).
The
accuracy
improved
as
progressed,
by
30
days
after
flowering
reaching
RMSE=1.6
t/ha
Lin's
concordance
correlation
coefficient
(LCCC)
0.67
level.
Explainability
SHAP
method,
revealing
likely
causes
low
individual
fields,
status
during
due
late
sowing.
ability
predict
inter-annual
further
validated
2006-2017
achieving
RMSE=0.62
t/ha,
LCCC=0.6
over
seasons
sowing
methods.