Sustainability,
Год журнала:
2025,
Номер
17(10), С. 4711 - 4711
Опубликована: Май 20, 2025
Fueled
by
scientific
innovations
and
data-driven
approaches,
accurate
agriculture
has
arisen
as
a
transformative
sector
in
contemporary
agriculture.
The
present
investigation
provides
summary
of
modern
improvements
machine-learning
(ML)
strategies
utilized
for
crop
prediction,
accompanied
performance
exploration
models.
It
examines
the
amalgamation
sophisticated
technologies,
cooperative
objectives,
methodologies
designed
to
address
obstacles
conventional
study
possibilities
intricacies
precision
analyzing
various
models
deep
learning,
machine
ensemble
reinforcement
learning.
Highlighting
significance
worldwide
collaboration
data-sharing
activities
elucidates
evolving
landscape
farming
industry
indicates
prospective
advancements
sector.
Agronomy,
Год журнала:
2024,
Номер
14(3), С. 634 - 634
Опубликована: Март 21, 2024
This
study
explores
spectroscopy
in
the
350
to
2500
nm
range
for
detecting
powdery
mildew
(Erysiphe
necator)
grapevine
leaves,
crucial
precision
agriculture
and
sustainable
vineyard
management.
In
a
controlled
experimental
setting,
spectral
reflectance
on
leaves
with
varying
infestation
levels
was
measured
using
FieldSpec
4
spectroradiometer
during
July
September.
A
detailed
assessment
conducted
following
guidelines
recommended
by
European
Mediterranean
Plant
Protection
Organization
(EPPO)
quantify
level
of
infestation;
categorising
into
five
distinct
grades
based
percentage
leaf
surface
area
affected.
Subsequently,
data
were
collected
contact
probe
tungsten
halogen
bulb
connected
spectroradiometer,
taking
three
measurements
across
different
areas
each
leaf.
Partial
Least
Squares
Regression
(PLSR)
analysis
yielded
coefficients
determination
R2
=
0.74
0.71,
Root
Mean
Square
Errors
(RMSEs)
12.1%
12.9%
calibration
validation
datasets,
indicating
high
accuracy
early
disease
detection.
Significant
differences
noted
between
healthy
infected
especially
around
450
700
visible
light,
1050
nm,
1425
1650
2250
near-infrared
spectrum,
likely
due
tissue
damage,
chlorophyll
degradation
water
loss.
Finally,
Powdery
Mildew
Vegetation
Index
(PMVI)
introduced,
calculated
as
PMVI
(R755
−
R675)/(R755
+
R675),
where
R755
R675
are
reflectances
at
755
(NIR)
675
(red),
effectively
estimating
severity
(R2
0.7).
The
demonstrates
that
spectroscopy,
combined
PMVI,
provides
reliable,
non-invasive
method
managing
promoting
healthier
vineyards
through
practices.
Smart Agricultural Technology,
Год журнала:
2024,
Номер
8, С. 100488 - 100488
Опубликована: Июнь 15, 2024
Innovations
in
precision
agriculture
enhance
complex
tasks,
reduce
environmental
impact,
and
increase
food
production
cost
efficiency.
One
of
the
main
challenges
is
ensuring
rapid
information
availability
for
autonomous
vehicles
standardizing
processes
across
platforms
to
maximize
interoperability.
The
lack
drone
technology
standardisation,
communication
barriers,
high
costs,
post-processing
requirements
sometimes
hinder
their
widespread
use
agriculture.
This
research
introduces
a
standardized
data
fusion
framework
creating
real-time
spatial
variability
maps
using
images
from
different
Unmanned
Aerial
Vehicles
(UAVs)
Site-Specific
Crop
Management
(SSM).
Two
interpolation
methods
were
used
(Inverse
Distance
Weight,
IDW,
Triangulated
Irregular
Networks,
TIN),
selected
computational
efficiency
input
flexibility.
proposed
can
UAV
image
sources
offers
versatility,
speed,
efficiency,
consuming
up
98
%
less
time,
energy,
computing
than
standard
photogrammetry
techniques,
providing
field
information,
allowing
edge
incorporation
into
acquisition
phase.
Experiments
conducted
Spain,
Serbia,
Finland
2022
under
H2020
FlexiGroBots
project
demonstrated
strong
correlation
between
results
this
method
those
techniques
(up
r
=
0.93).
In
addition,
with
Sentinel
2
satellite
was
as
that
obtained
photogrammetry-based
orthomosaics
0.8).
approach
could
support
irrigation
leak
detection,
soil
parameter
estimation,
weed
management,
integration
Agriculture,
Год журнала:
2024,
Номер
14(9), С. 1473 - 1473
Опубликована: Авг. 29, 2024
Agriculture
is
a
labor-intensive
industry.
However,
with
the
demographic
shift
toward
an
aging
population,
agriculture
increasingly
confronted
labor
shortage.
The
technology
for
autonomous
operation
of
agricultural
equipment
in
large
fields
can
improve
productivity
and
reduce
intensity,
which
help
alleviate
impact
population
on
agriculture.
Nevertheless,
significant
challenges
persist
practical
application
this
technology,
particularly
concerning
adaptability,
operational
precision,
efficiency.
This
review
seeks
to
systematically
explore
advancements
unmanned
operations,
focus
onboard
environmental
sensing,
full-coverage
path
planning,
control
technologies.
Additionally,
discusses
future
directions
key
technologies
fields.
aspires
serve
as
foundational
reference
development
large-scale
equipment.
Horticulturae,
Год журнала:
2024,
Номер
10(9), С. 1006 - 1006
Опубликована: Сен. 22, 2024
The
accurate
identification
of
tomato
maturity
and
picking
positions
is
essential
for
efficient
picking.
Current
deep-learning
models
face
challenges
such
as
large
parameter
sizes,
single-task
limitations,
insufficient
precision.
This
study
proposes
MTS-YOLO,
a
lightweight
model
detecting
fruit
bunch
stem
positions.
We
reconstruct
the
YOLOv8
neck
network
propose
high-
low-level
interactive
screening
path
aggregation
(HLIS-PAN),
which
achieves
excellent
multi-scale
feature
extraction
through
alternating
fusion
information
while
reducing
number
parameters.
Furthermore,
utilize
DySample
upsampling,
bypassing
complex
kernel
computations
with
point
sampling.
Moreover,
context
anchor
attention
(CAA)
introduced
to
enhance
model’s
ability
recognize
elongated
targets
bunches
stems.
Experimental
results
indicate
that
MTS-YOLO
an
F1-score
88.7%
[email protected]
92.0%.
Compared
mainstream
models,
not
only
enhances
accuracy
but
also
optimizes
size,
effectively
computational
costs
inference
time.
precisely
identifies
foreground
need
be
harvested
ignoring
background
objects,
contributing
improved
efficiency.
provides
technical
solution
intelligent
agricultural
